System and method for real-time detection of mastitis indicators in bovine milk

Abstract

Milk quality can be compromised by physiological conditions affecting dairy mammals, notably mastitis. Mastitis is an inflammatory disease of the mammary gland that may pose significant health and economic challenges. To address this, a system is proposed for monitoring at least one mammal to predict the onset of a clinical condition, such as, for example, mastitis. The system may be configured to sense one or more characteristics descriptive of mammal-related information, receive sensor data corresponding to those characteristics, and process the data to forecast the onset of mastitis within an upcoming time interval. Early detection enables timely intervention, promoting animal welfare and preserving milk quality.

Description

[0001] SYSTEM AND METHOD FOR REAL-TIME DETECTION OF MASTITIS INDICATORS IN BOVINE MILK

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003]

[0001] This patent application claims priority and / or benefit from the following US provisional patent application: US 63 / 708,353, filed October 17, 2024, titled "SYSTEM AND METHOD FOR DETECTING PRE- CLINICAL AND CLINICAL MASTITIS AND MACRONUTRIENTS MEASUREMENT IN MILK", and Israel patent application 318919, filed February 09, 2025, titled "SYSTEM AND METHOD FOR REAL-TIME DETECTION OF MASTITIS INDICATORS IN BOVINE MILK".

[0004]

[0002] It should be noted that the abovementioned US provisional patent application and Israel patent application are incorporated herein by reference in its entirety for all purposes. To the extent required, features, examples, and / or technical explanations from the above-referenced applications that are necessary for support, enablement, and / or priority are expressly disclosed herein in full and should be considered repeated in the present application.

[0005] BACKGROUND

[0006]

[0003] Commercial milk production may encompass the risk of widespread milk contamination, thus a system for analyzing milk samples to determine their quality and detect animal-borne mastitis would be desirable.

[0007]

[0004] Commercial milk is a vital source of nutrition for humans, providing essential nutrients such as protein, calcium, and vitamins. However, the quality of milk can be affected by numerous factors, including the health of the dairy mammals.

[0008]

[0005] Mastitis, an inflammation of the mammary gland, is a common and costly disease in dairy mammals that can significantly impact milk quality. Thus, it is crucial to detect and treat mastitis promptly to maintain the health of the mammals and ensure the production of high-quality milk.

[0009]

[0006] The description above is presented as a general overview of related art in this field and should not be construed as an admission that any of the information it contains constitutes prior art against the present patent application. BRIEF DESCRIPTION OF THE FIGURES

[0010]

[0007] In the following description, for purposes of explanation and not limitation, details and descriptions are set forth to provide a thorough understanding of the present disclosure.

[0011]

[0008] However, it will be apparent to those skilled in the art that the present disclosure may be practiced in other embodiments that depart from these details and descriptions.

[0012]

[0009] In the following description, the figures which are described illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.

[0013]

[0010] For simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity of presentation.

[0014] [Oil] Furthermore, reference numerals may be repeated among the figures to indicate corresponding and / or analogous elements. References to previously presented elements are implied without necessarily further citing the drawing and / or description in which they appear. The number of elements shown in the Figures should by no means be construed as limiting and is for illustrative purposes only. The figures are listed below.

[0015]

[0012] Figure 1 schematically depicts the first optional implementation of the system for real-time detection of mastitis indicators in bovine milk, according to some embodiments.

[0016]

[0013] Figure 2 schematically depicts a second optional implementation of the system for real-time detection of mastitis indicators in bovine milk, according to some embodiments.

[0017]

[0014] Figure 3 schematically depicts a third optional implementation of the system for real-time detection of mastitis indicators in bovine milk, according to some embodiments.

[0018]

[0015] Figure 4 schematically depicts a block diagram of an optional implementation of the system, according to some embodiments.

[0019]

[0016] Figure 5 schematically depicts a high-level block diagram of an optional system algorithm, according to some embodiments.

[0020]

[0017] Figure 6 schematically depicts a flow-chart illustrative of the system's action steps, e.g., method, according to some embodiments.

[0021]

[0018] Figure 7 schematically depicts a bar graph illustrative of measured value range of mammalian milk characteristics corresponding to a mammal classification, according to some embodiments.

[0022]

[0019] Figure 8 schematically depicts a data category flow-chart, according to some embodiments.

[0020] Figure 9 schematically depicts an illustration presenting the constitutes of mammal related information, according to some embodiments.

[0023]

[0021] Figure 10 schematically depicts a flow-chart illustrative of an optional system's action steps, e.g., method, according to some embodiments.

[0024]

[0022] Figure SI shows a graph of measured fat vs predicted fat, according to some embodiments.

[0025]

[0023] Figure S2 shows a graph of measured fat vs predicted fat, according to other embodiments.

[0026]

[0024] Figure S3 shows a graph of measured protein vs predicted protein, according to some embodiments.

[0027]

[0025] Figure S4 shows a graph of measured lactose vs predicted lactose, according to some embodiments.

[0028]

[0026] Figure S5 shows an array of flow reduction apparatuses and a single flow reduction apparatus, according to some embodiments.

[0029]

[0027] Figure S6 shows an exploded view of a flow reduction apparatus, according to some embodiments.

[0030]

[0028] Figure S7 shows a cross-sectional view of a flow reduction apparatus, according to some embodiments.

[0031]

[0029] Figure S8 shows an optional coupling of the capping module with the receiving chamber, according to some embodiments.

[0032]

[0030] Figure S9 shows an exploded view of a different flow reduction apparatus, according to some embodiments.

[0033]

[0031] Figure S10 shows a cross-sectional view of a different flow reduction apparatus, according to some embodiments.

[0034]

[0032] Figure Sil shows a first and a second receiving chamber configuration, according to some embodiments.

[0035]

[0033] Figure S12 shows a cross-sectional view of the first configuration of the receiving chamber, according to some embodiments.

[0036]

[0034] Figure S13 shows a cross-sectional view of the second configuration of the receiving chamber, according to some embodiments.

[0037]

[0035] Figure S14 shows an additional cross-sectional view of the second configuration of the receiving chamber, according to some embodiments.

[0038]

[0036] Figure Pl shows an additional graph of measured fat vs predicted fat, where values on the graph are associated with milk from a single cow, according to some embodiments.

[0037] Figure P2 shows an additional graph of measured fat vs predicted fat, where values on the graph are associated with milk in a milk tank, according to some embodiments.

[0039]

[0038] Figure P3 shows an additional graph of measured protein vs predicted protein, where values on the graph are associated with milk from a single cow, according to some embodiments.

[0040]

[0039] Figure P4 shows an additional graph of measured protein vs predicted protein, where values on the graph are associated with milk in a milk tank, according to some embodiments.

[0041]

[0040] Figure P5 shows an inline measurement graph of sample index vs intensity, according to some embodiments.

[0042]

[0041] Figure P6 shows an inline fat model graph of measured fat vs predicted fat, according to some embodiments.

[0043] DETAILED DESCRIPTION

[0044]

[0042] Commercial mammalian milk (MM) production encompasses the risks of milk contamination and widespread consumer affects, thus a system for analysing milk samples to determine their quality and detect different forms of animal-borne mastitis is suggested to be implemented. The samples may be assessed for quality and / or contamination through sensing and / or computing capabilities upon which corresponding feedback may be provided.

[0045]

[0043] Previously, milk quality and / or mastitis detection systems may have integrated methods for monitoring physical characteristics of a mammal and its respective MM product. Physical characteristics of interest were detected by chemical, optical, electrical, and / or mechanical properties measurement schemes.

[0046]

[0044] Approaches of photoelectric detection schemes, analytical reagent schemes and / or colorimetric schemes may affect the prediction validity of milk quality and / or mastitis detection.

[0047]

[0045] In some examples, the above approaches may not address subclinical and / or preclinical mastitis. Furthermore, the above approaches may lack the capability to determine a probability of a clinical condition impending mastitis onset within an upcoming time interval, or later, e.g., within 1 hour or later, within 12 hours or later, within 24 hours or later, within 2-7 days, or later.

[0048]

[0046] Embodiments of the present disclosure may relate to the field of monitoring, analyzing, detecting and / or predicting MM quality technologies, including, for example, a system configured for, e.g., determining a probability of a clinical condition impending mastitis onset within an upcoming time interval. The system may be configured to generate and / or present system output, comprising, for example, instruction output adapted to provide feedback descriptive and / or suggestive of preventative measures. The system may be configured to sense MM characteristic of milk flowing (e.g., freely) in a milking pipeline (also: milk line) and, for example, analyze, detect, and / or predict characteristics of the MM flowing in the pipeline, e.g., in real-time, or substantially in real-time. In some embodiments, the system or components thereof may be configured to allow retrofitting (e.g., upgrading) one or more existing milk pipelines for analyzing MM flowing in existing milking pipelines.

[0049]

[0047] Furthermore, embodiments of the present disclosure may concern a system for providing a user with a prediction and / or trajectory and / or prognosis intended for determining the probability of clinical, subclinical, and / or preclinical mastitis in at least one mammal and / or a plurality of mammals employed for producing MM. The term "clinical" refers to a disease state that has recognizable signs and / or symptoms. The term "subclinical" refers to an infection without recognizable disease. The term "preclinical" refers to a state where signs are indicative of a possible impending infection.

[0048] In some embodiments, the referenced at least one mammal may comprise cattle, buffaloes, goats, sheep, camels, yaks, horses, reindeers, donkeys, and / or any lactating mammal group.

[0050]

[0049] In some embodiments, the cattle may comprise cows, bulls, oxen, and / or calves.

[0051]

[0050] In some embodiments, the system may comprise at least one memory element configured to store data and / or executable instructions.

[0052]

[0051] In some embodiments, the system may comprise at least one processing element, e.g., at least one processor, which may be operable to execute instructions stored in the at least one memory element.

[0053]

[0052] In some embodiments, the system may employ one or more sensors configured to sense, for example, a physical and / or chemical and / or biological quantity and / or characteristic. The sensor may convert the sensed quantity / characteristic into an electrical signal, which may be converted into corresponding data. The sensor data may relate to at least one group-level characteristic, individual mammal characteristic at least one respective MM product characteristic, or any combination of the aforesaid.

[0054]

[0053] In some embodiments, a mammal characteristic may comprise, for example: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk electrical characteristic, or any combination of the aforesaid. By way of illustration only, mammal milk fat level can be measured by a sensor configured to measure at wavelengths ranging from 890 to 910 nm, e.g., at 900 nm. For example, by emitting light towards the milk at a wavelength or wavelengths ranging from 890 to 910 nm, e.g., at 900 nm, and detecting light reflected from the milk and / or transmitted through the milk, the system may determine the level of fat in the milk. In some examples, the level of fat may be determined based on detected light ranging for example from 890 to 910 nm, e.g., at 900 nm.

[0055]

[0054] In some embodiments, the mammal characteristic may comprise, for example: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; or any combination of the aforesaid.

[0056]

[0055] In some embodiments, the mammal characteristic may comprise, for example: mammal breed or mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level, or any combination of the aforesaid.

[0057]

[0056] In some embodiments, the mammal characteristics may comprise, for example: mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

[0058]

[0057] In some embodiments, the mammal characteristics may comprise, for example, mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; and / or mammal milk blood level.

[0058] In some embodiments, the analyzing of sensor data by at least one processor may be configured for detecting mastitis and / or preclinical mastitis, and / or configured for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0059]

[0059] In some embodiments, the executable instructions, which may be stored in at least one memory element and operably executed by at least one processor, may, for example, comprise:

[0060]

[0060] receiving sensor data, which may be descriptive of at least one mammal characteristic from the at least one sensor; and / or

[0061]

[0061] processing the sensor data, which may be configured for detecting mastitis, for detecting preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0062]

[0062] In some embodiments, the processing of the sensor data may be performed by at least one analysis model, for example, a trained machine-learning (ML) model, a classifier, and / or a rule-based model.

[0063]

[0063] In some embodiments, the received sensor data, and / or the processing of the received sensor data, may be descriptive of a plurality of distinct mammal characteristics to collectively factor-in the plurality of distinct mammal and / or MM characteristics.

[0064]

[0064] In some embodiments, the detection of mastitis and / or preclinical mastitis may be performed in real-time and / or substantially in real-time with respect to the sensing of the at least one mammal and / or MM characteristic.

[0065]

[0065] In some embodiments, the determining of a probability of a clinical condition impending mastitis onset within an upcoming time interval may be performed in real-time and / or substantially in real-time with respect to the sensing of the at least one mammal and / or MM characteristic.

[0066]

[0066] In some embodiments, determining a probability of a clinical condition may be indicative of a likelihood, severity, and / or timing of preclinical mastitis. In addition, the determined probability may be utilized for prediction, classification, risk assessment, and / or dynamic adjustment of the system behavior.

[0067]

[0067] The term "severity" may refer to the dynamics of a measured trend relating to a mammal and / or MM characteristic value. For example, the dynamics of a measured trend relating to SSC may comprise the dynamic increase of 10%, 25%, 33%, 50% or more from the initial measured SCC value. It should be noted that additional mammal and / or MM characteristic value may be measured to infer clinical and / or preclinical severity.

[0068]

[0068] The term "clinical condition" may, interchangeably, refer to "clinical" and / or "preclinical" conditions. In some examples, detecting, predicting and / or determining a probability may be utilized primarily in relation to the onset of impending mastitis. Additional supplementary clinical conditions may be of interest when utilizing the system capabilities including, for example: clinical ketosis, rumen acidosis, metabolic alkalosis, udder infection, subacute ruminal acidosis (SARA), fertility related conditions, e.g., pregnancy, metritis, lameness, hypocalcemia, heat-stress, or any combination thereof.

[0069] Table 1 below provides lists of examples of various clinical conditions / states and their associated biomarkers:

[0070]

[0069] Clinical Ketosis may present more severe metabolic signs than subclinical ketosis and may be detected by embodiments via milk and / or blood, e.g., BHBA > 1.2 mmol / L. Symptoms include loss of appetite, decreased milk production, and acetone breath.

[0071]

[0070] Pregnancy may be detected by embodiments via pregnancy-associated glycoproteins (PAGs) in milk and / or blood.

[0072]

[0071] Embodiments may be configured to provide pH-based insights into udder health, rumen function, and dietary buffering.

[0073]

[0072] Example parameter values: normal milk pH values may be in the range of, e.g., 6.6-6.8. Deviations may be, e.g., pH < 6.4 may give an indication regarding possible rumen acidosis and / or subclinical mastitis; e.g., pH > 6.9 may provide an indication regarding possible metabolic alkalosis and / or udder infection.

[0074]

[0073] Supplementary conditions may represent comorbidities, contributing factors, and / or secondary manifestations that are relevant to the overall clinical assessment of a mammal and / or a MM characteristic. The supplementary clinical conditions may be detected through the same sensing modalities used for the primary condition and / or through additional sources of clinical data.

[0075]

[0074] Furthermore, the system may correlate and / or otherwise analyze the supplementary clinical conditions with the primary clinical condition, e.g., the onset of impending mastitis, to enhance, for example, diagnostic accuracy, enable risk assessment, guide therapeutic decisions, prediction, classification and / or support herd health management. Such analysis (e.g., correlation) may be established through one or more analysis models.

[0076]

[0075] Embodiments may be employed for trait-enhancement; culling; genetic ROI; reduction and / or minimizing use of antibiotics and / or of other medication; cow grouping having similar clinical profiles for batch-specific production.

[0077]

[0076] In some embodiments, at least one mammal and / or MM characteristic may pertain to an individual mammal, a group of mammals, a herd, dairy farm, and / or a plurality of mammals located in, and / or related to, a geographic region.

[0078]

[0077] In some embodiments, processing data descriptive of mammal-related information may involve rule-based logic, statistical classifiers, machine learning (ML) models, artificial intelligence (Al) algorithms, deterministic methods, or any combinations thereof. The data may relate to various milk components like, for example, fat, protein, and / or lactose, may be processed using a range of advanced (e.g., ML and / or rule-based) algorithms, for example, to detect patterns, trends, and / or correlations, and / or to make predictions.

[0079]

[0078] In some embodiments, the processor may employ analysis models, which may comprise, for example, statistical models. In some examples, such statistical models may be implemented as mathematical representations of one or more real-world phenomena and / or processes using methods and techniques to analyze and / or make predictions based on sensor data. The models may be interpretable relative to an individual mammal and / or relative to a population of mammals.

[0080]

[0079] In some embodiments, the models may include, for example, linear regression, logistic regression, time series models, Bayesian models, and / or the like, and / or may for example be used to describe and / or express the relationships between variables, understand the underlying structure of data accordingly and make predictions about future events and / or outcomes. Machine learning models may be based (e.g., trained on their respective specific training datasets) using supervised approaches and / or unsupervised approaches.

[0081]

[0080] In some embodiments, the models may be expressed by at least one trained model that may comprise one or more rule-based models, ML models and / or classifiers, for example, one of the following: a decision tree, a random forest ensemble, a gradient boost based (XGBoost) classifier, a neural network, a Convolutional Neural Network (CNN), a Deep Learning Neural Network (DNN), or any combination of the aforesaid. Further examples of machine learning procedures suitable for implementing embodiments include, without limitation, one the following: clustering, association rule algorithms, feature evaluation algorithms, subset selection algorithms, classification rules, cost-sensitive classifiers, vote algorithms, stacking algorithms, Bayesian networks, instance-based algorithms, linear modeling algorithms, k-nearest neighbors (KNN) analysis, ensemble learning algorithms, probabilistic models, graphical models, logistic regression methods (including multinomial logistic regression methods), gradient ascent methods, singular value decomposition methods, principle component analysis, one or more classifiers, statistical classifiers and / or other statistical models, neural networks (NN) of various architectures (e.g., graph NN, fully connected NN, deep, encoder-decoder NN, recurrent NN), support vector machines (SVM), boosting, random forest, a regressor, and / or any other commercial, non-commercial, and / or open source package, and / or non-open source package, allowing regression, classification, dimensional reduction, supervised, unsupervised, semi-supervised and / or reinforcement learning, or any combination of the aforesaid. In some examples, any one of the models disclosed herein may be disclaimed, separately or in any combination.

[0082]

[0081] Specific ML model(s) may generate the respective target specific priority list as a whole, single, simultaneous outcome. Alternatively, or additionally, specific ML model(s) may generate numerical scores for each parameter value relating to mammal information (e.g., sequentially), and the respective list is generated (by the respective ML model, and / or by other code that receives the scores) by ranking parameters according to respective scores.

[0083]

[0082] For example, XGBoost (Extreme Gradient Boosting) can be used to build highly accurate predictive models, efficiently handling large and complex datasets to predict milk quality with precision. In addition, K- Means clustering can provide an unsupervised approach to grouping milk samples based on different patterns, helping to identify natural clusters related to, e.g., different milk quality levels, anomalies, and / or contamination risks. These ML techniques allow the system to provide real-time, high-accuracy analysis of milk composition. By way of example only, when training an XGBoost model on an imbalanced dataset, the model may heavily favor the majority class, leading to relatively inferior performance in predicting minority class instances. Applying Synthetic Minority Oversampling Technique (SMOTE) before training helps create a more balanced dataset, improving model generalization and performance.

