89 results about "Model system" patented technology

The invention discloses a multi-drive process multi-factor agricultural non-point source pollution prediction method based on coupling meteorological numerical forecasting. The method comprises the following steps: firstly, introducing numerical weather forecast data, and constructing a high-precision weather driving field with kilometer-level space and hour-level time resolution by combining WRF dynamic downscaling, DEM terrain correction and conservation resampling; secondly, establishing a multi-drive process coupling model system which comprises a meteorological drive layer, a hydrological response layer, a pollutant migration layer and a crop feedback layer and is used for simulating runoff production, sediment erosion, nitrogen and phosphorus migration and transformation and crop transpiration and root nutrient absorption processes; thirdly, performing precision verification on a simulation result by using observation data, and identifying key meteorological and hydrological factors through an error transfer matrix and a sensitivity analysis method; and finally, realizing parameter adaptive correction by adopting a long short-term memory network, finishing parameter optimization in combination with a multi-target genetic algorithm, packaging the model chain through a containerization technology, and realizing cross-platform deployment and visual output of a pollution load result. The method can be used for agricultural non-point source pollution prediction and management.

The invention discloses a SysMLv2.0 model library multiplexing method based on definition driving. The method comprises the following steps: S1, constructing a model definition library containing structures, behaviors, interfaces, constraints and semantic attributes; s2, analyzing a modeling demand, identifying a to-be-multiplexed module, and determining a definition unit identifier; s3, calling the target definition unit and inserting the target definition unit into the current model in a reference mode; s4, performing context adaptation to generate a binding relationship; s5, setting a version identification mechanism, and establishing a version mapping index between the use unit and the definition unit; s6, registering a reference relationship and an adaptation rule, and generating a modeling metadata document; s7, automatically updating the content of the use unit according to the metadata document in the modeling process; and S8, executing consistency verification after use unit integration is completed, and ensuring correct interface connection, conflict-free constraint logic and complete version binding. According to the method, a definition-driven model system is constructed, and cross-context semantic multiplexing and version consistency modeling management are realized.

A system for online-coupled atmospheric chemical transport modeling and data assimilation is built using online coupling and secondary parallelization. In the prototype code of a nested air quality forecasting model system, a parallel data assimilation framework routine is introduced. The system includes observation modules, model modules, and assimilation modules. The observation module is responsible for flexible access and preprocessing of various component-type observation data. The model module handles the model integration of initial fields, involving calculations of physical and chemical processes. The assimilation module performs analysis assimilation of model state variables. This system meets the requirements for coordinated assimilation of multiple chemical component variables, simultaneous introduction and flexible combination of various types of observation data, and effective handling of non-linear and non-Gaussian distribution issues in chemical assimilation.

The invention relates to the technical field of disease course trend modeling, in particular to a subarachnoid hemorrhage disease course trend modeling system fusing multi-source data. Four kinds of signals of intracranial pressure, blood flow velocity, cerebrospinal fluid pressure and electroencephalogram of a monitored object are synchronously collected, an instantaneous phase is extracted through Hilbert transform, a time window is adaptively adjusted according to the brain blood vessel conduction delay characteristic of an individual, and phase locking indexes among three pairs of signals are calculated. A multivariate coupled oscillator model is established, phase track topology invariant features are extracted, and comprehensive trend indexes are generated through tensor fusion. An individualized four-dimensional phase entropy baseline mode is established, and a double-layer early warning mechanism is adopted: when second derivative continuous symbol overturning occurs in all three phase locking indexes, early warning is directly performed, and when any two phase locking indexes are overturned, a trend index needs to be synthesized for confirmation. And predicting a state level, a trend level and an expected evolution trajectory based on a support vector regression model. According to the invention, precise disease course prediction and early warning are realized, and a basis is provided for clinical decision making.

The application provides a configuration method and device of a motor intention decoding model based on electroencephalogram signal data, and provides a novel training mechanism of the motor intention decoding model. In the training process, the electroencephalogram signal data and the motor posture data obtained by analyzing the video are jointly analyzed, so that the model system can quickly capture the correlation between the neural signals and the movement trajectory, comprehensively capture the motor intention, significantly improve the recognition accuracy of the model for various complex movement modes, reduce the required computing resources of the model processing, make the entire decoding process more efficient, and balance the individual adaptability and the generalization, so that the real-time application requirements of the invasive brain-computer interface research can be well met.

Modular mucosal tissue bioreactors combined with bioartificial mucus provide a high-fidelity, medium-throughput platform for evaluating CF treatments and modeling host-pathogen biology, a stepping stone towards better options for HEMT-nonresponsive patients. Whole lung ex vivo Cystic Fibrosis model system allows for investigation of candidate CF therapies.

The invention discloses a chronic obstructive pulmonary disease high risk dynamic assessment model system based on an artificial intelligence algorithm, relates to the technical field of chronic obstructive pulmonary disease high risk assessment, and aims to solve the technical problem that the timeliness and accuracy of an assessment result of an existing assessment model are limited. The medical data acquisition module is used for acquiring medical data of a subject through a wearable device, an electronic medical record system or a manually input multi-source channel, generating standardized preprocessed medical data after performing format cleaning, missing value filling and abnormal value filtering on the data, and transmitting the standardized preprocessed medical data to the memory of the cloud database; and the artificial intelligence dynamic assessment model construction module is used for constructing an artificial intelligence assessment model fusing time sequence characteristics and a nonlinear relationship based on the preprocessed medical data, and generating an intermediate result and a final parameter of risk assessment through multi-level calculation. The method has the advantage that the high risk of chronic obstructive pulmonary disease can be dynamically evaluated in real time.

The embodiment of the invention discloses a causal inference method for traffic accident data processing and prediction model optimization, and the method comprises the steps: constructing a multi-source heterogeneous accident database, and constructing a standardized feature matrix; based on the standardized feature matrix, extracting a feature constraint rule through a decision tree, and generating a minority class anti-fact sample conforming to domain knowledge in combination with a heuristic algorithm to form an equalized data set; inputting the equalized data set into a double-path model system for training, expanding a feature space by a data path to improve the characterization capability of a minority class, and embedding an interpretability constraint module into an interpretation path to obtain a trained model; based on the trained model, constructing a visual interpretation system comprising a feature importance map and a causal association network; and based on a visual interpretation system and the standardized feature matrix, constructing a multi-level causal network identification core influence factor, and quantifying the causal effect of intervention measures through anti-fact simulation to form a priority intervention list.

The invention relates to the technical field of three-dimensional modeling, and discloses a modeling system fusing a laser point cloud and a two-dimensional vector, and the system comprises a data collection module, a data fusion module, a model generation module, a visualization module, an optimization adjustment module, and a user feedback module. Laser point cloud and two-dimensional vector data are acquired through a data acquisition module and standardized preprocessing is carried out; performing registration, conversion and weighted fusion on the point cloud and vector data based on a data fusion module to generate high-precision fusion data; performing three-dimensional reconstruction, detail enhancement and quality verification through a model generation module, and outputting a final model; utilizing a visualization module to render a scene and support interactive operation; evaluating model efficiency and dynamically optimizing parameters through an optimization adjustment module; and a user feedback module is combined to analyze requirements and adaptively adjust system settings. According to the method, the precision and reliability of three-dimensional modeling are improved, the robustness and consistency of the modeling process are enhanced, and the overall output quality and engineering applicability of the system are improved.

The invention relates to the technical field of tree species identification, in particular to a tree species identification method and system based on multi-source remote sensing data fusion, and the method comprises the steps: obtaining multi-source remote sensing data in a target identification region, carrying out the cross-domain feature decoupling processing of the multi-source remote sensing data, and obtaining the attribute features of tree species and the environmental interference features; inputting the tree species attribute features into a preset adaptive spatial-temporal feature library to obtain correction features; collecting current real-time environment parameters, and fusing the tree species attribute features, the environment interference features, the correction features and the real-time environment parameters to obtain multi-source coordination features; a tree species identification result is generated according to the multi-source coordination characteristics, tree species identification requirements in different geographical environments can be adaptively matched, the problem of precision attenuation caused by data distribution offset during cross-regional migration of a model system is effectively solved, and the tree species identification robustness in different ecological environments is remarkably improved.