[0084]

[0083] ML algorithms may not only utilize raw data but also derive features that incorporate different mathematical, physical, and / or chemical models. For instance, spectral features (e.g., characteristics and / or "fingerprints") can be augmented by applying known physical laws, such as, for example, Beer- Lambert's law, and / or through chemical models that quantify specific milk components. By combining raw data with these model-derived features, the system may achieve higher precision in, e.g., identifying and / or predicting milk quality. This fusion of feature engineering from various domains may enhance the interpretability and robustness of the models, allowing the system to more accurately account for complex interactions within the data.

[0085]

[0084] In some embodiments, the system may incorporate advanced deep learning architectures to further enhance its analytical capabilities. Convolutional Neural Networks (CNNs) can be used to analyze high-dimensional data by automatically learning prominent features and patterns. This may be valuable for detecting subtle variations in milk quality that may arise from changes in fat and / or protein content. In some examples, Deep Neural Networks (DNNs) can be employed to model complex, non-linear relationships between the data and milk quality attributes. These networks, in any combination with features derived from physical and chemical models, provide deeper insights into the data, enabling more accurate predictions. More architectures, such as, for example, U-Net, Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks can be used for segmentation, time-sensitive and / or other tasks.

[0086]

[0085] In some embodiments, deterministic approaches are also used to complement the analysis. By applying physical models such as, for example, Beer-Lambert's law, the system can provide quick, interpretable results based on known physical principles. These deterministic methods an offer transparency and / or predictability, ensuring that the device can deliver (e.g., real-time) estimates of specific milk components in situations requiring fast, reliable outputs, together without the need for a large database.

[0087]

[0086] In some embodiments, a hybrid approach of combining deterministic methods with ML and Al algorithms may ensure a balance between interpretability and / or adaptability, and / or may enhance the capacity to monitor and improve, for example, milk quality, providing dairy producers with a powerful tool for ensuring the safety, quality, and / or consistency of cow milk production.

[0088]

[0087] In some embodiments, the training of the ML model(s) may be done, e.g., as known in the art, for example, by allocating a plurality of non-overlapping subsets (groups) of the labeled training samples to train, test, and / or optionally validate the ML model(s) and / or verify the ML model(s) outputs.

[0089]

[0088] For example, a first subset of the labeled training samples may be allocated to a training dataset used to train the ML model(s), a second subset may be allocated to a test subset used to test the ML model(s), and / or optionally, a third subset may be allocated to a validation dataset used to validate the ML model(s).

[0090]

[0089] In some examples, analysis models may be expressed by a linear and / or non-linear regression model, which may be based on a combination of the input features and / or a time series model.

[0091]

[0090] In some examples, system analysis models may be modelled by a logistic regression model that estimates the probability of the output variable belonging to a specific category based on a linear combination of the input features and / or a time series model that receives the data as time series.

[0092]

[0091] In some examples, a series model may be employed, such as, for example, an autoregressive model and / or moving average model, may capture the temporal dependencies in the data and can be used to predict future values of the time series and / or the probability of an event and / or state occurring at a specific time point.

[0093]

[0092] The term "models" may refer, but not limited, to a plurality of model types implementable by the system with the aim of, e.g., continuously, predicting the probability of at least one mammal characteristic and / or at least one respective MM product characteristic, which may be related to subclinical and / or preclinical mastitis in a mammal and / or a plurality of mammals employed for producing MM. It is noted that any mammal characteristic mentioned herein may be used alone, or in any combination by the system and / or method disclosed herein. In some examples, any mammal characteristic may be disclaimed as being employed by the system and / or by the method disclosed herein.

[0094]

[0093] In an embodiment, such models may comprise, for example: parametric statistical models, nonparametric statistical models, clustering models, nearest neighbor models, regression methods, and / or machine-learning models such as, for example, engineered (artificial) neural networks.

[0095]

[0094] In some embodiments, models may include assessing influence weights for at least one group-level characteristic, individual characteristic of a mammal and / or at least one characteristic of the mammal respective MM product to predict a health-state of a mammal and / or its respective MM product in relation to at least one MM contamination marker and / or threshold value of at least one group-level characteristic, individual characteristic of a mammal and / or MM characteristic.

[0096]

[0095] In some embodiments, models may employ, for example: generalized linear models, neural networks, and / or other mathematical, computational, and / or statistical functions dependent on at least one group-level characteristic, individual characteristic of a mammal and / or MM characteristic, which may include at least one distinguishable influence weight.

[0097]

[0096] The term "influence weights" may refer to a computational construct configured to account for the contribution of a specific group-level characteristic, individual characteristic of a mammal and / or the respective MM characteristic in relation, for example, to at least one MM contamination marker.

[0098]

[0097] Furthermore, the term "influence weights" may refer to the relative contribution of each mammal characteristic to the overall system prediction output.

[0099]

[0098] In some embodiments, the system may pertain to a system which may implement models configured for various system adaptations and / or predictions, comprising, for example, adaptively and / or dynamically changing the thresholds values, e.g., for assessing preclinical and / or subclinical mastitis within, for example, at least one mammal in at least one a dairy farm.

[0100]

[0099] The term "static thresholds" may refer to predetermined thresholds that remain constant.

[0101]

[0100] The term "dynamic thresholds" may refer to forcefully changed thresholds, for example, at a certain time of day, and / or a certain day of the year.

[0101] In some embodiments, adaptive thresholds may be changed in response to changes in characteristics of the mammal, characteristics of the network, farming system, treatment regime, etc., and may vary depending on a variety of corresponding parameters.

[0102]

[0102] Embodiments of systems may, additionally and / or alternatively, pertain to evaluating the healthstate of a mammal comprising, for example, prodromal, latent, asymptomatic, clinical, and / or convalescent state of a mammal.

[0103]

[0103] It should be noted that the terms "correlation," "association," "correspondence" as well as any grammatical variation thereof, may be used interchangeably. In some embodiments, these terms may refer to any and all techniques by which a relationship between two or more data sets may be established, inferred, and / or mapped. Unless otherwise specified, these terms encompass statistical inference, probabilistic modeling, rule-based mapping, machine-learning-based inference, pattern matching, feature linking, or any other method capable of deriving a relationship between data elements.

[0104]

[0104] In some embodiments, the phrase "anomaly of a mammal characteristic" may refer to an anomalous value descriptive of at least one mammal characteristic, for example, by exceeding and / or dropping below at least one threshold value, and / or by exhibiting less probable value across a plurality of corresponding values.

[0105]

[0105] Additionally, and / or alternatively, the phrase "anomaly of a mammal characteristic" may refer to an anomalous value descriptive of at least one mammal characteristic, for example, by deviating from known values recorded in one the following, for example, professional literature, verified database empirical results, in previous measurements, or any combination of the aforesaid.

[0106]

[0106] In some embodiments, the system may be configured to distinguish at least between a first anomaly of a mammal characteristic that may be related to pre-clinical mastitis, and a second anomaly of a mammal characteristic that is not related to the pre-clinical mastitis.

[0107]

[0107] In some embodiments, the system may be configured to distinguish at least between a first anomaly of a mammal characteristic that may be related to clinical mastitis, and a second anomaly of a mammal characteristic that is not related to the clinical mastitis.

[0108]

[0108] In some embodiments, the system may be configured to distinguish at least between a first anomaly of a mammal characteristic that may be related to pre-clinical mastitis, and a second anomaly of a mammal characteristic that is not related to the clinical mastitis.

[0109]

[0109] In some embodiments, the system may be configured to distinguish at least between a first anomaly of a mammal characteristic that may be related to pre-clinical mastitis, and a second anomaly of a mammal characteristic that is not related to pre-clinical mastitis.

[0110] In some embodiments, the system may be configured to distinguish at least between a first anomaly of a mammal characteristic that may be related to clinical mastitis, and a second anomaly of a mammal characteristic that is not related to the clinical mastitis.

[0110]

[0111] In some embodiments, the processing of the sensor data comprises comparing at least some of the sensor data descriptive of one or more of the at least one mammal characteristic against one or more thresholds associated with a corresponding normal, e.g., common, probable, etc., and / or abnormal, e.g., anomalous, mammal characteristic parameter values.

[0111]

[0112] The term "threshold" may refer, but not limited, to a static and / or dynamic baseline, which may be indicative of at least one value descriptive of at least one group-level characteristic, individual characteristic of a mammal and / or MM characteristic, which may be associated with a health-state of a mammal.

[0112]

[0113] In some embodiments, an example threshold for analyzing input data may include, for example:

[0113]

[0114] a predetermined and / or procedurally modelled threshold, generated in relation to at least one database and / or accumulative sensor data history; and / or

[0114]

[0115] a personalized threshold, generated in relation to an individual mammal; and / or

[0115]

[0116] a treatment regime dependent threshold; and / or

[0116]

[0117] a relative threshold, generated in relation to other mammals, for example in relation to a group of mammals, a herd, dairy farm, and / or a plurality of mammals located in, and / or related to, a geographic region; and / or

[0117]

[0118] a contamination marker dependent threshold; and / or

[0118]

[0119] an influence weight dependent threshold; and / or

[0119]

[0120] mammal related information dependent threshold.

[0120]

[0121] In some embodiments, the individual characteristics of a mammal (e.g., mammal makeup information) may comprise mammal identity factors, current mammal health condition, mammal medication and diet factors, environmental factors, genetics, and / or species-specific factors, etc.

[0121]

[0122] In some examples, mammal identity factors, which may comprise the following: mammal lineage information, breed of the mammal, age of the mammal, number of pregnancies, lactation stage, etc., or any combination of the aforementioned.

[0122]

[0123] In some examples, current mammal health condition may comprise an undesirable condition comprising, but not limited to, mastitis, inflammation, metabolic disorder, e.g., hypocalcemia, hormonal imbalance, e.g., prolactin and / or oxytocin imbalance, malnutrition, dehydration, parasitic and / or infectious disease, or any combination of the aforesaid.

[0123]

[0124] In some examples, mammal medication and diet factors, which may comprise drugs and / or supplements administered to the mammal, mammal dietary intake, etc., or any combination of the aforesaid.

[0124]

[0125] In some examples, environmental factors (also: environmental parameter values) may relate to: overall weather conditions including ambient humidity and / or temperature, overall environmental stressors, e.g. disruptive light exposure, loud acoustic exposure, repulsive ambient scent, air quality, toxin exposure, sensory stressors from insects and / or living-habitat conditions, e.g. crowding, shelter and / or availability of nutritious diet and adequate hydration, etc., or any combination of the aforesaid.

[0125]

[0126] In some embodiments, the individual characteristic of a mammal (e.g., mammal makeup information) may further comprise the physiological state of a mammal, which is different from the healthstate of a mammal.

[0126]

[0127] In some embodiments, the term "current mammal health condition" may partly overlap with the term "health-state of a mammal", insofar that both terms may reference mastitis.

[0127]

[0128] Conversely, the term "health-state of a mammal" refers to stage of development of a condition, e.g., a disease, such as, for example, mastitis. The term "current mammal health condition" may refer to a plurality of possible conditions which may be inflicted upon at least one mammal.

[0128]

[0129] The term "physiological state of a mammal" may refer to the physiological factors of a mammal, which may be affected by a condition, e.g., a disease, which may reside in mammals, both collectively and individually.

[0129]

[0130] The physiological state of the mammal may comprise biomolecular state, biochemical state, bio- cellular state, metabolic state, hormonal state, genetic condition, or any combination of the aforesaid, which may be descriptive of the physiological state of at least one mammal and / or at least one sample of the respective MM product.

[0130]

[0131] In some embodiments, MM evaluation criteria, e.g., MM characteristics, may comprise: MM nutritional composition, MM immunological content, MM hormonal content, MM chemical and physical characteristics, etc.

[0131]

[0132] In some examples, MM nutritional composition may comprise: MM proteins content and / or level, MM fat content and / or level, MM carbohydrates, e.g., lactose, content and / or level, MM vitamins and mineral content and / or level, etc., or any combination of the aforesaid.

[0133] In some examples, MM immunological content and / or level may comprise antibodies, enzymes, cytokines, growth factors, etc., or any combination of the aforementioned.

[0132]

[0134] In some examples, MM hormonal content and / or level may comprise: oxytocin, estrogens, progesterone, cortisol, growth hormone, insulin-like growth factors, etc., or any combination of the aforesaid.

[0133]

[0135] In some examples, MM chemical and physical characteristics may comprise: MM electrical characteristics, MM temperature, MM acidity, etc., or any combination of the aforementioned.

[0134]

[0136] In some embodiments, MM electrical characteristics may comprise: impedance, electrical conductivity (EC), electric potential difference, capacitance, or any combination of the aforesaid.

[0135]

[0137] In some embodiments, MM evaluation criteria may comprise: MM somatic cell count (SCC), MM urea content and / or level, MM hormone content and / or level, MM antibiotic content and / or level, MM milk blood content and / or level, or any combination of the aforesaid.

[0136]

[0138] Furthermore, MM evaluation criteria, e.g., MM characteristics, may additionally comprise at least one individual characteristic of a mammal (e.g., mammal makeup information), for example: mammal lineage, mammal breed, identity, age, diet, lactation stage, reproduction status, geographical region, farming management system, etc.

[0137]

[0139] The term "framing management" may interchangeably refer to the terms "herd health management" and / or "milking parlor management". In some embodiments, the disclosed system and method may be utilized to enable, for example, the following operational and / or management outcomes:

[0138]

[0140] detection and / or prediction of a clinical and / or preclinical condition;

[0139]

[0141] feed efficiency, for example by accurate monitoring of MUN, pH, and / or milk solids allowing ration balancing and avoids protein overfeeding;

[0140]

[0142] environmental regulation compliance, for example by reducing nitrogen waste;

[0141]

[0143] value-based milk storing, for example by identifying cows with high casein, fat, and / or protein yields to allow for sorting milk by end-use category;

[0142]

[0144] enhancing genetic return of investment and supporting genetic culling decision; and / or

[0143]

[0145] reducing operational costs.

[0144]

[0146] It should be noted that farming management may be directed to encompass additional operational and / or management outcomes and should not be limited to the aforementioned outcomes.

[0145]

[0147] In some embodiments, mammal breed may refer to dairy cattle breeds, comprising, for example: Holstein-Friesian, Jersey, and / or Brown Swiss breed. In some examples, dairy cattle breeds may differ significantly in their milk yield, milk composition, and / or in the dairy cattle physiological traits. For example, parameters such as, for example, SCC, MUN, milk conductivity, and / or solids content may differ across different breeds.

[0146]

[0148] Accordingly, mammal makeup information may contribute to establish breed specific ranges, baselines, thresholds, parameters, calibration and / or any idiosyncratic reference value that may be utilized in the system processing and / or analyzing workflows.

[0147]

[0149] The above example should by no means be construed in a limiting manner, additional individual characteristic of a mammal (e.g., mammal makeup information) may be considered as contributor when evaluating MM.

[0148]

[0150] "Mammal characteristics" may relate, for example, to "MM evaluation criteria", "MM product characteristic", "mammal makeup information" "individual characteristic", and / or "group-level characteristics".

[0149]

[0151] In some embodiments, mammal characteristics may be affected, e.g., changed, due to the presence of MM contamination markers.

[0150]

[0152] In some examples, MM contamination markers may comprise: biological contamination markers, chemical contamination markers, physical contamination markers, or any combination of the aforesaid.

[0151]

[0153] In some embodiments, MM contamination markers may be sensed, captured, measured, computed, processed, and / or analyzed with respect to at least one of the following evaluation values, for example, with respect to a threshold, range, a trend, signal noise, absolute value, relative value, or any combination of the aforementioned.

[0152]

[0154] In some embodiments, the following evaluations may be employed: a threshold-dependent evaluation; a trend-dependent evaluation; a baseline deviation dependent evaluation; a pattern dependent evaluation; a classifier dependent evaluation; a correlation dependent evaluation; or any combination of the aforementioned. In some examples, the evaluation may be realized by the analysis model.

[0153]

[0155] In some embodiments, MM contamination evaluation values, e.g. threshold, range, absolute value, relative value, etc., may be dependent on the production context, for example, geographical factors, regulatory standards, species-specific requirements, farming practices, dietary influences, and intended use (e.g., human consumption, industrial processing, and / or neonatal feeding) may affect MM contamination evaluation values.

[0154]

[0156] In some embodiments, MM chemical contamination markers may comprise, for example: milk urea nitrogen (MUN). In embodiments, measuring MUN level, e.g., urea nitrogen concentration in milk, may reveal, for example, the protein status of dairy cows. In addition, MUN measurements may be descriptive of common MUN levels that reside in the range of, e.g., 10-16 mg / dL. Furthermore, MUN level less than e.g., 8 mg / dL may be descriptive of possible protein deficiency and / or overfeeding of fermentable carbohydrates, and MUN level greater than, e.g., 18 mg / dL may be descriptive of possible excess dietary protein intake and / or an imbalanced energy-to-protein ratio.

[0155]

[0157] In some embodiments, monitoring the dynamics of MUN values may be utilized for adjusting dietary crude protein levels, enhancing nitrogen utilization, reducing excretion, and / or improving reproductive performance by avoiding elevated urea that may interfere with fertility.

[0156]

[0158] In some embodiments, biological contamination markers may comprise, for example: somatic cell count (SCC). In addition, SCC measurements may include further processing of the measured SCC value with respect to the following thresholds values:

[0157]

[0159] SCC less than, e.g., 100 cells / pL may be indicative of healthy quarters in primiparous (first-lactation) cows; SCC range of, e.g., 100 to200 cells / pL may be revealing of normal to low-risk range of mastitis onset, for example, when early signs of infection may be present, e.g. indicative of preclinical or subclinical mastitis;

[0158]

[0160] SCC greater than, e.g., 200 cells / pL may be indicative of subclinical mastitis in which symptoms may be present;

[0159]

[0161] Example SCC range 300 to 400 cells / pL may imply chronic and / or contagious infection;

[0160]

[0162] Example SCC greater than 500 cells / pL may be associated with clinical mastitis;

[0161]

[0163] SCC greater than, e.g., 750 cells / pL may be indicative of severe clinical mastitis where milk may not be safe for consumption.

[0162]

[0164] In some embodiments, the onset of the pre-clinical mastitis is predictable for mammal milk somatic cell count (SCC) that is less than or equal to, e.g., 200 cells / pL; and in some embodiments SCC is less than or equal to, e.g., 180 cells / pL, and in further embodiments SCC is less than or equal to, e.g., 150 cells / pL.

[0163]

[0165] In some embodiments, elevated SCC may indicate, for example, the following: mastitis and / or inflammation in the mammary gland; and / or bacterial load including presence of, for example, pathogens, e.g. milk bacterium cultures, for example, Streptococcus agalactiae, Staphylococcus aureus, Staphylococcus spp, Mycoplasma spp, environmental Streptococci, Coliforms, Salmonella, or any combination of the aforesaid, which may indicate mastitis and / or inflammation in the mammary gland.

[0164]

[0166] In some embodiments, monitoring the dynamics of SCC values may be utilized for detecting, determining a probability and / or predicting preclinical mastitis. For example, subclinical inflammation, e.g., subclinical mastitis, may occur with a dynamic increase of SCC values even below, e.g., the 200 cells / pL range. For example, a dynamic increase from 80 cells / pL to 120 cells / pL across 2-3 consecutive milkings sessions may be an early indicator of preclinical mastitis. In some examples, the dynamic increase may encompass an increase of 10%, 25%, 33%, 50% or more of the initial measured SCC value. The abovementioned values should not be construed in a limiting manner. Additional characteristics of the dynamics of SCC values may be applicable for detecting, determining a probability and / or predicting preclinical mastitis.

[0165]

[0167] Furthermore, biological contamination markers may include, for example, enzymatic activity. For example, released enzymes from within the mammalian cells and / or from present bacteria may degrade milk quality, for example degrade milk fat content by lipase and protease activity.

[0166]

[0168] Biological contamination markers may include hormonal activity. For example, synthetic hormones and / or elevated levels of natural reproductive hormones may compromise milk quality.

[0167]

[0169] In some embodiments, chemical contamination markers may comprise, for example: antibiotics and / or antibiotic residues. For example, contamination may occur from the mammal and / or MM product exposure to antibiotic treatments.

[0168]

[0170] Chemical contamination markers may include, for example, pesticides, which may comprise contamination from feed and / or environment which the mammal and / or MM product may have been exposed to, for example, organophosphates and / or DDT residues.

[0169]

[0171] Chemical contamination markers may include, for example, heavy metals. For example, the presence of, for example, lead, cadmium, mercury, etc., from environmental exposure may be toxic, thus, contaminating the MM product; and / or

[0170]

[0172] In some embodiments, physical contamination markers may comprise, for example, foreign particles, which may comprise material, external to the process of MM production, for example, dirt, dust, foreign organic particles, foreign unorganic particles, and / or debris due to poor handling and / or unclean equipment.

[0171]

[0173] In some embodiments, physical contamination markers may include, for example, adulterants. For example, dilution with water and / or addition of substances, for example, starch, may manipulate milk quality.

[0172]

[0174] In some embodiments, in addition to SCC indicative threshold values, detecting, determining a probability and / or predicting preclinical mastitis may involve, for example, the following markers, separately or in any combination:

[0173]

[0175] subclinical ketosis, for example, inferred by elevated concentration of Beta-Hydroxybutyrate (BHBA) in the milk and / or a fat-to-protein ratio greater than, e.g., 1.4;

[0174]

[0176] metritis, for example, inferred by elevated milk temperature, elevated milk conductivity, and / or acute-phase proteins (APPs) markers;

[0177] lameness inflammation, for example, inferred by activity data and a drop in yield;

[0175]

[0178] hypocalcemia, e.g., milk fever, for example, inferred by changes in Ca2+ and / or delayed milk letdown; and

[0176]

[0179] fertility-related changes, for example, inferred by shifts in macro-nutrients and / or progesterone- linked temperature changes.

[0177]

[0180] Accordingly, embodiments of the present disclosure support prediction of inflammation prior to onset of clinical symptoms, e.g., preclinical mastitis. Thus, facilitating proactive treatment and herd health management, for example, mitigating antibiotic use.

[0178]

[0181] Aspects of embodiments may relate to providing a user with a prediction relating to at least one group-level characteristic, individual characteristic, and / or MM characteristic. For example, the prediction may comprise determining a probability of at least one health-state of a mammal and / or its respective MM product.

[0179]

[0182] Additionally, embodiments may relate to providing a user with at least one group-level characteristic, individual characteristic, and / or MM characteristic that may be continuously and / or automatically monitored.

[0180]

[0183] In some embodiments, the system may be configured for generating granular, time-stamped, realtime, sensor-based data. In some embodiments, the data that is sensed, captured, measured, computed, processed, and / or analyzed may be utilized according to any of the following suitable configurations, for example:

[0181]

[0184] sensor data may be employed entirely on-site, entirely remotely, or through a hybrid arrangement combining local and remote resources;

[0182]

[0185] data processing may occur in a centralized, distributed, federated, and / or hierarchical manner, and may be executed in real-time, near-real-time, and / or on a deferred schedule; and

[0183]

[0186] data analysis may be synchronous and / or asynchronous, may involve continuous and / or batch operations, and may incorporate dynamic allocation and / or load balancing among available computational resources.

[0184]

[0187] It should be noted that any combination of these local, remote, hybrid, centralized, distributed, synchronous, asynchronous, real-time, and / or deferred configurations is within the scope of the present disclosure.

[0185]

[0188] In some embodiments, the system may employ analysis models to process sensor data, which may be descriptive of a first characteristic of a mammal and / or a first characteristic of a mammal respective MM product, having a first influence weight, in relation to a second characteristic of a mammal and / or a second characteristic of a mammal respective MM product, having a second influence weight. The relation of the first and second influence weight and / or the first and second characteristics may be incorporated in determining at least one health-state probability of a mammal and / or its respective MM product.

[0186]

[0189] Some embodiments may relate to a system configured for determining a health-state probability configured for reducing, or minimizing prediction errors adapted to avoid false positive and / or false negative interpretation of analyzed sensor data.

[0187]

[0190] In some embodiments, to reduce, or minimize prediction errors and / or increase prediction accuracy, various error reduction or minimization techniques may be employed, which are aimed at refining model outputs. For example, Cost Function Optimization ((mean squared error (MSE), mean absolute error (MAE), Cross-Entropy, etc.) Gradient Descent, and / or Regularization (Lasso, Ridge, etc.) may be employed. In some examples, techniques for increasing prediction accuracy such as, for example, Feature Selection and Engineering, Ensemble Learning, Cross-Validation, Hyperparameter Tuning, Transfer Learning, may be employed.

[0188]

[0191] In some embodiments, methods for data Quality Improvement may be employed, including, for example, data cleaning and preprocessing methods. In some embodiments, the system is configured to detect and handle, for example, missing values, outliers, and / or noisy data. In some embodiments, to the extent possible, balanced and / or substantially balanced datasets are employed. Some embodiments may relate to a system which may provide a user with feedback comprising actionable preventive measures supported by system prediction of at least one health-state probability. The system predictions may be improved and / or optimized per individual mammal and / or per a group of mammals, for example, by employing, generating, adapting, and / or processing multiple sensor data, computational, rule-based, classifiers, machine-learning (ML) models, and / or statistical models, e.g., for the purpose of reducing or minimizing prediction errors.

[0189]

[0192] In some embodiments, the system may be configured to continuously and / or intermittently sense at least one characteristic of a mammal and / or of its respective MM product. The sensor may be operable to a sensing regime, e.g., a monitoring regime.

[0190]

[0193] In some embodiments, the system may be configured to sense at least one mammal characteristic adhering to a sensing regime, which may include, for example:

[0191]

[0194] chronological sensing. For example, the operation of sensors may be sequenced, for example: continuous sensing, intermittent sensing, alternate sensing, cyclic sensing, randomized sensing, etc.; and / or

[0192]

[0195] instructional sensing. For example, the operation of sensors may be rule-based sequenced, for example: event-driven sensing, which may be triggered by a specific event, adaptive sensing. The sensing may, for example, adjust its parameters based on the environment, and / or collaborative sensing, which may involve coordinating multiple sensors working together.

[0193]

[0196] In some embodiments, the chronological sensing regime may be configured to sense, over a recent monitoring time interval, the at least one mammal characteristic. For example, the sequential sensing may be within the upcoming time interval, which may be consecutive of the recent monitoring time interval.

[0194]

[0197] Reference is now made for further disclosure of the sensor data sources. For example, the system may be configured to acquire sensor data, e.g., sensing, monitoring, and / or storing in at least one memory element at least one mammal characteristic and / or MM characteristic.

[0195]

[0198] In some embodiments, the acquired data may be achieved by the operation of at least one of the following sensors, for example: an optical sensor, a sensor configured to sense an electrical characteristic of the milk, a thermal sensor, a temperature sensor, a chemical sensor, a biological sensor, a biochemical sensor, an electrochemical sensor, a flow sensor, a pressure sensor; or any combination of the aforesaid.

[0196]

[0199] Optical analysis may be performed based on light transmitted through the milk, and / or based on light reflected from the milk. It should be noted that the term "light" may not be limited to visible light, but also energy deliverable by electromagnetic energy in all and / or portions of the electromagnetic spectrum, including but not limited to radio frequency (RF), infrared (IR), near infrared, visible light, ultraviolet, etc. Light-related parameters that may be analyzed by embodiments of the system may include, for example, scattering, reflectance; transmittance, phase, polarization; intensity; coherence; and / or refraction.

[0197]

[0200] In some embodiments, data acquisition may be implemented by, for example: remote sensors, wearable sensors, implanted sensors, and / or noninvasive sensors.

[0198]

[0201] The above examples should by no means be construed in a limiting manner, additional sensors may be implemented in the system for receiving sensor data.

[0199]

[0202] The term "data" may refer, for example, to:

[0200]

[0203] sensor data, indicative of at least one sensed physical at least one mammal characteristic and / or MM characteristic comprising, for example, chemical, optical, electrical, and / or mechanical properties; and / or

[0201]

[0204] data that is descriptive of previous sensing results of an individual mammal and / or respective MM product; and / or

[0202]

[0205] data that is descriptive of a plurality of mammals and / or respective MM product, which may be acquired from at least one memory element, open-source database, professional literature, etc.

[0203]

[0206] In some embodiments, the sensor data may be based on at least one electrical signal measurement output. The system may incorporate, separately or in any combination, electrical signal processing methods including, for example: signal filtering, which may remove unwanted noise and interference from the measured data, for example removing ambient acoustic noise, e.g. dairy farm fans, farming machinery, etc. ; and / or calibration, which may employ comparing the measured values to known standards within a given context, e.g. mammal age, breed, lineage, and / or lactation stage, etc., and adjusting the instrument accordingly; and / or error correction algorithm. For example, the system may incorporate temperature compensation methods by adjusting measured values based on the temperature of the system, and / or temperature correction, which may involve using mathematical models to correct temperature-induced errors.

[0204]

[0207] In some embodiments, the sensor data may be indicative of MM fluid flow, for example the sensor data may be descriptive of MM flowing into a milk tank and / or of milk stored in a milk tank.

[0205]

[0208] In some embodiments, the MM may be stored in a milk tank, which respectively may be the product of an individual mammal. Additionally, and / or alternatively, the milk tank may be adapted to receive milk from a plurality of mammals.

[0206]

[0209] In some embodiments, the milk tank may refer to a bulk milk cooling tank which may be configured for holding and cooling milk content at a desired temperature until it may be further picked up by a milk hauler and transported to a milk processing and production facility.

[0207]

[0210] The term "system outputs" may refer, but not limited, to system utilization of sensor data and statistical models, with the purpose to provide the system user with at least one system output, which may comprise, for example: tracking at least one mammal characteristic and / or at least one respective MM product characteristic over time; and / or system prediction output, comprising detecting and / or determining at least one individual characteristic of a mammal (e.g. mammal makeup information). For example, a probability of at least one individual characteristic of a mammal (e.g., mammal makeup information) may be assigned.

[0208]

[0211] In some embodiments, the system outputs may be adapted to modify a MM production-related component and / or characteristic, for example, modifying the flow path of the MM product to a MM container, and / or modifying MM fluid flow characteristic.

[0209]

[0212] In some embodiments, the system output may include notifications output. For example, the system may provide a notification concerning the assigned probability of at least one individual characteristic of a mammal (e.g., mammal makeup information), and / or a value of the tracked at least one mammal characteristic and / or at least one respective MM product characteristic; and / or system instructions output. For example, insights and / or feedback suggesting at least one preventive measures output, for example, cleaning mammal habitation arena, changing mammal diet, administering preventive medication, e.g., antibiotics, and / or isolating the mammal from the rest of the group, etc.

[0213] The above examples should by no means be construed in a limiting manner, additional system outputs may be derived from system utilization of sensor data and within the system computational and / or statistical models processing of sensor data.

[0210]

[0214] In some embodiments, the system monitoring may comprise, for example, real-time monitoring of the sensor data. For example, the sensor data may be recorded (continuously and / or intermittently) in the system's memory element.

[0211]

[0215] In some embodiments, the system monitoring may adhere to the sensing regime, e.g., monitoring regime. For example, the sensor data may be recorded into the system's memory element in accordance with the monitoring regime.

[0212]

[0216] In some embodiments, the system predictions may be configured to detect preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset at an accuracy of at least 90%, at least 94%, or at least 98%.

[0213]

[0217] In some embodiments, the system may be configured to detect a preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset in a significantly higher accuracy level compared to a corresponding control system. For example, the corresponding control system is configured to sense a smaller plurality of distinct mammal characteristics, and / or a different plurality of distinct mammal characteristics.

[0214]

[0218] For example, the corresponding "control" system is configured to sense a smaller plurality of distinct MM characteristics, and / or a different plurality of distinct MM characteristics.

[0215]

[0219] In some embodiments, the system may be configured to detect a preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset in a significantly higher accuracy level compared to a corresponding "control" system. For example, the corresponding "control" system is configured to sense a smaller plurality of distinct mammal characteristics and MM, and / or a different plurality of distinct mammal and MM characteristics.

[0216]

[0220] In some embodiments, the system predictions may comprise evaluation, separately and / or in any combination, for example, the following health-states of a mammal: prodromal state, which may refer to refers to a state of a mammal in a period of time before the onset of characteristic symptoms of unfavorable mammal condition, e.g. a disease. For example, some vague and / or nonspecific symptoms may be present; and / or

[0217]

[0221] latent state, which may refer to a state of a mammal in a period of time when the unfavorable mammal condition, e.g., a disease, may be physiologically present before the outburst of the unfavorable mammal condition, e.g., a disease symptom; and / or

[0222] asymptomatic state, which may refer to the state of a mammal. For example, at least one unfavorable mammal condition, e.g., a disease, may be physiologically present but with no apparent symptoms; and / or

[0218]

[0223] clinical state, which may refer to the state of a mammal in a period of time when an unfavorable mammal condition, e.g., a disease may be physiologically present during the outburst of at least one unfavorable mammal condition, e.g., a disease symptom; and / or

[0219]

[0224] preclinical state, may refer to a prodromal and / or latent state of a mammal; and / or

[0220]

[0225] convalescent state, which may refer to the state of a mammal in a period of time after an unfavorable mammal condition, e.g., a disease.

[0221]

[0226] In some embodiments, system predictions may account for mammal characteristic, which may influence prediction accuracy, for example, individual characteristics such as, for example, stage of lactation, breed, lineage and / or diet, may affect the electrical properties of the MM, leading to falsepositive and / or false-negative predictions, if the electrical signal would be acquired and interpreted without the proper context.

[0222]

[0227] In some embodiments, the system adaptations may comprise performing, separately and / or in any combination, for example:

[0223]

[0228] analysis models adaptation, which may be in correspondence with the results of the statistical measures and / or models, plurality mammals, adapting at least one threshold of at least one contamination marker; and / or

[0224]

[0229] farming system adaptation, which may be in correspondence with the farming system and may be adapted to modify a MM production-related component and / or characteristic, for example, modifying the path of the MM product to a MM container, modifying MM fluid flow characteristic, etc.; and / or

[0225]

[0230] treatment adaptation, which may be in correspondence with the treatment regime of at least one mammal.

[0226]

[0231] In some embodiments, system adaptations may comprise, for example, Model Updates and Retraining: For instance, the system may continuously and / or periodically retrain its prediction models based on new data to improve accuracy and adapt to changes in the environment. In some embodiments, a model may be retrained for each farm.

[0227]

[0232] In some embodiments, the system may be configured to implement farm calibration and baseline for adapting the models.

[0233] In some embodiments, the system may be configured to perform Parameter Tuning and Optimization. For example, the system may include mechanisms for automatically tuning model parameters (hyperparameters) to optimize performance.

[0228]

[0234] In some embodiments, the system may be configured to consider Contextual Awareness and perform Data-Driven Adjustments. For example, the models may be designed to adapt based on contextual factors (e.g., time of day, location, user behaviour, cow behaviour).

[0229]

[0235] In some embodiments, the system is configured to perform anomaly detection and, optionally, respond accordingly. For example, the system may be configured to adapt by using an anomaly detection mechanism that triggers adjustments when unexpected patterns and / or outliers are detected in the data.

[0230]

[0236] In some embodiments, the system may be configured to perform self-learning and implementing a feedback mechanism: For example, the system may include a feedback loop that allows it to learn from its own performance.

[0231]

[0237] The above examples should by no means be construed in a limiting manner, additional system adaptations may be derived from particular user aspirations and / or user preferences.

[0232]

[0238] In some embodiments, the system notifications may comprise separately and / or in any combination, for example, one of the following:

[0233]

[0239] visual notification. For example, the system may generate presentable dashboards, scorecards, graphs, charts, stats, etc., for example, the visual notification may be generated with the aim of representing the at least one value dynamics of the at least one characteristic descriptive of mammal related information.

[0234]

[0240] In some embodiments, system notifications may include audible notifications. For example, the system may generate an acoustic and / or physical, e.g., vibration, representation of at least one related metric of the at least one monitored sensor data.

[0235]

[0241] In some embodiments, system notifications may include advisory notifications. For example, the system may generate a notification with recommended course of action regarding at least one mammal treatment, for example, notifying with a recommended preventive measure.

[0236]

[0242] In some embodiments, system notifications may include alert notification, for example, the system may generate a notification which may alarm the user to immediately change of at least one mammal treatment, primarily with respect to mastitis and / or preclinical mastitis.

[0237]

[0243] The above examples should by no means be construed in a limiting manner, additional system notifications may be derived from particular user aspirations and / or user preferences.

[0244] In some embodiments, the system instructions may comprise at least one treatment instruction. For example, the system may generate at least one instruction referring to at least one mammal. For example, the instruction may affect at least one sensor data value indicative of at least one mammal and / or MM characteristic.

[0238]

[0245] In some embodiments, the instructions may comprise separately and / or in any combination, for example, at least one of the following:

[0239]

[0246] correctional instructions. For example, the system may generate at least one instruction responsive of at least one deviation from a particular treatment regime; and / or

[0240]

[0247] In some embodiments, system instructions may include preventative instructions. For example, the system may generate at least one instruction directed to recommend a preventative measure, which may be adapted to conform with a particular treatment regime, with reference to at least one mammal.

[0241]

[0248] The above examples should by no means be construed in a limiting manner, additional system instructions could be derived from system utilization of sensor data and / or statistical models, and may vary with respect to, for example: mammal breed, mammal identity, etc.

[0242]

[0249] In addition, system instructions may be provided within the generated system notifications, which may be provided by system selection from a pre-existing library of notifications and / or instructions.