An oncological foundation model is trained with broad, multimodal data to make predictions concerning a variety of different types of cancers. For example, the foundation model may make use of medical images drawn from radiology and pathology, as well as immunohistochemistry data; the presence or absence of biomarkers for particular diagnoses; patient history data; patient demographic data; and other forms of medical data. When using medical images, whole medical images as well as feature sets derived from the medical images may be used. The foundation model may have both causal predictive abilities as well as generative abilities.

Systems and methods include techniques associated with one or more machine learning systems to normalize disparate entries within one or more datasets for common data types. The one or more machine learning systems may be used to generated relationships between attribute-value pairs associated with a particular data type and then to determine, from a corpus of free-form data, individual entries for a target data type. The identified individual entries may be used to extract information from the dataset and generate a modified, clean dataset.

The application discloses a geothermal caprock evaluation modeling method and belongs to the technical field of geothermal resource exploration. In view of the problems that existing caprock evaluation standards are uneven, subjective and lack of quantitative coupling of structural factors and calibration of measured data, the application firstly acquires caprock physical properties and structural data; secondly, a single-factor evaluation model based on physical mechanism is constructed for lithology, thickness, permeability and thermal conductivity; on this basis, a structure-mechanical-integrity coupling model is constructed, which includes basic structure scores, fracture risk indexes and plastic self-repairing capacity factors; finally, by using observation data such as historical breakthrough pressure and leakage events, key parameters in the above model are calibrated through regression and Bayesian methods. The method forms a unified and portable caprock evaluation basic model system, reduces subjectivity, and improves the stability and interpretability of the evaluation results.

Systems and methods for learning from mistakes to improve detection rates of Machine Learning (ML) models. The systems and methods including receiving data with labels; running the data through a trained ML model for predictions; identifying errors in the predictions based on the labels received with the data; adjusting weights associated with samples in the data based on the identified errors; and retraining the ML model with the adjusted weights.

The application relates to a calculation method of a high-temperature alloy impurity diffusion coefficient and an atomic mobility parameter based on a molecular dynamics simulation, which comprises the following steps: parameter setting; model establishment; setting a potential function as a multicomponent EAM alloy potential; energy minimization and setting an initial atomic speed; calculating RDF values of a model system and drawing RDF curves; calculating MSD values of all atoms and respectively outputting MSD values of various atomic groups according to various different metal atom types; defining thermodynamic physical quantity output and commanding each step to output and save; giving a random initial speed to the system, and running under each system in three stages: a temperature rising stage, a temperature keeping stage and continuous temperature keeping and relaxation, and outputting MSD values; calculating the impurity diffusion coefficient of the system based on the MDS values; and taking the measured impurity diffusion coefficient as an input value, and obtaining the atomic mobility parameter through DICTRA software. Compared with the prior art, the application has the advantages of simple method, accurate numerical value and the like.

The invention discloses a breeding performance prediction system based on an intelligent sheep breeding platform, and belongs to the technical field of animal husbandry informatization. The intelligent breeding platform is designed, standardized collection, storage and intelligent management of sheep full-life-cycle data are achieved, and a solid data foundation is laid for follow-up research; secondly, innovatively combining ensemble learning (AdaBoost, GBRT and the like), machine learning (SVR, KNN and the like) and a sorting learning algorithm, and constructing a multi-level breeding sheep breeding performance prediction model system; particularly, a subjective and objective combination weighting method based on AHP-PCA is provided, and the prediction precision of the model is remarkably improved through feature reconstruction; in addition, an Achimedes optimization algorithm (AOA) is introduced into the field of breeding prediction for the first time, and adaptive search of hyper-parameters is realized by using a physical simulation mechanism of the AOA, so that the accuracy, efficiency and robustness of the model are remarkably improved.

Systems and methods for generating a large volume of synthetic stream-of-commerce security imaging data is disclosed. Methods for creating synthetic baggage x-ray scans, synthetic passenger millimeter wave scans, synthetic passenger video surveillance data, and introducing prohibited items to real security images are also disclosed.