[0243]

[0250] Additionally, and / or alternatively, the notifications and / or instructions may be generated by a Machine Learning model, such as, for example, a Large Language Model (LLM).

[0244]

[0251] Reference is now made to Figure 1. A system may be configured to serve a dairy farm 1000. Such a system may be configured to implement an analysis engine 2000. Dairy farm 1000 may be adapted to host a plurality of "n" mammals and may comprise, for example, a milking parlor 1100 and one or more bulk milk cooling tanks 1200.

[0245]

[0252] Furthermore, dairy farm 1000 may comprise, for example, a milking parlor 1100 where a 1stmammal 1110 may be milked and the corresponding MM product may be stored in a separate designated milk tank 1210.

[0246]

[0253] Accordingly, a 2ndmammal 1120, a 3rdmammal 1130 up to an n-th mammal 1140, which may be milked in the milking parlor 1100, and where the corresponding MM product may be stored is a separate designated milk tank 1220, 1230 and 1240, respectively.

[0247]

[0254] The term "milking parlor" having reference numeral 1100 may further interchangeably refer to any arena, e.g., living-habitat, where at least one mammal may reside in, for example, a cowshed, a pasture, a milk processing facility, a ranch, a livestock pen, a livestock feedlot, etc.

[0255] In some embodiments, the term "milking parlor" 1100 may directly refer to at least one mammal within an arena where at least one mammal may reside in.

[0248]

[0256] In some embodiments, the term "milking parlor" 1100 which may be located in a dairy farm 1000, may be encapsulate the broader arena in which it may reside. For example, when referring to a milking parlor 1100, the present disclosure may interchangeably refer to the dairy farm 1000 itself and / or any analogous arena where at least one mammal may reside.

[0249]

[0257] The above examples should by no means be construed in a limiting manner, an additional arena where at least one mammal may reside may be considered when implementing the disclosed system and form which sensor data may be received.

[0250]

[0258] Additionally, analysis engine 2000 of the mastitis detection and / or determining system may further comprise one or more sensors 2100 and a computing unit 2200 having at least one memory element 2210 and at least one processor 2220. For example, one or more sensors 2100 may be configured to acquire sensor data from at least one mammal within a dairy farm 1000 by sensing a mammal characteristic through probing at least one mammal, e.g., 1110, 1120, 1130 and / or 1140.

[0251]

[0259] Additionally, and / or alternatively, one or more sensors 2100 may be configured to acquire sensor data from at least one mammal within a dairy farm 1000 by sensing a mammalian milk (MM) characteristic through probing at least one designated milk tank, e.g., 1210, 1220, 1230 and / or 1240.

[0252]

[0260] Moreover, at least one memory element 2210 may be configured to store data and executable instructions, and at least one processor 2220 may be operative to execute instructions stored in the at least one memory element 2210 to facilitate system mastitis detection and / or probability determination.

[0253]

[0261] In some embodiments, the one or more sensors 2100 may be probing at least one designated milk tank. For example, received sensor data may be facilitated through Cx. In addition, to probing at least one mammal. For example, the receiving of sensor data may be facilitated through C2-

[0254]

[0262] The acquired sensor data may be communicated to the computing unit 2200 of the analysis engine 2000 through C3.

[0255]

[0263] Further reference is now made to Figure 2. In some embodiments, dairy farm 1000 may be adapted to have a plurality of "n" mammals, which may comprise, for example, a milking parlor 1100 and one or more bulk milk cooling tanks 1200. A corresponding MM product may be stored in at least one united milk tank 1200 adapted for receiving, holding, and / or cooling MM product from the plurality of n mammals in milking parlor 1100.

[0256]

[0264] One or more sensors 2100 may be configured to acquire sensor data from a plurality of n mammals in a milking parlor 1100 within a dairy farm 1000 by sensing a mammalian milk (MM) characteristic through probing at least one united milk tank 1200.

[0265] Additionally, and / or alternatively, one or more sensors 2100 may be configured to acquire sensor data from a plurality of mammals within a dairy farm 1000 by sensing a mammal characteristic, which may be indicative of a characteristic associated with a group-level characteristic of mammals, for example, through probing a plurality of n mammals 1100.

[0257]

[0266] In some embodiments, a group-level characteristic may comprise, for example, at least one of the following:

[0258]

[0267] group health characteristics. The system may be adapted to receive group-level sensor data which may comprise examples: disease outbreaks. For example, audio recording may be analyzed for detection of increased frequency of mammals coughing, sensing group-level body temperature by thermal imaging, etc., stress level. For example, abnormal movement patterns and / or vocalization may be sensed, and may be further associated with heightened group-level cortisol level, nutritional status including, for example, monitoring rate of consumption of food and / or water, rate of manure accumulation, monitoring of rumen activity, etc.

[0259]

[0268] A group-level characteristic may comprise a group behavior characteristic. For example, the system may be adapted to receive group-level sensor data which may comprise: movement patterns including, for example, tracking position across individuals with GPS trackers and / or accelerometers, social interactions such as, for example, monitoring arousal, and / or aggressive state across individuals and / or synchronization activity using proximity sensors, RFID tags and / or video analysis.

[0260]

[0269] A group-level characteristic may comprise, for example, productivity and / or yield characteristics. In some examples, the system may be adapted to receive group-level sensor data which may comprise, for example: milk production such as, for example, monitoring MM production rate, MM output consistency across a plurality of mammals by flowmeter, volume analysis, etc.

[0261]

[0270] The above examples should by no means be construed in a limiting manner, additional group-level characteristics may be derived from system utilization of sensor data and within the system computational and / or statistical models processing of sensor data.

[0262]

[0271] Additional reference is now made to Fig.3. Fig.3 further depicts an n-th mammal 1140 having a corresponding separated designated n-th milk tank 1240. For example, one or more sensors 2100 may be configured for probing the n-th mammal 1140 through C2and / or for probing the MM content of the n-th milk tank 1240 through

[0263]

[0272] In some embodiments, the acquired senor data sensed through Ci and C2may be further communicated to the computing unit 2200 of the analysis engine 2000 through C3.

[0264]

[0273] In some embodiments, the acquired sensor data and / or the analyzed sensor data may be communicated to a server 2300 through C4.

[0274] In some embodiments, the acquired sensor data and / or the analyzed sensor data may be communicated to and / or displayed on a monitor 2400 through C5.

[0265]

[0275] In some embodiments, the data communicated to a server 2300 through C4may be further communicated to and / or displayed on a monitor 2400 through C6.

[0266]

[0276] The term "communicated through" may refer to the transfer of data through the following methods, for example:

[0267]

[0277] wired data transfer methods, for example: ethernet, USB, serial communication, parallel communication, HDMI / DisplayPort, Fiber Optic cables, Thunderbolt, etc.

[0268]

[0278] wireless data transfer methods, for example: Wi-Fi, Bluetooth, NFC, IR, cellular networks, satellite communication, RF,

[0269]

[0279] internet-based data transfer methods, for example: email, cloud storage services, file transfer protocol (FTP), peer-to-peer (P2P), HTTP / HTTP / HTTPS, Application programing interfaces (APIs), streaming protocols (e.g., RTSP, WebRTC),

[0270]

[0280] physical data transfer methods, for example, storage media (e.g., external hard drives, SD cards, etc.), Optical discs (e.g., CD, DVD, Blu-ray, etc.), printed barcodes, QR codes, manual transcription and / or scanning, or any combination of the aforesaid.

[0271]

[0281] The above examples should by no means be construed in a limiting manner, additional data transfer methods may be applied.

[0272]

[0282] In some embodiments, the descriptors C±— C6may facilitate unidirectional, bidirectional, and / or multidirectional transfer of data in accordance with the implemented transfer data method incorporated in the mastitis detection and / or determining system.

[0273]

[0283] In some embodiments, the server may facilitate at least part of the processing of the sensor data. The server may be adapted to communicate computational feedback to the computing unit 2200, to communicate display data to be presented on monitor 2400.

[0274]

[0284] Additionally, and / or alternatively, the server may communicate directly with at least one sensor 2100 (not shown). The server may facilitate the sensing regime by direct communication.

[0275]

[0285] In some embodiments, the monitor may refer to displaying capabilities adapted to present a user with at least one notification and / or instructions output.

[0276]

[0286] Reference is now made to Fig. 4. A schematic system block diagram depicts the n-th mammal 1140 coupled with a computer-readable mammal labeling 1141. The MIVI product may be stored in a corresponding separated designated n-th milk tank 1240 coupled with a computer-readable milk tank labeling 1241. The one or more sensors 2100 may be configured to read at least one computer-readable labeling, which uniquely associates the acquired sensor data with an individual mammal and / or corresponding MM product, for example, with the n-th mammal 1140 and / or with a corresponding separated designated n-th milk tank 1240.

[0277]

[0287] In some embodiments, the MM product, for example, the MM product of the n-th mammal 1140, may be sampled. The MM sample 400 may be further subjected to sensing from one or more sensors 2100.

[0278]

[0288] Additionally, and / or alternatively, the MM sample 400 may be further analyzed in lab 2110. The MM sample 400 may produce lab examined data, which may be communicated to the computing unit 2200, where, for example, the lab examined data may be stored in at least one memory element 2210 and / or may be analyzed by at least one processor 2220.

[0279]

[0289] In some embodiments, the analyzing of MM sample 400 in lab 2110 may be within the dairy farm 1000, within a milking parlor, integrated within the analysis engine 2000, in proximity to the one or more sensors 2100, remotely located, etc., or any combination of the aforesaid.

[0280]

[0290] In some embodiments, the analyzing of MM sample 400 in lab 2110 may be executed by a milk analyzer.

[0281]

[0291] In some embodiments, the lab 2110 testing procedure integrated within the analysis engine 2000 and / or in proximity to the one or more sensors 2100 may include diverting flow of a MM sample (not shown). For example, lab 2110 testing of the diverted sample 400 flow may be manual, automatic, and / or operably directed by analysis engine 2000.

[0282]

[0292] In some embodiments, lab 2110 testing of the diverted sample 400 flow may involve executing at least one MM testing protocol Tltfor example, executing a somatic cell count protocol, which may involve measuring viscosity change in MM sample 400 following the addition of an anionic detergent, which may cause gelling to an extent determined by a somatic cell count protocol.

[0283]

[0293] In some embodiments, at least one lab 2110 testing protocol 7^ may comprise: headspace testing protocol, gas chromatography protocol, microbial testing protocol, moisture content testing protocol, residual solvent testing protocol, volatile organic compound analysis protocol, quality control testing protocol, calibration protocol, etc., or any combination of the aforementioned.

[0284]

[0294] in some embodiments, lab 2110 examined data produced from at least one testing protocol T±may be further utilized, for example, within a calibration protocol. Calibrating data from each milking mammal may be used as a comparative tool between mammals and / or to monitor changes in the somatic cell count (SCC) of at least one individual mammal between at least two different MM samples.

[0285]

[0295] In some embodiments, one or more sensors 2100 may be utilized for sensing T2a MM sample 400, additionally, and / or alternatively, one or more sensors 2100 may be utilized for sensing T3an individual mammal and / or corresponding MM product, for example, with the n-th mammal 1140 and / or with a corresponding separated designated n-th milk tank 1240.

[0286]

[0296] In some embodiments, a database 2120 may communicate data to the computing unit 2200 configured to provide, for example, comparative data, mammal characteristic threshold, at least one mammal history indicative of individual characteristic of a mammal (e.g., mammal makeup information) s, MM contamination markers, MM evaluation criteria, group-level characteristics, etc.

[0287]

[0297] In some embodiments, database 2120 may be configured for receiving data directly from one or more sensors 2100 to be stored within database 2120, additionally and / or alternatively, data from one or more sensors 2100 may be stored in at least one memory element 2210.

[0288]

[0298] Additionally, and / or alternatively, database 2120 may reside within at least one memory element 2210 and vice versa.

[0289]

[0299] Reference is now made to Fig. 5. A general illustration of an example relation between system input 5100, data analysis 5200 and system output 5300 is hereby presented.

[0290]

[0300] In some embodiments, system input 5100 may refer to data utilized by an analysis engine to employ at least one analysis model. System input 5100 may comprise, for example:

[0291]

[0301] database and / or accumulated history 5110, which may refer to, for example, professional literature database, previous system employment database, current operation accumulated sensor data history; lab related data 5120, including, for example, MM sample analyzed in a lab produces lab examined data by employing at least one testing protocol when analyzing the MM sample; and / or experimental sensor measurements 5130. For example, one or more sensors may produce sensor data associated with at least one characteristic descriptive of mammal related information.

[0292]

[0302] Reference now is made to data analysis 5200. A machine learning (ML) algorithm 5220 employing, for example a classification model 5221 may be configured for categorizing system input 5100 data into labels and / or classes, for example, the classification models may categorize input senor data into the following classes health, pre-clinical mastitis, and / or clinical mastitis.

[0293]

[0303] In some embodiments, the categorization, e.g., labeling, of the input data may be employed on the basis of SCC and electrical conductivity (EC) sensor readings, for examples mammals with preclinical mastitis may have slightly elevated levels of SCC and EC with respect to a health mammal. Moreover, mammals with clinical mastitis may exhibit significantly higher levels of SCC and EC, indicating an active infection.

[0294]

[0304] In some embodiments, the ML algorithm 5220 may also identify the specific type of mastitis present, such as, for example, bacterial and / or fungal, based on the data patterns.

[0305] Additionally, a machine learning (ML) algorithm 5220 may employ, for example, a regression model 5222 configured for predicting a continuous characteristic value descriptive of mammal related information. The generated predication may be used for forecasting clinical mastitis and / or preclinical mastitis, in addition to trend analysis, probability generation, risk assessment, etc.

[0295]

[0306] The above ML algorithm and the models employed should by no means be construed in a limiting manner, it may be obvious to one skilled in the art that additional models and / or ML algorithm architectures may be employed.

[0296]

[0307] In some embodiments, system input 5100 may be (for example, arbitrarily, e.g., randomly) divided Ai into subsets, which may be, in any combination, comprise algorithm input data 5230.

[0297]

[0308] In some embodiments, system input 5100 may be utilized in data analysis 5200 by feeding A2algorithm input data 5230 into ML algorithm 5220. Algorithm input data 5230 may comprise at least a first subset of system input 5100 data to a training set 5231, at least second subset of system input 5100 data to a validation set 5232 and / or at least third subset of system input 5100 data to a testing set 5233.

[0298]

[0309] Reference is now made to system output 5300, which may comprise, for example, separately or in any combination: a monitoring output 5310, an adaptation output 5320, notification output 5330, an instruction output 5340, and / or a prediction output 5350.

[0299]

[0310] In some embodiments, the employment of at least one analysis model executing data analysis 5200 by analysis engine may be configured for generating A3at system output of 5300.

[0300]

[0311] In some embodiments, the prediction output 5350 may comprise, for example mammal-related output 5351, which may be revealing of a classification of received data associated with an anomalous and / or common characteristic value indicative of mammal-related information.

[0301]

[0312] Additionally, and / or alternatively, the mammal-related output 5351 may comprise assigned probability to a received data associated with an anomalous and / or common characteristic value indicative of mammal-related information and / or assigned probability of at least one health-state of at least one mammal and / or the respective MM product of at least one mammal.

[0302]

[0313] In some embodiments, the probability may be referring to the probability of clinical mastitis inflicted upon at least one mammal, and / or to a probability of preclinical mastitis in at least one mammal.

[0303]

[0314] The above mammal related output 5351 examples should by no means be construed in a limiting manner, additional prediction output may be implemented, for example, forecasting output, trend analysis and / or risk contamination assessment, etc.

[0315] Additionally, in some embodiments, the prediction output 5350 may comprise a verification set 5352 which may comprise validated and verified data of mammal-related output 5351. Verification set 5352 may be fed back A4to at least one subset comprising the algorithm input data 5230.

[0304]

[0316] In some embodiments, feeding back A4the verification set 5352 into at least one subset comprising the algorithm input data 5230 may contribute to reducing or minimizing prediction errors and / or increasing prediction accuracy.

[0305]

[0317] Reference is now made to Fig.6. In some embodiments, a method may include receiving from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information (block 610).

[0306]

[0318] In some embodiments, the method may further include processing the received sensor data for detecting mastitis, for detecting a preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval, (block 620)

[0307]

[0319] In some embodiment, the system may be configured for receiving mammal initial input data, the mammal initial input data being descriptive of the respective individual mammal and / or group of mammals, e.g. MM evaluation criteria, mammal characteristic, mammal group-level characteristic, individual characteristic of a mammal (e.g. mammal makeup information).

[0308]

[0320] In some embodiments, the method may include determining, based on the initial input data, an initial risk level of the respective mammal.

[0309]

[0321] Reference is now made to Fig.7. A schematic bar illustration of a value range of MIVI evaluation criteria is shown: PH 710, protein level (%) 720, fat level (%) 730 comparing healthy MM, sub-clinical MM, and / or clinical MM. A predictive trend may be derived, depicted by an arrow. The data presented in Fig.7 demonstrates that some parameters alone may not be predictive, as there is an overlap in the ranges of values of healthy MM, sub-clinical MM, and / or clinical MM. In some embodiments, PH level with MM increases 710 in the transition from healthy MM, through sub-clinical MM, to clinical MM. A transition may occur, for example, approximately from PH level of 6.5% to 6.9%. in some examples, PH level in the range of 6.6-6.8 may qualify as common PH level of the MM. In addition, PH level less than 6.4 may be descriptive of possible rumen acidosis and / or subclinical mastitis, and PH level greater than 6.9 may be descriptive of possible metabolic alkalosis, and / or udder infection.

[0310]

[0322] Moreover, PH measurement may offer insights into udder health, rumen function, and / or dietary buffering. For example, saliva and / or rumen PH monitoring may be used to assess subacute ruminal acidosis (SARA).

[0323] In some embodiments, protein level (%) of MM increases 720 in the transition from healthy MM, through sub-clinical MM, to clinical MM. A transition may occur, for example, approximately from a protein level (%) of 3.25% to 3.5%.

[0311]

[0324] In some embodiments, fat level (%) of MM decreases 730 in the transition from healthy MM, through sub-clinical MM, to clinical MM. A transition may occur, for example, approximately from a fat level (%) of 4.5% to 3.2%.

[0312]

[0325] In some embodiments, any combination of the aforementioned trends may be identified as a contributor for the detection and probability determination of clinical and / or subclinical mastitis.

[0313]

[0326] In some embodiments, the terms subclinical and preclinical may be used interchangeably, and should not be interpreted in a limiting manner.

[0314]

[0327] Reference is now made to Fig.8. At least one of the following data categories may be utilized within the system:

[0315]

[0328] mammal-related information 9000, which may comprise separately or in any combination, for example, MM characteristics (e.g. MM evaluation criteria) 9100, group-level characteristics 9200, individual characteristics (e.g. individual characteristics of a mammal (e.g. mammal makeup information) 9300; and / or MM contamination markers 8000, which may comprise separately or in any combination, for example, biological 8100, chemical 8200 and / or physical 8300 contamination markers.

[0316]

[0329] In some embodiments, data categories may comprise, for example, the following data types descriptive of the stored category-related data: foundational data types comprising, for example, at least one integer, floating-point, character, Boolean, and / or string; composite data types comprising, for example, at least one array, list, tuple, dictionary, map, and / or set; abstract data types, comprising, for example, at least one stack, Queue, Deque, graph, and / or tree; statistical and computational-related data types comprising, for example, at least one matrix, tensor, and / or complex number; media and graphic data types, comprising, for example, at least one pixel data, audio data, and / or video data, or any combination of the aforesaid.

[0317]

[0330] The above examples of data types should by no means be construed in a limiting manner, additional data types may be utilized, for example, geospatial data type, log data, time-series data, etc.

[0318]

[0331] In some embodiments, database 2120 may comprise at least one database descriptive of at least one data category, for example database comprising mammal related information 9000 and / or at least one MM contamination markers 8000.

[0319]

[0332] In some embodiments, at least one memory element 2210 may store data descriptive of at least one data category, for example, at least a memory element 2210 configured to store mammal related information 9000 and / or at least one MM contamination markers 8000.

[0333] Additionally, and / or alternatively, database 2120 may reside within at least one memory element 2210 and vice versa. At least one database descriptive of at least one data category may be stored.

[0320]

[0334] In some embodiments, analysis engine 2000 may operationally utilize at least one data category for the execution of system algorithm having at least one analysis model, for example, the analysis engine may utilize MM contamination markers 8000 for the detection of clinical and / or preclinical mastitis, and / or any anomaly of a value descriptive of at least one mammal-related information 9000.

[0321]

[0335] In some embodiments, at least one sensor 2100 may be configured to produce, by sensing, at least one data-type descriptive of at least one mammal-related information 9000.

[0322]

[0336] Reference is now made to Fig.9. Mammal related information 9000 may comprise, separately or in any combination, at least one of the following: MM characteristics (e.g., MM evaluation criteria) 9100, group-level characteristics 9200, individual characteristics (e.g., mammal makeup information) 9300.

[0323]

[0337] MM characteristics (e.g., MM evaluation criteria) 9100 may comprise, separately or in any combination, for example:

[0324]

[0338] MM nutritional composition 9110; and / or

[0325]

[0339] MM immunological content 9120; and / or

[0326]

[0340] MM hormonal content 9130; and / or

[0327]

[0341] MM chemical and physical characteristics 9140.

[0328]

[0342] A group-level characteristics 9200 may comprise, separately or in any combination, for example:

[0329]

[0343] group health characteristics 9210; and / or

[0330]

[0344] group behavior characteristics 9220; and / or

[0331]

[0345] productivity and yield characteristics 9230.

[0332]

[0346] An individual characteristic (e.g., mammal makeup information) 9300 may comprise, separately or in any combination, for example:

[0333]

[0347] mammal identity factors 9310; and / or

[0334]

[0348] current mammal health condition 9320; and / or

[0335]

[0349] mammal medication and diet factors 9330; and / or

[0336]

[0350] environmental factors 9340; and / or

[0337]

[0351] genetic and / or species-specific factors 9350; and / or

[0338]

[0352] physiological state of a mammal, which may comprise: biomolecular / biochemical state 9361, bio cellular state 9362, metabolic state 9363, hormonal state 9364, and / or a genetic condition 9365.

[0353] Further reference is now made to Fig.lO. In some embodiments, a method may include receiving sensor data descriptive of at least one mammal related information from the one or more sensors (block 11000).

[0339]

[0354] The method may further include, in some embodiments, processing the received sensor data for detecting mastitis, for detecting preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval (block 12000).

[0340]

[0355] In some embodiments, the method may include comparing at least some of the sensor data descriptive of one or more mammal related information against one or more thresholds associated with a normal and / or abnormal value descriptive of a mammal related information (block 13000).

[0341]

[0356] In some embodiments, the method may further include distinguishing between a first anomalous value descriptive of a mammal related information which is related to pre-clinical and / or clinical mastitis; and a second anomalous value descriptive of a mammal related information which is not related to preclinical and / or clinical mastitis (block 14000).

[0342]

[0357] In some embodiments, the method may include predicting, based on the analysis model executed by the analysis engine, at least one value descriptive of a mammal related information (block 15000).

[0343]

[0358] In some embodiments, the method may include providing, based on prediction, at least one system adaptation (block 16000).

[0344]

[0359] In some embodiments, the method may include adapting and / or maintaining, based on the monitored value descriptive of a mammal related information, analysis model threshold and / or adaptation related to the farming system and / or the treatment regime (block 17000).

[0345]

[0360] It should be noted that the figures described herein are presented solely for illustrative purposes and are not intended to limit the scope of the present disclosure in any way. These illustrations serve to facilitate a more comprehensive understanding of the disclosed system and method, and to provide support for enablement by further disclosing an apparatus and prediction models results configured for enabling the employment of the disclosed system and method.

[0346]

[0361] Furthermore, the depicted embodiments of the apparatus are merely exemplary and do not encompass the full breadth of possible implementations. Accordingly, additional embodiments, variations, and results may be conceived by those skilled in the art based on the teachings set forth herein, without departing from the scope of the present disclosure.

[0347]

[0362] Reference is now made to Fig. SI. Graph 21000 schematically depicts a fat percentage prediction model. In graph 21000, an example of experimental data descriptive of the measured MM fat percentage (%) is brought forth with respect to predicted values of MM fat percentage (%). Moreover, the disclosed prediction model of graph 21000 may be derived from one or more analysis models.

[0363] In some embodiments, an optical analysis may be performed based on light transmitted through the milk, and / or based on light reflected from milk. Subsequently, the acquired optical sensor data may be processed, e.g., using analysis models. The employed analysis models may be configured to detect, for example, anomalies, trends, deviations, and / or levels of correspondence (e.g., correlations, crosscorrelation, etc.) within the spectral data.

[0348]

[0364] For example, the analysis models may establish a level of correspondence and / or association (e.g., correlation) between MM fat level with the obtained discrete reflectance and / or reflectance spectra as a result of light transmitted through the milk, and / or based on light reflected from milk, respectively. In some examples, the light transmitted and / or reflected may be in the visible (VIS) spectrum (400-700 nm), nearinfrared (NIR) spectrum (700-1100 nm), and / or in short-wave infrared (SWIR) spectrum (1100-2500 nm).

[0349]

[0365] It is noted that all embodiments, examples, and / or the like discussed herein that refer to transmittance, may additionally or alternatively be applicable with respect to reflectance.

[0350]

[0366] In some embodiments, the established a level of correspondence and / or association may be further optimized for decreasing false negative and / or false positive predictions by utilizing analysis models to compare the determined MM fat level with corresponding empirical lab-test database of fat levels in MM, as depicted in graph 21000. Therefore, a fat parameter value (e.g., fat percentage) prediction model may be derived.

[0351]

[0367] Reference is now made to Fig. S2. Graph 22000 schematically depicts a fat level prediction. In some embodiments, the system may be configured for iteratively reinforcing the prediction model disclosed in Fig. SI. In some examples, the prediction model may be progressively refined through repeated exposure to training data and feedback loops.

[0352]

[0368] In some embodiments, in each iteration, the prediction model receives input data that may include, for example, corrections, additional labeled samples, and / or results from, e.g., validation testing. Hence, the prediction model may adjust its internal parameters (e.g., weights, thresholds, and / or rules) to improve future predictions.

[0353]

[0369] In some embodiments, iterative reinforcement may occur through supervised learning, reinforcement learning, and / or adaptive algorithmic tuning. In some examples, across successive iterations, the prediction model may become more accurate and resilient, as shown in graph 22000.

[0354]

[0370] In some embodiments, the accuracy and / or resiliency of the model may comprise, for example, recognizing patterns, minimizing false positives, false negatives, and / or adapting to real-world variability. The iterative reinforcement process may be executed in conjunction with validation and verification steps, thereby ensuring that prediction model improvements translate into performance gains.

[0371] In some embodiments, validation and verification (V&V) steps may be configured for repeatedly testing the prediction model against known reference data and / or empirical, e.g., lab obtained, data. In some examples, the V&V process may comprise the following steps including, for example, collecting datasets adapted for training and / or validating prediction model outputs; applying error analysis techniques to assess prediction failure; identifying and / or correcting systematic biases and / or overfitting; or any combination of the aforesaid.

[0355]

[0372] In some embodiments, iterations may be repeated until performance metrics meet, for example, a threshold value descriptive of prediction model reliability. Therefore, enhancing confidence in the system's outputs when deployed in uncontrolled and / or real-world environments. Accordingly, additional MM characteristic prediction models may be derived, for example, as further illustrated in Fig. S3 and in Fig. S4.

[0356]

[0373] In Fig. S3, graph 23000 schematically depicts a protein level prediction model where experimental data descriptive of measured protein percentage (%) is compared to predicted values of protein percentage (%) allowing for further optimization of the generated predictions. In addition, in Fig. S4, graph 24000 schematically depicts a lactose level prediction model.

[0357]

[0374] It should be noted that the physical embodiment described herein is provided as a representative example of working apparatuses for realizing the disclosed system and method. These embodiments are not intended to be exhaustive and / or to limit the disclosure to specific structures or configurations as presented. Rather, the working apparatuses serve to illustrate how the principles of the present disclosure may be applied in practice. Those skilled in the art will recognize that various modifications, substitutions, and / or alternative physical implementations may be made without departing from the scope of the disclosed system and method.

[0358]

[0375] Reference is now made to Fig. S5. A system may be configured to serve on a dairy farm that may be adapted to host a plurality of mammals, for example, in a milking parlor, as disclosed in Fig. 1.

[0359]

[0376] In Fig. S5, an array of flow reduction apparatuses 25001 may be employed in a milking parlor. For example, a flow reduction apparatus 25000 may be designated to each milking station allowing intaking the IVIM extracted for further processing.

[0360]

[0377] In some embodiments, the flow reduction apparatus 25000 may comprise a receiving chamber 25100, having an inlet and an outlet. The flow reduction apparatus 25000 may be situated in a plurality of possible orientations without compromising the flow reduction apparatus 25000 disclosed functionalities. For example, receiving chamber 25100 inlet and outlet may be aligned with the milking parlor floor, as illustrated by receiving chamber 25100 coordinate system xl-x2-x3 aligned with a milking parlor floor coordinate system xW-yW-zW. In other embodiments, the receiving chamber 25100 inlet and outlet may be misaligned with the milking parlor floor. In some examples, the apparatus 25000 may have any suitable orientation relative to the world reference frame. In some examples, the apparatus 25000 may comprise a valve allowing controllably widening and narrowing the narrowing section of the throttle, for example, based on sensed MM characteristics and / or system characteristics.

[0361]

[0378] In some embodiments, the receiving chamber 25100 may be configured for intaking the extracted MM, adjusting MM flow within the chamber, and / or allowing the system to apply sensing, e.g., remotely and / or physically, of the sampled MM in the chamber from one or more sensors. In some examples, the receiving chamber 25100 may have a corresponding capping module 25200.

[0362]

[0379] Reference is now made to Fig. S6. In some embodiments, previously presented flow reduction apparatus 25000 may comprise a receiving chamber 25100 operably coupled with a sensing section 25110. In some embodiments, the receiving chamber 25100 may be a stand-alone structure that is not to be coupled with sensing section 25110.

[0363]

[0380] In some embodiments, sensing section 25110 may be configured for remote sensing of extracted mammalian milk. For example, the sensing section 25110 may be a screen configured for facilitating spectral analysis of electromagnetic (EM) radiation transmitted through the sampled MM and / or received from the sampled MM.

[0364]

[0381] In some embodiments, the receiving chamber 25100 may be a stand-alone structure that is configured for remote sensing of the extracted MM. In such instances, the receiving chamber 25100 may facilitate the remote sensing by, for example, transmitting EM radiation through a sensing section to interact with the sampled MM and / or receiving reflected EM radiation from the sampled MM passing through the sensing section. In some examples, a sensing section discussed herein may be at least partially opaque to some wavelength ranges and at least partially transparent to some other wavelength ranges. For example, a transparent section may be at least partially transparent to visible light but opaque to light that is not in the visible range. In some other examples, the sensing section may be opaque to visible light, but at least partially transparent to EM radiation that is not in the visible range.

[0365]

[0382] In some embodiments, sensing section 25110 may be realized in a plurality of geometrical formations and / or may be constructed from materials with properties suitable for allowing the passage of EM radiation with minimal attenuation and / or distortion, thereby enabling accurate spectral analysis.

[0366]

[0383] In some examples, the sensing section 25110 may be at least partly transparent configured for allowing propagation of EM radiation in the visible range , e.g., for remote sensing. In some examples, sensing section 25110 may be configured for allowing the passage of EM radiation above and / or below the visible range, e.g., for enabling remote sensing.

[0367]

[0384] In some embodiments, the sensing section 25110 may be configured to enhance and / or modify specific characteristics of the EM radiation to optimize the performance of the spectral analysis. For example, EM radiation characteristics may comprise the following: phase; wavelength; polarization; intensity; or any combination of the aforementioned.

[0368]

[0385] In some embodiments, the sensing section 25110 may be configured to be operably coupled with the receiving chamber 25100, such that the coupling may allow the receiving chamber 25100 to be suitable for holding and / or retaining MM within the chamber. Accordingly, this may be achieved through the use of materials, coatings, and / or structural features that may prevent leakage and support the containment of MM within receiving chamber 25100. Additionally, the dimensions of the sensing section 25110 may vary. For example, the dimensions may be adapted to the spectral range applied.

[0369]

[0386] In some embodiments, a cover 25120 may be implemented for operably coupling the sensing section 25110 with the receiving chamber 25100. The sensing section 25110 and / or the sensing section cover 25120 may include an impermeable layer and / or an integrated barrier that may prevent leakage of MM from the receiving chamber 25100.

[0370]

[0387] It should be noted that the sensing section 25110 functionality should not be construed in a limiting manner. Thereby different measurement modes may be facilitated by the sensing section 25110. For example, in addition to spectral analysis, the sensing section 25110 may allow image processing of the contained MM in the receiving chamber 25100.

[0371]

[0388] In some embodiments, sensing section 25110 and / or the sensing section cover 25120 may be configured for allowing fasteners-based coupling, friction-based coupling and / or form-fitting coupling with the receiving chamber 25100. As such, the coupling may be facilitated by mechanical engagement by which two or more components sensing section 25110 and / or the sensing section cover 25120 and / or receiving chamber 25100, are physically joined. In some examples, the coupling may be facilitated by chemical engagement, for example, by utilizing adhesives and / or permanent bonding agents, and / or through heating.

[0372]

[0389] In some embodiments, the receiving chamber 25100 may have a corresponding capping module 25200 that may comprise, for example, the following: a cap 25210, a filter sealing element 25220, and a filter element 25230. In some embodiments, the capping module 25200 may be configured for filtering the extracted MM upon intake into the receiving chamber 25100. In some examples, the capping module 25200 may comprise one or more filter elements 25230 integrated with and / or operably linkable to an opening of the capping module 25200, for example, integrated with cap 25210. In some examples, capping module 25200 may regulate the passage of MM into the receiving chamber 25100.

[0373]

[0390] In some embodiments, the filter element 25230 may be configured to selectively allow the flow of MM while preventing the inflow of undesired materials, such as, for example, contaminants and / or debris. The filter element 25230 may comprise, for example, a porous membrane, mesh, and / or other selectively permeable medium.

[0391] Reference is now made to Fig. S7. Cross section C-C 26000 of the receiving chamber 25100 is revealing of a divide 26115 illustrated with a dashed line. In some embodiments, divide 26115 may partition the receiving chamber 25100 into a plurality of sections, e.g., as follows:

[0374]

[0392] a fluid intake section 26100 configured for receiving the extracted MM into the receiving chamber 25100.

[0375]

[0393] a restricted flow section 26200 configured for introducing hindrances that may provide change in the flow characteristics, for example, changes in the flow rate, flow regime, and / or flow velocity profile.

[0376]

[0394] an unimpeded flow section 26300 configured for allowing the MM to flow uninterruptedly, e.g., with no significance change in the flow characteristics; and

[0377]

[0395] an outlet section 26400 configured for draining the MM that entered in the fluid intake section 26100 from the receiving chamber 25100.

[0378]

[0396] In some embodiments, divide 26115 may allow flow of MM from the restricted flow section 26200 to the unimpeded flow section 26300 in an instance where the restricted flow section 26200 is full, thereby allowing the MM to overflow into the unimpeded flow section 26300. In some examples, the overflow may enable milk exchange in the restricted flow section 26200.

[0379]

[0397] In some embodiments, the fluid intake section 26100 may comprise an inlet region 26110 allowing flow through, previously presented, optionally arranged capping module 25200. In some examples, the capping module may regulate, filter, and / or prevent spillage of MM when entering into inlet region 26110 to further flow into the receiving chamber 25100. In some examples, previously presented, filter sealing element 25220 and filter element 25230, may be operably coupled, as disclosed by 25240.

[0380]

[0398] Additional reference is made to the restricted flow section 26200. In some embodiments, the MM may be directed to a flow-limiting region 26210, to be further disclosed in figures S11-S13.

[0381]

[0399] Reference is now made to Fig. S8. In some embodiments, the receiving chamber opening 25201 may be threaded configured for operably coupling with the capping module 25200 having a cap 25210, a filter sealing element 25220, and a filter element 25230. It should be noted that the coupling of the capping module 25200 and receiving chamber opening 25201 may be linkable in other means different than the disclosed threaded screw cap.

[0382]

[0400] Reference is now made to Fig. S9. Additional embodiments are disclosed herein, a flow reduction apparatus 27000 may comprise a receiving chamber 27100 having an inlet and an outlet.

[0383]

[0401] In some embodiments, the receiving chamber 27100 may be configured, for example, intaking the extracted MM, adjusting MM flow within the chamber, and / or allowing the system to apply sensing of the sampled MM in the chamber from one or more sensors. In some examples, the receiving chamber 27100 may have a corresponding capping module 27200.

[0384]

[0402] In some embodiments, the capping module 27200 may incorporate a filter 27210 within the module. In addition, in some embodiments, a sensing section cover 27120 may be implemented for operably coupling the sensing section 27110 with the receiving chamber 27100.

[0385]

[0403] Reference is now made to Fig. S10. Cross section B-B 28000 of the flow reduction apparatus 27000 is revealing of a divide 28115 illustrated with a dashed line. In some embodiments, divide 28115 may partition the receiving chamber 27100 into the following sections:

[0386]

[0404] a fluid intake section 28100 configured for receiving the extracted MM into the receiving chamber 27100;

[0387]

[0405] a restricted flow section 28200 configured for introducing hindrances that may provide change in the flow characteristics, for example, changes in the flow rate, flow regime, and / or flow velocity profile (e.g., from turbulent to laminar flow or vice versa);

[0388]

[0406] an unimpeded flow section 28300 configured for allowing the MM to flow uninterruptedly, e.g., with no significance change in the flow characteristics; and

[0389]

[0407] an outlet section 28400 configured for draining the MM that entered in the fluid intake section 28100 from the receiving chamber 27100.

[0390]

[0408] Reference is now made to Fig. Sil. In some embodiments, previously cited receiving chamber 25100 may be implemented in a first configuration 25101 and a second configuration 25102.

[0391]

[0409] In some embodiments, a side view of first configuration 25101A and a cross-sectional view of first configuration 25101B are shown. Correspondingly, a side view of second configuration 25102A and a cross- sectional view of second configuration 25102B are shown.

[0392]

[0410] Reference is now made to previously disclosed flow-limiting region 26210, the flow-limiting region may be configured for changing the flow characteristic of the MM, for example, by reducing flow rate. In addition, the flow-limiting region 26210 may be configured for facilitating sensing of the MM and / or reducing sensing noise.

[0393]

[0411] In some embodiments, the cross-sectional view of first configuration 25101B reveals a first configuration of a flow-limiting region 26211 having a converging nozzle 0. Correspondingly, the cross- sectional view of second configuration 25102B reveals a second configuration of a flow-limiting region 26212 having a converging section a and diverging section p.

[0394]

[0412] It should be noted that the disclosed configurations of the receiving chamber should by no means be construed as affecting the disclosed functionality of the receiving chamber.

[0413] In some embodiments, the flow-limiting region 26210 may facilitate operably employing a sensing regime of MM by altering, primarily reducing, the flow rate of the MM to correspond, for example, to a designated sampling rate.

[0395]

[0414] In some embodiments, the previously disclosed sensing regime may be further configured for controlling the sampling rate. In some embodiments, the sampling rate may be predetermined, dynamically determined, and / or adaptively changed, for example, optical, temperature and / or electrical conductivity measurements may be employed with sampling rate range that may be vary, for example, between ~1 sample / second, ~10 samples / seconds, and / or ~100 samples / seconds. In some embodiments, the range of the sampling rate may vary in correspondence to samples per minute, per hour, per day and / or per week.

[0396]

[0415] In some embodiments, the sampling rate may be adaptive in correspondence to perceived trend in the measurement curve and / or values indicative of healthy milk obtained during a session and / or in correspondence to perceived trend in the measurement curve and / or values indicative of non-healthy milk. Furthermore, the sampling rate may be configured to facilitate the sensing from the onset of a milking session to the termination of a milking session, allowing for averaging of measurements obtained during any milking session. In addition, the sampling rate may be configured for providing a momentary, e.g., in the milliseconds, seconds, or minutes range, measurement output.

[0397]

[0416] In some embodiments, the flow reduction apparatus may be configured for restricting and splitting the MM flow within the apparatus allowing for reducing the flow rate of mammal milk. In some embodiments, the reduced flow may enable the operable matching of the MM flow rate with a corresponding sampling rate.

[0398]

[0417] Reference is now made to Fig. S12. A cross-sectional view of first configuration 25101B reveals a flow-limiting region 26211 having a converging nozzle 0. In some embodiments, the converging nozzle 0 may direct the flow of the discharged MM into a closed channel 26211C.

[0399]

[0418] In some embodiments, a converging nozzle 0 may be employed to reduce MM flow by constricting the cross-sectional area through which the MM passes, for example, cross section area Al may be smaller than A2. In some examples, as the MM enters the nozzle, the gradually decreasing internal diameter may lead to a reduction in flow rate downstream. Thus, converging nozzle may be configured to regulate, restrict, and / or stabilize MM flow allowing for controlled delivery, pressure modulation, and / or turbulence reduction.

[0400]

[0419] Reference is now made to Fig. S13. A cross-sectional view of second configuration 25102B reveals a flow-limiting region 26212 having a convergence-divergence nozzle, e.g., Venturi nozzle.

[0401]

[0420] In some embodiments, the Venturi nozzle comprises a converging section a which may be configured to accelerate the incoming MM, a throttle section T defining a constricted flow area where the MM reaches increased velocity and reduced static pressure, and a diverging section p that may be configured to allow deceleration of the fluid with a corresponding pressure recovery.

[0402]

[0421] In some embodiments, the sensing of the MM may be performed via an upper sensing section 25110U, a lower sensing section 25110L, or both. In some examples, reducing sensing noise may comprise reducing air bubbles introduced during MM entering the receiving chamber.

[0403]

[0422] Reference is now made to Fig.S14. According to some embodiments, MM mixed with air bubbles 100 may be formed when a MM enters the fluid intake section 26100. For illustrative purposes, an abstraction of flow-splitting and flow-reduction capabilities are illustrated by drawing 29000.

[0404]

[0423] In some embodiment, an upper restricted flow section 29220, e.g., air-bubble removal section, configured for allowing air bubbles to rise. In some examples, the upper restricted flow section 29220 may comprise a less ordered MM flow. In addition, a lower restricted flow section 29210, e.g., sensing section, may be configured to allow MM to sink. In some embodiments, the lower restricted flow section 29210 may be utilized as a sampling region characterized by a more ordered MM flow compared to the MM flow in the upper restricted flow section 29220.

[0405]

[0424] In some examples, the flow of MM in the upper restricted flow section 29220 may be more turbulent compared to the MM flow in the lower restricted flow section 29210.

[0406]

[0425] In some embodiments, an unimpeded flow section 29300 configured for allowing an overflow of MM mixed with air bubbles to pass through, for example, in the event that the upper restricted flow section 29220 is fully occupied with incoming MM.

[0407]

[0426] In some embodiments, an outlet section 29400 configured for receiving MM mixed with air bubbles and filtered MM to be discharged from the receiving chamber through the receiving chamber outlet.

[0408]

[0427] Reference is now made to Fig. Pl. Graph 31100 schematically depicts a single cow fat level prediction model. In some embodiments, the system may be configured for sensing, measuring, and monitoring a single cow for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0409]

[0428] Accordingly, graph 31100 schematically depicts measured fat vs predicted fat, where values on graph 31100 are associated with milk from a single cow.

[0410]

[0429] Reference is now made to Fig. P2. Graph 31200 schematically depicts a milk tank fat level prediction model. In some embodiments, the system may be configured for sensing, measuring, and monitoring milk in a milk tank for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0430] Accordingly, graph 31200 schematically depicts measured fat vs predicted fat, where values on graph 31200 are associated with milk in a milk tank.

[0411]

[0431] Reference is now made to Fig. P3. Graph 32100 schematically depicts a single cow protein level prediction model. In some embodiments, the system may be configured for sensing, measuring, and monitoring a single cow for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0412]

[0432] Accordingly, graph 32100 schematically depicts measured protein vs predicted protein, where values on graph 32100 are associated with milk from a single cow.

[0413]

[0433] Reference is now made to Fig. P4. Graph 32200 schematically depicts a milk tank protein level prediction model. In some embodiments, the system may be configured for sensing, measuring, and monitoring milk in a milk tank for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0414]

[0434] Accordingly, graph 32200 schematically depicts measured protein vs predicted protein, where values on graph 32200 are associated with milk in a milk tank.

[0415]

[0435] Reference is now made to Fig. P5. Graph 33100 schematically depicts an inline measurement graph. In some embodiments, the system may be configured for sensing, measuring, and / or monitoring EM radiation transmittance intensity across time, where a discrete time interval Ati is associated with the duration of a single sample index. In some examples, a timeframe of Ati may be in the order of magnitude of, approximately, seconds, deci-seconds (0.1 seconds), and / or centi seconds (0.01 seconds). It should be noted that timeframe of Ati may correspond to system sampling rate (not shown) that may be in the order of magnitude of, approximately, 1 Hz, 10 Hz, and / or 100 Hz, in the order of magnitude of kHz (e.g., 1-999 kHz), in the order of magnitude of MHz (e.g., 0.1-999 MHz).

[0416]

[0436] It should be noted that for illustrative purposes only and for the further interpretation clarity of graph 33100 sample index axis may not show values of each sample index. However, appropriate timeframes of interest, e.g. Ati, Ati and At2, are presented on the sample index axis.

[0417]

[0437] In addition, the EM radiation transmittance intensity axis, also, does not show tick marks of each transmittance intensity measurement. Nonetheless, the qualitative indicators of Low and High transmittance intensity are presented.

[0418]

[0438] As shown, measured intensity values may be considered relatively stable when exhibiting only minor fluctuations across time. Minor fluctuations in measured intensity values may refer to fluctuations between consecutive measurements that are in one or less order of magnitude difference from each other, e.g., within a certain range, within which the intensity may be considered to be relatively stable and / or uniform. Such temporal consistency and / or uniformity in measured intensity may indicate, for example, one or more the following: a well-controlled sensing environment, minimal interference, and / or reliable interaction between the probing EM radiation and the MM. In some embodiments, the interaction between the probing EM radiation and the MM may occur in the sensing section of the receiving chamber. In other embodiments, measured intensity values may be of reflectance intensity.

[0419]

[0439] According to some embodiments, Fig. P5 shows an inline measurement graph 33100, where the following distinct regions may be identified:

[0420]

[0440] A steady empty chamber 33110 region associated with sensing, measuring, and monitoring EM radiation intensity across time when the receiving chamber is (substantially) empty, e.g., (substantially) devoid from MM content. In some examples, in an empty receiving chamber the transmittance intensity may result in a comparatively a High transmittance intensity.

[0421]

[0441] Steady full chamber 33120 region associated with sensing, measuring, and monitoring EM radiation intensity across time when the receiving chamber is fully or substantially fully occupied with MM content. In some examples, in a full receiving chamber transmittance intensity maybe of a Low transmittance intensity. In some embodiments, comparatively stable Low transmittance intensity readings, e.g., when the receiving chamber is fully occupied with MM content, may reflect, for example, the following: optimal optical alignment, low background noise, and / or consistent optical properties within the receiving chamber and / or within the contained MM.

[0422]

[0442] Chamber filling region 33130 associated with sensing, measuring, and monitoring EM radiation intensity across time when the receiving chamber is being filled with MM content. In some embodiments, the filling of MM content into the receiving chamber may be referring to, for example, enabling a reduced turbulence flow of MM upon flowing into the receiving chamber and / or allowing for stable fluid, e.g. MM, behavior. In some examples, the filling of MM content into the receiving chamber may be executed across or during a timeframe of Atl.

[0423]

[0443] Chamber slowly emptying region 33140 may be associated with sensing, measuring, and monitoring EM radiation intensity across time when the receiving chamber is being emptied, e.g., slowly, from MM content. In some embodiment, the (e.g., relatively slow) emptying of MM content from the receiving chamber may be referring to, for example, enabling a controlled flow of MM upon flowing out from the receiving chamber. In some examples, the emptying of MM content from the receiving chamber may be executed across or during a timeframe of At2. In some embodiments, identifying distinct regions across inline measurements may enable differentiation of MM flow characteristics over time and / or space, allowing detection of localized anomalies, and facilitating dynamic and / or adaptive adjustment of system parameters. In some examples, the valve may be controlled based on sensed parameters values (e.g., optical parameter values, spectral values, flow characteristics, environmental characteristics) while, for example, allowing free flow of MM. The valve may be controlled for widening or narrowing the narrowing section of the throttle, and / or any actionable manipulation, e.g., for the adjusting of flow parameters values, e.g., based on system parameters. As a result, improved system responsiveness, operational efficiency, predictive maintenance capabilities and / or prediction accuracy associated with detecting a preclinical mastitis and / or determining a probability of a clinical condition impending mastitis onset within an upcoming time interval may be achieved.

[0424]

[0444] In some embodiments, stable fluid, e.g. MM, behavior within the sensing section may contribute to improved measurement reliability and / or reduced signal noise. By minimizing turbulence, flow irregularities, and / or transient disturbances in the MM, the system may maintain consistent optical paths and / or predictable interaction conditions between the probing EM radiation and the MM constituents. Such stability enhances the accuracy of optical measurements by reducing variability and / or suppressing background interference. In some examples, stable fluid behavior may be achieved within a timeframe of Atl. In some examples, the timeframe of Atl may be in the order of magnitude of the timeframe of Ati.

[0425]

[0445] In some embodiments, the filling and / or emptying of the receiving chamber maybe in the timeframe of Atl and / or in the timeframe of At2. In some examples, the timeframe of Atl in shorter than At2. In some examples, the timeframe of Atl is in an order of magnitude shorter in At2.

[0426]

[0446] In some embodiments, intermittent regions (not shown) may be identified when sensing, measuring, and monitoring EM radiation intensity across time. In some examples, the system may be configured for obtaining intermittent regions that exhibit stable fluid behavior and / or minor fluctuations in measured intensity values. These intermittent regions may arise naturally due to flow dynamics and / or may be engineered through structural and / or control-based manipulation. The temporal stability of MM movement and signal intensity within such regions may support additional measurement precision, reduced noise, and / or improved repeatability.

[0427]

[0447] Accordingly, these intermittent regions (not shown) may be selectively targeted for secondary and / or complementary sensing tasks, such as, for example, spectral analysis, scattering measurements, and / or flow characterization. In addition, these intermittent regions may be in transit from a steady empty chamber region to a steady full camber region and vica versa. It is noted that the identification and use of such regions may vary depending on system configuration and sensing objectives, and are considered to be within the scope of the present disclosure.

[0428]

[0448] It is noted that while minor intensity shifts are expected due to inherent system dynamics and / or MM constituents' variability, sustained Low and / or High transmittance intensity with limited deviation may serve as a marker of robustness of the disclosed apparatus, system and method. As already mentioned herein, the examples discussed with respect to Fig. P5 may also be applicable with respect to the measurement of reflectance alone, or in combination with transmittance.

[0449] Reference is now made to Fig. P6. Graph 33200 schematically depicts an inline fat model graph of measured fat vs predicted fat, according to some embodiments. In such examples, graph 33200 may incorporate statistical modeling techniques such as, for example, Partial Least Squares Regression (PLSR), Leave-One-Out (LOO) validation, and broader cross-validation (CV) frameworks. These models may be constructed using unnormalized input data, preserving the original scale and distribution of the measured variables, e.g., fat content in the MM. It should be noted that such combination of advanced modeling and raw data integrity may yield visual and analytical outputs that surpass conventional benchmarks.

[0429]

[0450] Additional examples:

[0430]

[0451] Embodiments pertain to a system configured to monitor at least one mammal for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0431]

[0452] In embodiments, the system comprises at least one sensor that is configured for sensing at least one characteristic descriptive of mammal related information.

[0432]

[0453] In embodiments, the system comprises at least one memory element configured to store data and executable instructions.

[0433]

[0454] In embodiments, the system comprises at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following:

[0434]

[0455] receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; and

[0435]

[0456] processing the received sensor data for detecting mastitis, for detecting a preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0436]

[0457] In embodiments, the at least one characteristic comprises: mammal milk fat level; mammal milk protein level; mammal milk lactose level; and / or mammal milk electrical characteristic.

[0437]

[0458] In embodiments, the at least one characteristic comprises at least one of the following: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk electrical characteristic, or any combination of the aforesaid.

[0438]

[0459] Embodiments pertain to a system configured to monitor at least one mammal for detecting mastitis, for detecting a preclinical mastitis and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval, wherein the system comprises:

[0439]

[0460] at least one sensor configured for sensing at least one characteristic descriptive of mammal related information;

[0461] at least one memory element configured to store data and executable instructions; and

[0440]

[0462] at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following:

[0441]

[0463] receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information;

[0442]

[0464] processing the received sensor data for detecting mastitis, for detecting a preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset within an upcoming time interval.

[0443]

[0465] In embodiments, the system comprises at least one sensor configured to sense the at least one characteristic descriptive of mammal related information for providing the sensor data.

[0444]

[0466] In embodiments, the at least one sensor is configured to continuously and / or intermittently sense the at least one characteristic descriptive of mammal related information.

[0445]

[0467] In embodiments, the at least one sensor is configured to sense, over a recent monitoring time interval, the at least one characteristic descriptive of mammal related information.

[0446]

[0468] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval.

[0447]

[0469] In embodiments, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics to collectively factor-in the plurality of distinct mammal characteristics.

[0448]

[0470] In embodiments, the detecting and / or determining is performed in real-time or substantially in real-time with respect to the sensing of the at least one characteristic descriptive of mammal related information.

[0449]

[0471] In embodiments, the system is configured to distinguish between a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis.

[0450]

[0472] In embodiments, the system is configured distinguish between a first anomaly of a characteristic descriptive of mammal related information related to clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to clinical mastitis.

[0451]

[0473] In embodiments, the processing of the sensor data is performed by a trained machine-learning (ML) model.

[0452]

[0474] In embodiments, the processing of the sensor data is performed by a classifier.

[0453]

[0475] In embodiments, the processing of the sensor data is performed by a rule-based model.

[0476] In embodiments, the processing of the sensor data comprises comparing at least some of the sensor data descriptive of one or more of the at least one mammal characteristic against one or more thresholds associated with a normal and / or abnormal characteristic descriptive of mammal-related information parameter values.

[0454]

[0477] In embodiments, the at least one characteristic comprises: mammal milk fat level; mammal milk protein level; mammal milk lactose level; and / or mammal milk electrical characteristic.

[0455]

[0478] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; or any combination of the aforesaid.

[0456]

[0479] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

[0457]

[0480] In embodiments, the electrical characteristic comprises at least one of the following: impedance;

[0458]

[0481] conductivity; electric potential difference; capacitance; or any combination of the aforesaid. In embodiments, the at least one mammal comprises cattle, buffaloes, goats, sheep, camels, yaks, horses, reindeers, and / or donkeys.

[0459]

[0482] In embodiments, the cattle comprise cows, bulls, oxen, and / or calves.

[0460]

[0483] In embodiments, the at least one characteristic of the at least one mammal milk pertains to an individual mammal, a group of mammals, a herd, dairy farm, and / or a plurality of mammals located in a geographic region.

[0461]

[0484] Embodiments pertain to an apparatus configured to reduce mammal milk flow rate and to reduce sensing noise. The apparatus may comprise a receiving chamber for intaking mammal milk into the apparatus via the inlet, the receiving chamber comprising a fluid inlet, a fluid outlet, and one or more sensing sections that are at least partially transparent to electromagnetic radiation; and a fluid restriction section for reducing the velocity and / or the flow rate of the mammal milk flow. The one or more sensing sections are configured for allowing optical sensing of the mammal milk of reduced flow velocity and / or reduced flow rate.

[0462]

[0485] Embodiments pertain to an apparatus configured for reducing mammal milk flow rate and reducing sensing noise, the apparatus comprising:

[0463]

[0486] a receiving chamber for intaking mammal milk into the apparatus via the inlet, the receiving chamber comprising a fluid inlet, a fluid outlet, and one or more sensing sections that are at least partially transparent to electromagnetic radiation; and

[0487] an air bubble removal section configured for removing air bubbles from the intaken mammal to provide bubble-reduced mammal milk;

[0464]

[0488] wherein the one or more sensing sections are configured for enabling remote sensing of the bubble-reduced mammal milk.

[0465]

[0489] In embodiments the apparatus(es) comprise a capping module configured for:

[0466]

[0490] filtering out containment and / or configured for sampling the mammal milk at a sampling rate that corresponds with the reduced mammal milk velocity and / or flow rate.

[0467]

[0491] In embodiments the apparatus(es) comprise a housing module configured for providing optical isolation for enabling the sensing, and / or configured for sampling the mammal milk at a sampling rate that corresponds with the reduced mammal milk velocity and / or flow rate.

[0468]

[0492] In embodiments, the two apparatuses may be configured as one apparatus. In embodiments, various systems discussed herein may be configured as one system.

[0469]

[0493] Embodiments, pertain to a system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising:

[0470]

[0494] at least one sensor configured for sensing at least one characteristic descriptive of mammal related information;

[0471]

[0495] at least one memory element configured to store data and executable instructions; and

[0472]

[0496] at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following:

[0473]

[0497] receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information;

[0474]

[0498] processing the received sensor data for predicting onset of mastitis within an upcoming time interval;

[0475]

[0499] wherein the onset of the mastitis is predictable for mammal milk somatic cell count (SCC) that is about equal or less than 200 cells / pL or less; or about equal or less than 180 cells / pL; about equal or less than 150 cells / pL, or about equal or less than 120 cells / pL; or about equal or less than 100 cells / pL.

[0476]

[0500] In embodiments, the system is configured for determining the onset of pre-clinical mastitis.

[0477]

[0501] In embodiments, the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

[0502] In embodiments, the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete reflectance spectral; and wherein, the at least one processor is configured to correlate MM PH level based on the optical sensor data.

[0478]

[0503] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval; and wherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

[0479]

[0504] In embodiments, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics to collectively factor-in the plurality of distinct mammal characteristics.

[0480]

[0505] In embodiments, the detecting and / or determining is performed in real-time or substantially in real-time with respect to the sensing of the at least one characteristic descriptive of mammal related information.

[0481]

[0506] In embodiments, the system is further configured to distinguish between:

[0482]

[0507] a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and

[0483]

[0508] a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis or clinical mastitis.

[0484]

[0509] In embodiments, the processing of the sensor data is performed by one of the following: a trained machine-learning (ML) model; a classifier; a rule-based model; a deterministic model; or any combination of the aforesaid.

[0485]

[0510] In embodiments, the at least one characteristic comprises: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk pH level; and / or mammal milk electrical characteristic.

[0486]

[0511] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

[0487]

[0512] In embodiments, the at least one characteristic of the at least one mammal milk pertains to an individual mammal, a group of mammals, a herd, dairy farm, and / or a plurality of mammals located of a geographic region.

[0488]

[0513] In embodiments, the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

[0514] In embodiments, the system is configured to detect changes in mammal characteristic due to the presence of milk bacterium cultures comprising at least one of the following: Streptococcus agalactiae, Staphylococcus aureus, Staphylococcus spp, Mycoplasma spp, environmental Streptococci, Coliforms, or any combination of the aforesaid.

[0489]

[0515] In embodiments, the system is configured to detect a preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset at an accuracy of at least 90%, at least 94%, or at least 98%., wherein the corresponding control system is configured to sense: a smaller plurality of distinct mammal characteristics, and / or a different plurality of distinct mammal characteristics.

[0490]

[0516] Embodiments pertain to a method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset.

[0491]

[0517] In embodiments, the method comprises receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein the onset of the mastitis is predictable for mammal milk somatic cell count (SCC) that is about equal or less than 200 cells / pL or less; or about equal or less than 180 cells / pL; about equal or less than 150 cells / pL, or about equal or less than 120 cells / pL; or about equal or less than 100 cells / pL.

[0492]

[0518] Embodiments pertain to a system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising: at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a trend of a mammal milk somatic cell count (SCC) within the range of 50 to 200 cells / pL; or within 80 to 120 cells / pL.

[0493]

[0519] In embodiments, the system is configured for determining the onset of pre-clinical mastitis.

[0494]

[0520] In embodiments, the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

[0495]

[0521] In embodiments, the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of transmitted and / or reflected spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

[0522] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval; and wherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

[0496]

[0523] In embodiments, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such collectively factor-in the plurality of distinct mammal characteristics.

[0497]

[0524] In embodiments, the system is further configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis or clinical mastitis.

[0498]

[0525] In embodiments, the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

[0499]

[0526] Embodiments pertain to a method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset. In embodiments, the method comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a trend of a mammal milk somatic cell count (SCC) within the range of 50 to 200 cells / pL; or within 80 to 120 cells / pL.

[0500]

[0527] Embodiments to a system configured to monitor at least one mammal for predicting onset of a clinical condition. In embodiments, the system comprises at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following:

[0501]

[0528] receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information;

[0502]

[0529] processing the received sensor data for predicting onset of mastitis within an upcoming time interval;

[0503]

[0530] wherein an onset of the mastitis is predictable based on a change of 10% or more of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

[0504]

[0531] In embodiments, the system is configured for determining the onset of pre-clinical mastitis.

[0532] In embodiments, the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

[0505]

[0533] In embodiments, the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete transmitted spectral and / or discrete reflectance spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

[0506]

[0534] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval; and the upcoming time interval comprises, for example, at least one day, at least two days, at least three days, at least one week, or at least two weeks.

[0507]

[0535] In embodiments, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such to collectively factor-in the plurality of distinct mammal characteristics.

[0508]

[0536] In embodiments, the system is configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis or clinical mastitis. In embodiments, the at least one characteristic comprises: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk pH level; and mammal milk electrical characteristic.

[0509]

[0537] In embodiments, the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

[0510]

[0538] Embodiments pertain to a method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset, comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval. In some examples, an onset of the mastitis is predictable based on a change of 10% or more of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

[0511]

[0539] Embodiments pertain to a system configured to monitor at least one mammal for predicting onset of a clinical condition. In embodiments, the system comprises at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 100% or less of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

[0512]

[0540] In embodiments, the system is configured for determining the onset of pre-clinical mastitis.

[0513]

[0541] In embodiments, the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

[0514]

[0542] In embodiments, the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete transmitted and / or discrete reflectance spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

[0515]

[0543] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval.

[0516]

[0544] In embodiments, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

[0517]

[0545] In embodiments, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such to collectively factor-in the plurality of distinct mammal characteristics.

[0518]

[0546] In embodiments, the system is configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis or clinical mastitis.

[0519]

[0547] In embodiments, the at least one characteristic comprises, for example: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk pH level; and / or mammal milk electrical characteristic.

[0520]

[0548] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

[0521]

[0549] Embodiments pertain to a method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset. In embodiments, the method comprises receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 100% or less of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

[0522]

[0550] In embodiments, the at least one sensor is configured to sense a characteristic related to mammal milk, the at least one sensor comprising at least one of the following: an optical sensor; a sensor configured to sense an electrical characteristic of the milk; a thermal sensor; a temperature sensor; a chemical sensor; a biological sensor; a biochemical sensor; an electrochemical sensor; a flow sensor; a pressure sensor; or any combination of the aforesaid.

[0523]

[0551] It is noted that the following embodiment, further disclosing the optical sensor, is presented solely for illustrative purposes and, as such, is not accompanied by a corresponding figure. Nevertheless, this embodiment is fully within the scope of the present disclosure. Furthermore, the described embodiment may, in certain implementations, overlap partially or entirely with one or more of the other embodiments disclosed herein.

[0524]

[0552] In some embodiments, the optical sensor may be, interchangeably, referred to as an optical system comprising at least one optical sensing module configured for concurrently and operably engaging with the MM for characterization of milk during milking.

[0525]

[0553] In some embodiments, the optical system may comprise a scattering module, a spectral analysis module, and / or an optical flow module.

[0526]

[0554] In some examples, the optical system may comprise a light source configured to transmit light through the sensing section, through milk containing sections, and / or through any section of interest in the system. In some embodiments, the optical system may comprise at least one detector or at least two detectors configured to receive scattered light. In some examples, the at least two detectors may be positioned at multiple different angles with respect to the sensing section. The term "scattering" may, for example, relate to Mie scattering, Rayleigh scattering, and / or intensity distribution.

[0527]

[0555] In some embodiments, the optical system may be configured to perform spectral analysis, and may comprise a light source and a spectral detection element that may be configured to measure the absorption, transmission, and / or reflection characteristics of light directed to interact with the MM over a defined spectral range, for example: ultraviolet (UV), visible (VIS), near-infrared (NIR), short-wave infrared (SWIR), mid-infrared (MIR), and / or long-wave infrared (LWIR) spectral range, and / or other spectral ranges. In some embodiments, MM characteristics may be sensed based on ultrasound.

[0528]

[0556] In some embodiments, the optical system may be configured for determining flow characteristics of milk in a cell. For example, the optical system may be configured to characterize, for example, flow rate, flow direction, turbulence, and / or shear profiles. In some examples, the optical flow module may be implemented to execute, for example, the following: determine MM flow velocity, assess dynamic changes in interference patterns caused by moving particles within the MM, detect flow-induced variations in the MM, monitor the displacement of tracer particles, and / or natural contrast features in the MM. In some examples, flow characteristics may be determined based on Doppler shift, speckle pattern analysis, light beam modulation, image-based tracking of fluid movement, and / or the like.

[0529]

[0557] In some embodiments, the scattering module may be configured for enabling scattering measurement that may be performed based on one or more optical measurement principles including, for example: Mie scattering, Rayleigh scattering, intensity distribution analysis, angular scattering analysis, phase function evaluation, and / or polarization-based detection.

[0530]

[0558] In some embodiments, the spectral measurement may be based on suitable optical principles including, for example: Beer-Lambert absorption, dispersive spectrometry (e.g., using prisms or diffraction gratings), Fourier-transform infrared (FTIR) spectroscopy, interferometry, tunable optical filtering (e.g., using acousto-optic and / or liquid crystal tunable filters), and / or Raman spectroscopy. These principles may enable the quantification and characterization of molecular constituents including, for example: proteins, lipids, and / or other analytes.

[0531]

[0559] In some embodiments, the optical measurement of fluid flow may be based on suitable optical principle including, for example: Doppler shift analysis, speckle pattern analysis, light beam modulation, and / or image-based tracking of fluid movement.

[0532]

[0560] It is noted that the above lists of principles are illustrative and not exhaustive. These principles may be applied individually or in combination. Additional optical measurement principles, spectral measurement principles, optical flow measurement principles and / or techniques not explicitly listed herein may also be applicable depending on the specific implementation context.

[0533]

[0561] In some embodiments, at least one optical sensing module may employ one or more light sources configured to transmit and / or reflect light in different operational modes. These modes may include continuous wave (CW) emission, pulsed emission, modulated intensity emission, and / or wavelength- tunable emission. The light source may comprise, for example, a halogen, a laser diode, LED, super luminescent diode, and / or other suitable emitter capable of producing light at one or more wavelengths.

[0534]

[0562] In some embodiments, at least one optical sensing module may include one or more detectors configured to receive scattered light resulting from interaction with a sample and / or medium, for example, MM in the sensing section. The detectors may operate in various modes, including time-resolved detection, angle-resolved detection, polarization-sensitive detection, and / or spectral-resolved detection. Suitable detectors may include photodiodes, avalanche photodiodes (APDs), photomultiplier tubes (PMTs), Focal Plane Array (FPA), CMOS, CCD sensor arrays, and / or other optoelectronic devices capable of capturing light intensity, phase, and / or wavelength information. In certain configurations, multiple detectors may be used in parallel to capture complementary scattering data across different dimensions.

[0535]

[0563] In some embodiments, two or more of the disclosed modules may be configured to operate in combination to achieve enhanced functionality and / or measurement accuracy.

[0536]

[0564] In some examples, the combined operation of the two or more of the disclosed modules may be sequential, parallel, or interdependent, depending on the system architecture and measurement objectives. Such modular integration allows for flexible adaptation to various milking scenarios and supports multi-dimensional MM data acquisition.

[0537]

[0565] It is noted that any specific combinations described herein are illustrative and should not be construed in a limiting manner. Additional combinations and / or configurations may be implemented within the scope of the present disclosure. For example, one or more of the disclosed modules may be combined with additional measurements modalities, such as, for example, electrical conductivity (EC) and temperature, thereby providing complementary information on MM composition and flow dynamics.

[0538]

[0566] It is emphasized that the following embodiments descriptive of the optical sensor are provided as additional disclosures and may or may not be associated with the optical sensing modules previously described. In some implementations, these embodiments may function independently, while in others they may be integrated with one or more of the disclosed modules to achieve complementary and / or enhanced functionality.

[0539]

[0567] In some examples, the optical sensor may comprise a spectral sensing unit configured for monitoring a characteristic related to mammal milk, for example by spectral separation of sensed light. Additionally, the spectral sensing unit may be configured to execute reflectance and / or transmission measurements related to mammal milk.

[0540]

[0568] In some embodiments, the optical measurement may be adaptive to the sensed characteristic related to mammal milk, for example, by selecting an appropriate spectral range in which the measurement is performed. The spectral range of the optical measurement may comprise EM radiation in the ultraviolet (UV), visible (VIS), near-infrared (NIR), shortwave infrared (SWIR), and / or other spectral bands adaptive for sensing characteristic related to mammal milk.

[0541]

[0569] Furthermore, the spectral sensing unit may comprise real time calibration and / or compensation functionality configured to dynamically adjust operational parameters based on detected variations in environmental and / or system conditions. For example, the system may monitor optical signals, spectral fluctuations, drift, and / or other relevant factors and apply corrective measures in real time to maintain desired accuracy of the measurements.

[0570] In embodiments, spectral separation may be achieved along an illumination path, a detection path, or both, related to the spectral sensing unit. Such spectral separation may facilitate the differentiation, isolation, and / or selective processing of optical sensor data based on wavelength and / or spectral content.

[0542]

[0571] In embodiments, the optical sensor may incorporate one or more optical elements, including but not limited to optical filters (e.g., bandpass, notch, and / or dichroic filters), dispersive elements (e.g., prisms and / or diffraction gratings), and / or integrated spectral sensing hardware that may be capable of resolving spectral components directly at the point of detection. These components may be arranged in-line and / or off-axis and may be configured to operate in static or dynamically tunable modes. The implementation of spectral separation may serve to enhance signal fidelity, reduce crosstalk, enable multiplexing, and / or support other wavelength-dependent functionalities.

[0543]

[0572] In some embodiments, an optical sensing module may include a spectral analysis module which may include, for example, a light source (e.g., a broadband illumination source, discrete LEDs, and / or other emitters), and a spectral detection element employed to measure the absorption, transmission, and / or reflection characteristics of the milk over a defined spectral range (e.g., UV, VIS, NIR, SWIR, MIR, and / or spectral ranges). The spectral measurement may be based on suitable optical principles, including but not limited to, for example, Beer-Lambert absorption, dispersive spectrometry, interferometry and / or tunable optical filtering. These measurements enable quantification of molecular constituents, including proteins and other analytes.

[0544]

[0573] In some embodiments, an optical sensing module may be configured as an optical flow module. An optical measurement unit configured to determine flow characteristics of milk in a cell. The flow determination may be based on any suitable optical principle, including but not limited to Doppler shift, speckle pattern analysis, light beam modulation, and / or image-based tracking of fluid movement. In some embodiments, the sensor data may be acquired by one or more sensing regimes. For example, when acquiring sensor data by the spectral sensing unit a single discrete measurement, continuous and / or repeated measurements may be executed in real-time during a milking session and / or in temporal proximity to the milking session.

[0545]

[0574] In some embodiments, the acquired optical sensor data may be subjected to processing using analysis models. These analysis models may be configured to detect anomalies, trends, deviations, a level of correspondence, and / or associations within the spectral data, as well as to identify spectral fingerprints and / or patterns indicative of particular materials, conditions, and / or events related to a characteristic of MM.

[0546]

[0575] In some embodiments, the optical sensor data may be correlated and / or associated with data obtained from one or more additional sensing modalities, such as, for example, electrical, thermal, chemical, biological , biochemical, electrochemical, flow, pressure, or any combination of the aforesaid sensing modalities. Additionally, the optical sensor data may be analyzed (e.g., correlated) in conjunction with data obtained from an empirical lab-test database and / or a professional literature database. In some examples, the (e.g., correlated) data may improve accuracy, context-awareness, and / or system detection and / or prediction robustness.

[0547]

[0576] For illustrative purposes, the optical sensor comprising a spectral sensing unit may be configured for obtaining discrete reflectance spectra. Furthermore, the optical sensor data may comprise the discrete reflectance spectra. Thus, allowing the optical sensor data to be, optionally, correlated with at least one MM characteristic, for example, MM PH level based on the obtained discrete reflectance spectra.

[0548]

[0577] Accordingly, the system may be configured for utilizing analysis models to compare the determined MM PH level with corresponding empirical lab-test database of PH levels. Therefore, providing support for the established association (e.g., correlation) between MM PH level with the obtained discrete reflectance spectra.

[0549]

[0578] In embodiments, the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

[0550]

[0579] In embodiments, the milk tank receives milk from a plurality of mammals.

[0551]

[0580] In embodiments, the system is configured to detect changes in mammal characteristics due to the presence of milk bacterium cultures.

[0552]

[0581] In embodiments, the milk bacterium cultures comprise at least one of the following: Streptococcus agalactiae, Staphylococcus aureus, Staphylococcus spp, Mycoplasma spp, environmental Streptococci, Coliforms, or any combination of the aforesaid.

[0553]

[0582] In embodiments, the system is configured to detect a preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset at a significantly higher accuracy level compared to a corresponding control system, wherein the corresponding control system is configured to sense: a smaller plurality of distinct mammal characteristics, and / or a different plurality of distinct mammal characteristics.

[0554]

[0583] In embodiments, the system is configured to detect preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset at an accuracy of at least 90%, at least 94%, or at least 98%.

[0555]

[0584] Embodiments pertain to a method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset.

[0585] In embodiments, the method comprises: receiving sensor data that is descriptive of mammal related information; processing the received sensor data for detecting mastitis, for detecting a preclinical mastitis, and / or for determining a probability of a clinical condition impending mastitis onset.

[0556]

[0586] In embodiments, the method comprises sensing the at least one characteristic descriptive of mammal related information for providing the sensor data.

[0557]

[0587] In embodiments, the method comprises continuously and / or intermittently sensing the at least one characteristic descriptive of mammal related information.

[0558]

[0588] In embodiments, the method comprises sensing, over a recent monitoring time interval, the at least one characteristic descriptive of mammal related information.

[0559]

[0589] In embodiments, the upcoming time interval is consecutive of the recent monitoring time interval. In some embodiments, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

[0560]

[0590] In embodiments of the method, the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics to collectively factor-in the plurality of distinct mammal characteristics.

[0561]

[0591] In embodiments, the detecting and / or determining is performed in real-time or substantially in real-time with respect to the sensing of the at least one characteristic descriptive of mammal related information.

[0562]

[0592] In embodiments, the method comprises distinguishing between a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre-clinical mastitis.

[0563]

[0593] In embodiments, the method comprises distinguishing between: a first anomaly of a characteristic descriptive of mammal related information related to clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to clinical mastitis.

[0564]

[0594] In embodiments, the processing of the sensor data is performed by a trained machine-learning (ML) model.

[0565]

[0595] In embodiments, the processing of the sensor data is performed by a classifier.

[0566]

[0596] In embodiments, the processing of the sensor data is performed by a rule-based model.

[0567]

[0597] In embodiments, the processing of the sensor data comprises comparing at least some of the sensor data descriptive of one or more of the at least one mammal characteristic against one or more thresholds associated with a normal and / or abnormal characteristic descriptive of mammal related information parameter values.

[0598] In embodiments, the at least one mammal characteristic comprises at least one of the following: mammal milk fat level; mammal milk protein level; mammal milk lactose level; and mammal milk electrical characteristic.

[0568]

[0599] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; or any combination of the aforesaid.

[0569]

[0600] In embodiments, the at least one mammal characteristic further comprises at least one of the following: mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

[0570]

[0601] In embodiments, the electrical characteristic comprises at least one of the following: impedance; conductivity; electric potential difference; capacitance; or any combination of the aforesaid.

[0571]

[0602] In embodiments, the at least one mammal is selected from a group consisting of cattle, buffaloes, goats, sheep, camels, yaks, horses, reindeers, and donkeys.

[0572]

[0603] In embodiments, the cattle are selected from a group consisting of cows, bulls, oxen, and calves.

[0573]

[0604] In embodiments, the at least one characteristic of the at least one mammal milk pertains to an individual mammal, a group of mammals, a herd, dairy farm, and / or a plurality of mammals of a geographic region.

[0574]

[0605] In embodiments, the at least one sensor is configured to sense a characteristic related to mammal milk, the at least one sensor comprising at least one of the following: an optical sensor; a sensor configured to sense an electrical characteristic of the milk; a thermal sensor; a temperature sensor; a chemical sensor; a biological sensor; a biochemical sensor; an electrochemical sensor; a flow sensor; a pressure sensor; or any combination of the aforesaid.

[0575]

[0606] In embodiments, the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

[0576]

[0607] The various features and steps discussed above, as well as other known equivalents for each such feature and / or step, can be mixed and matched by one of the ordinary skills in this art to perform methods in accordance with principles described herein.

[0577]

[0608] Although the disclosure has been provided in the context of certain embodiments and examples, it will be understood by those skilled in the art that the disclosure extends beyond the specifically described embodiments to other alternative embodiments and / or uses and obvious modifications and equivalents thereof.

[0609] It should be noted that the term "light" as used herein may refer to electromagnetic radiation of any suitable wavelength for the purposes of the applications disclosed herein. Accordingly, the term "light" should not be construed as being limited to visible light and may additionally or alternatively include non- visible radiation such as, for example, laser light in the infrared range and UV light. The term "wavelength range", "spectral range", and / or similar expression, may also refer to a particular wavelength, which may be a central wavelength of a band.

[0578]

[0610] The disclosure is not intended to be limited by the specific disclosures of embodiments herein.

[0579]

[0611] Any digital computer system, module and / or engine exemplified herein can be configured and / or otherwise programmed to implement a method disclosed herein, and to the extent that the system, module, and / or engine is configured to implement such a method, it is within the scope and spirit of the disclosure.

[0580]

[0612] Once the system, module and / or engine are programmed to perform particular functions pursuant to computer readable and executable instructions from program software that implements a method disclosed herein, it in effect becomes a special purpose computer particular to embodiments of the method disclosed herein.

[0581]

[0613] The methods and / or processes disclosed herein may be implemented as a computer program product that may be tangibly embodied in an information carrier including, for example, in a non-transitory tangible computer-readable and / or non-transitory tangible machine-readable storage device.

[0582]

[0614] The computer program product may be directly loadable into an internal memory of a digital computer, comprising software code portions for performing the methods and / or processes as disclosed herein. The term "non-transitory" is used to exclude transitory, propagating signals, but to otherwise include any volatile and / or non-volatile computer memory technology suitable to the application.

[0583]

[0615] Additionally, or alternatively, the methods and / or processes disclosed herein may be implemented as a computer program that may be intangibly embodied by a readable signal medium.

[0584]

[0616] A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband and / or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof.

[0585]

[0617] A readable computer signal medium may be any readable computer medium that is not a non- transitory computer and / or machine-readable storage device and that can communicate, propagate, and / or transport a program for use by and / or in connection with apparatuses, systems, platforms, methods, operations, and / or processes discussed herein.

[0618] The terms "non-transitory computer-readable storage device" and "non-transitory machine- readable storage device" encompasses distribution media, intermediate storage media, execution memory of a computer, and any other medium and / or device capable of storing for later reading by a computer program implementing embodiments of a method disclosed herein.

[0586]

[0619] A computer program product can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by one or more communication networks.

[0587]

[0620] These computer readable and executable instructions may be provided to a processor of a general- purpose computer, special purpose computer, and / or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and / or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0588]

[0621] These computer readable and executable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0589]

[0622] The computer readable and executable instructions may also be loaded onto a computer, other programmable data processing apparatus, and / or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus and / or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, and / or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0590]

[0623] In the disclosure, unless otherwise stated, adjectives such as "substantially" and "about" that modify a condition and / or relationship characteristic of a feature or features of an embodiment of the invention, are to be understood to mean that the condition and / or characteristic is defined to within tolerances that are acceptable for operation of the embodiment for an application for which it is intended.

[0591]

[0624] Unless otherwise specified, the terms 'about' and / or 'close' with respect to a magnitude and / or a numerical value may imply to be within an inclusive range of -10% to +10% of the respective magnitude and / or value.

[0592]

[0625] It should be noted that where an embodiment refers to a condition of "above a threshold", this should not be construed as excluding an embodiment referring to a condition of "equal or above a threshold".

[0626] Analogously, where an embodiment refers to a condition "below a threshold", this should not be construed as excluding an embodiment referring to a condition "equal or below a threshold". It is clear that should a condition be interpreted as being fulfilled if the value of a given parameter is above a threshold, then the same condition is considered as not being fulfilled if the value of the given parameter is equal or below the given threshold.

[0593]

[0627] Conversely, should a condition be interpreted as being fulfilled if the value of a given parameter is equal or above a threshold, then the same condition is considered as not being fulfilled if the value of the given parameter is below (and only below) the given threshold.

[0594]

[0628] It should be understood that where the claims or specification refer to "a" or "an" element and / or feature, such reference is not to be construed as there being only one of that element. Hence, reference to "an element" or "at least one element" for instance may also encompass "one or more elements".

[0595]

[0629] As used herein the term "configuring" and / or 'adapting' for an objective, and / or a variation thereof, implies using materials and / or components in a manner designed for and / or implemented and / or operable or operative to achieve the objective.

[0596]

[0630] Unless otherwise stated or applicable, the use of the expression "and / or" between the last two members of a list of options for selection indicates that a selection of one or more of the listed options is appropriate and may be made, and may be used interchangeably with the expressions "at least one of the following", "any one of the following" or "one or more of the following", followed by a listing of the various options.

[0597]

[0631] As used herein, the phrase "A, B, C, or any combination of the aforesaid" should be interpreted as meaning all of the following: (i) A or B or C or any combination of A, B, and C, (ii) at least one of A, B, and C; and (iii) A, and / or B and / or C. This concept is illustrated for three elements (i.e., A, B, C), but extends to fewer and greater numbers of elements (e.g., A, B, C, D, etc.).

[0598]

[0632] It is noted that the terms "operable to" or "operative to" can encompass the meaning of the term "adapted or configured to". In other words, a machine "operable to" or "operative to" perform a task can in some embodiments, embrace a mere capability (e.g., "adapted") to perform the function and, in some other embodiments, a machine that is actually made (e.g., "configured") to perform the function.

[0599]

[0633] Throughout this application, various embodiments of this invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention.

[0600]

[0634] Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as, for example, from 1 to 6 should be considered to have specifically disclosed subranges such as, for example, from 1 to 4, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 4 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0601]

[0635] Whenever a numerical range is indicated herein, it is meant to include any cited numeral (fractional or integral) within the indicated range. The phrases "ranging / ranges between" a first indicate number and a second indicate number and "ranging / ranges from" a first indicate number "to" a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numerals therebetween.

[0602]

[0636] It should be appreciated that combinations of features disclosed in different embodiments are also included within the scope of the present inventions.

[0603]

[0637] While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

[0604]

[0638] The adjective "gradually" may refer to the temporal change, which may take place over a period of time in small, incremental steps.

[0605]

[0639] The term "continuously" may refer to spatial change, which may progress steadily without stops and / or gaps.

[0606]

[0640] The expression "real-time" as used herein generally refers to the updating of information at essentially the same rate as the data is received. For example, "real-time" can be intended to mean that the data is acquired, processed, and transmitted from a sensor at a high enough data rate and at a low enough time delay that information is presented to the user, for example, before the milk is received by the container. Receiving the signals from the sensor, the processing of the related data, and presenting of corresponding information may be performed within one second or less.

[0607]

[0641] The expression "clinical condition" may refer to a physiological and / or a pathological condition. The expressions "sub-clinical" and "pre-clinical" may herein be used interchangeably. Although embodiments may herein relate to mastitis, this should by no means be construed in a limiting. Accordingly, the same and / or analogous principles, processes, methods, setups, configurations, system, apparatuses and / or the like discussed herein with respect to (pre-clinical) mastitis, may also be applied with respect to any other clinical condition. It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments or examples, may also be provided in any combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, example and / or option, may also be provided separately or in any suitable sub-combination or as suitable in any other embodiment described, example or option of the invention. Furthermore, any feature and / or any combination of features disclosed herein may be disclaimed. Certain features described in the context of various embodiments, examples and / or options are not to be considered essential features of those embodiments, unless the embodiment, example and / or option is inoperative without those elements.

Claims

CLAIMSWhat is claimed is:

1. An apparatus configured for reducing mammal milk flow rate and reducing sensing noise, the apparatus comprising: a receiving chamber for intaking mammal milk into the apparatus via the inlet, the receiving chamber comprising a fluid inlet, a fluid outlet, and one or more sensing sections that are at least partially transparent to electromagnetic radiation; a fluid restriction section for reducing the velocity and / or the flow rate of the mammal milk flow; wherein the one or more sensing sections are configured for allowing optical sensing of the mammal milk of reduced flow velocity and / or reduced flow rate.

2. An apparatus configured for reducing mammal milk flow rate and reducing sensing noise, the apparatus comprising: a receiving chamber for intaking mammal milk into the apparatus via the inlet, the receiving chamber comprising a fluid inlet, a fluid outlet, and one or more sensing sections that are at least partially transparent to electromagnetic radiation; and an air bubble removal section configured for removing air bubbles from the intaken mammal to provide bubble-reduced mammal milk; wherein the one or more sensing sections are configured for enabling remote sensing of the bubble- reduced mammal milk.

3. The apparatus of claims 1 and / or 2, comprising a capping module configured for: filtering out containment and / or configured for sampling the mammal milk at a sampling rate that corresponds with the reduced mammal milk velocity and / or flow rate.

4. The apparatus of any one or more of the claims 1 to 3, comprising a housing module configured for providing optical isolation for enabling the sensing, and / or configured for sampling the mammal milk at a sampling rate that corresponds with the reduced mammal milk velocity and / or flow rate.

5. A system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising: at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein the onset of the mastitis is predictable for mammal milk somatic cell count (SCC) that is about equal or less than 200 cells / pL or less; or about equal or less than 180 cells / pL; about equal or less than 150 cells / pL, or about equal or less than 120 cells / pL; or about equal or less than 100 cells / pL.

6. The system of claim 5, configured for determining the onset of pre-clinical mastitis.

7. The system of claim 5 and / or claim 6, wherein the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

8. The system of any one of the claims 5 to 7, wherein the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete reflectance spectral; and wherein, the at least one processor is configured to correlate MM PH level based on the optical sensor data.

9. The system of any one or more of the claims 5 to 8, wherein the upcoming time interval is consecutive of the recent monitoring time interval; andwherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

10. The system of any one or more of the claims 5 to 9, wherein the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics to collectively factor-in the plurality of distinct mammal characteristics.

11. The system of any one or more of the claims 5 to 10, wherein the detecting and / or determining is performed in real-time or substantially in real-time with respect to the sensing of the at least one characteristic descriptive of mammal related information.

12. The system of any one or more of the claims 5 to 11, further configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre- clinical mastitis or clinical mastitis.

13. The system of any one or more of the claims 5 to 12, wherein the processing of the sensor data is performed by one of the following: a trained machine-learning (ML) model; a classifier; a rule-based model; a deterministic model; or any combination of the aforementioned.

14. The system of any one or more of the claims 5 to 13, wherein the at least one characteristic comprises at least one of the following: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk pH level; mammal milk electrical characteristic; or any combination of the aforesaid.

15. The system of any one or more of the claims 5 to 14, wherein the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

16. The system of any one or more of the claims 5 to 15, wherein the at least one characteristic of the at least one mammal milk pertains to an individual mammal, a group of mammals, a herd, dairy farm, and / or a plurality of mammals located of a geographic region.

17. The system of any one or more of the claims 5 to 16, wherein the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

18. The system of any one or more of the claims 5 to 17, configured to detect changes in mammal characteristic due to the presence of milk bacterium cultures comprising at least one of the following: Streptococcus agalactiae, Staphylococcus aureus, Staphylococcus spp, Mycoplasma spp, environmental Streptococci, Coliforms, or any combination of the aforesaid.

19. The system of any one of the claims 5 to 18, wherein the system is configured to detect a preclinical mastitis and / or a clinical mastitis and / or determine a probability of a clinical condition impending mastitis onset at an accuracy of at least 90%, at least 94%, or at least 98%., wherein the corresponding control system is configured to sense: a smaller plurality of distinct mammal characteristics, and / or a different plurality of distinct mammal characteristics.

20. A method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset, comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein the onset of the mastitis is predictable for mammal milk somatic cell count (SCC) that is about equal or less than 200 cells / pL or less; or about equal or less than 180 cells / pL; about equal or less than 150 cells / pL, or about equal or less than 120 cells / pL; or about equal or less than 100 cells / pL.

21. A system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising: at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following:receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a trend of a mammal milk somatic cell count (SCC) within the range of 50 to 200 cells / pL; or within 80 to 120 cells / pL.

22. The system of claim 21, configured for determining the onset of pre-clinical mastitis.

23. The system of claim 21 and / or 22, wherein the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

24. The system of any one or more of the claims 21 to 23, wherein the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of transmitted and / or reflected spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

25. The system of any one or more of the claims 21 to 24, wherein the upcoming time interval is consecutive of the recent monitoring time interval; and wherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

26. The system of any one or more of the claims 21 to 25, wherein the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such collectively factor-in the plurality of distinct mammal characteristics.

27. The system of any one or more of the claims 21 to 26, further configured to distinguish between:a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre- clinical mastitis or clinical mastitis.

28. The system of any one or more of the claims 21 to 27, wherein the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

29. A method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset, comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a trend of a mammal milk somatic cell count (SCC) within the range of 50 to 200 cells / pL; or within 80 to 120 cells / pL.

30. A system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising: at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 10% or more of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

31. The system of claim 30, configured for determining the onset of pre-clinical mastitis.

32. The system of claim 30 and / or claim 31, wherein the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

33. The system of any one or more of the claims 30 to 32, wherein the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete transmitted spectral and / or discrete reflectance spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

34. The system of any one or more of the claims 30 to 34, wherein the upcoming time interval is consecutive of the recent monitoring time interval; and wherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

35. The system of any one or more of the claims 30 to 34, wherein the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such to collectively factor-in the plurality of distinct mammal characteristics.

36. The system of any one or more of the claims 30 to 35, further configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre- clinical mastitis or clinical mastitis.

37. The system of any one or more of the claims 30 to 36, wherein the at least one characteristic comprises at least one of the following: mammal milk fat level; mammal milk protein level; mammal milk lactose level; mammal milk pH level; mammal milk electrical characteristic; ; or any combination of the aforesaid.

38. The system of any one or more of the claims 30 to 37, wherein the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

39. The system of any one or more of the claims 30 to 38, wherein the sensor data is descriptive of milk flowing into a milk tank and / or of milk stored in a milk tank.

40. A method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset, comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 10% or more of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

41. A system configured to monitor at least one mammal for predicting onset of a clinical condition, the system comprising: at least one sensor configured for sensing at least one characteristic descriptive of mammal related information; at least one memory element configured to store data and executable instructions; and at least one processor that is operative to execute instructions stored in the at least one memory element to perform the following: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 100% or less of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

42. The system of claim 41, configured for determining the onset of pre-clinical mastitis.

43. The system of claim 41 and / or claim 42, wherein the at least one processor is configured for processing the received sensor data for predicting a severity of mastitis within an upcoming time interval.

44. The system of any one or more of the claims 41 to 43, wherein the at least one sensor is an optical sensor configured for outputting optical sensor data descriptive of discrete transmitted and / or discrete reflectance spectral ranges; and wherein, the at least one processor is configured to associate at least one MM characteristic level based on the optical sensor data.

45. The system of any one or more of the claims 41 to 44, wherein the upcoming time interval is consecutive of the recent monitoring time interval; and wherein, the upcoming time interval comprises: at least one day, at least two days, at least three days, at least one week, or at least two weeks.

46. The system of any one or more of the claims 41 to 45, wherein the processing of the sensor data comprises collectively processing the sensor data descriptive of a plurality of distinct mammal characteristics such to collectively factor-in the plurality of distinct mammal characteristics.

47. The system of any one or more of the claims 41 to 46, further configured to distinguish between: a first anomaly of a characteristic descriptive of mammal related information related to pre-clinical mastitis or clinical mastitis; and a second anomaly of a characteristic descriptive of mammal related information that is not related to pre- clinical mastitis or clinical mastitis.

48. The system of any one or more of the claims 41 to 47, wherein the at least one characteristic comprises at least one of the following: mammal milk fat level; mammal milk protein level; mammal milk lactose level;mammal milk pH level; mammal milk electrical characteristic, or any combination of the aforesaid.

49. The system of any one or more of the claims 41 to 48, wherein the at least one mammal characteristic further comprises at least one of the following: mammal breed; mammal identity; mammal milk temperature; mammal milk somatic cell count (SCC); mammal milk acidity level; mammal milk urea level; mammal milk hormone level; mammal milk antibiotics level; mammal milk blood level; or any combination of the aforesaid.

50. A method for detecting, in at least one mammal, mastitis, preclinical mastitis and / or a probability of a clinical condition impending mastitis onset, comprises: receiving, from the at least one sensor, sensor data associated with at least one characteristic descriptive of mammal related information; processing the received sensor data for predicting onset of mastitis within an upcoming time interval; wherein an onset of the mastitis is predictable based on a change of 100% or less of a milk somatic cell count (SCC) within a range of 50 to 200 cells / pL for at least two consecutive measurements.

Images