The invention discloses a prediction model system for multiple myeloma venous thromboembolism, and the system comprises a data obtaining module which obtains detection data including baseline data; the data category imbalance processing module is used for performing category imbalance processing according to the baseline data to obtain sample data; the data variable screening processing module is used for carrying out variable screening according to the sample data to obtain characteristic variable data; and the data visualization processing module is used for determining the weight of each variable based on proportional risk regression according to the characteristic variable data, incorporating the weight into a preliminary screening variable, segmenting continuous variables, establishing a point value conversion system, calculating a total score and corresponding to a risk probability, and constructing a data visualization chart. The invention discloses a prediction model system for multiple myeloma venous thromboembolism, a storage medium and a use method, and aims to greatly improve the cross-metal transmission rate of ultrasonic signals and improve the accuracy, stability, convenience and practicability of risk early warning.

The invention relates to the technical field of model construction, in particular to a modeling system and modeling method suitable for a rat epileptic status model.The modeling method comprises the steps that electrical stimulation is applied to a rat according to preset stimulation parameters, and the stimulation parameters are output; monitoring physiological signals of the rats in real time, performing feature extraction on the physiological signals, and outputting epilepsy feature parameters; comparing the epilepsy characteristic parameters according to a preset threshold value to confirm whether an epilepsy persistent state is reached, and generating a final modeling result based on a state confirmation result; when the model is successfully established, the medicine intervention module is automatically triggered, the anti-epileptic effect of the candidate medicine is evaluated in real time based on the change of epileptic characteristic parameters obtained in real time, and a medicine effect evaluation report is output; according to the method, the process of automatically constructing the rat epileptic status model is realized, and the establishment of the model can be dynamically adjusted and confirmed according to the change of the epileptic characteristic parameters by accurately controlling the preset stimulation parameters and monitoring the physiological signals of the rat in real time.

In some implementations, a model system may train a deep learning model to determine baseline figures and stretch figures and may train a shallow learning model to determine likelihoods associated with achieving the baseline figures and the stretch figures. The model system may receive indicators associated with a current entity and may provide the indicators to the deep learning model to generate a baseline figure and a stretch figure. The model system may receive progress data associated with the current entity. The model system may provide output based on the deep learning model and the progress data to the shallow learning model to generate a likelihood associated with the current entity achieving at least one of the baseline figure or the stretch figure. The model system may selectively provide an alert to a user based on the likelihood.

The invention discloses an efficient operation and maintenance method and device for a large model system, and belongs to the technical field of artificial intelligence, and the implementation of the method comprises the following steps: constructing an operation and maintenance agent cluster of the large model system, which comprises a model deployment agent, a model detection agent, a model operation agent, a model upgrading agent and an operation and maintenance planning agent; after an operation and maintenance task is input, the operation and maintenance planning agent receives an input instruction, performs task understanding and analysis, and divides the task into a conventional operation and maintenance mode and a customized operation and maintenance mode; setting a conventional operation and maintenance mode by using the operation and maintenance planning agent, and calling the model detection agent and the model operation agent to guarantee and maintain function indexes and operation states of models in the system; and setting a customized operation and maintenance mode by using the operation and maintenance planning agent, and calling the model deployment agent and the model upgrading agent to complete customized deployment and upgrading of the model. According to the method, efficient deployment, continuous verification, dynamic expansion and intelligent upgrading of the model are realized.

Systems and methods for property guided molecular optimization using artificial intelligence diffusion models. An equivariant continuous denoising diffusion implicit model autoencoder framework (DDIM-AE) can be trained (510) on a conformational dataset to predict raw data from data corrupted by a time-dependent noise to obtain a trained DDIM-AE that ensures controlled generation of threedimensional (3D) molecules. Linear optimization of semantic embeddings of 3D molecules can be performed (520) with a linear classifier to achieve a target property value from desired properties and obtain an optimized embedding. An optimized 3D molecule that includes molecular conformation with the desired properties while preserving interactions with biochemical molecules can be generated (530) from the optimized embedding with the trained DDIM-AE.

A workflow is presented herein which includes methods and computational systems and devices for providing 3D computational models of potential off-target peptides each positioned in a groove of an MHC molecule ("MHC-off-target models"), quantifying structural similarity between each potential off-target peptide to a target peptide based on a comparison of the MHC-off-target models to a 3D computational model of a target MHC-peptide complex ("MHC-target model"), and ranking the potential off-target peptides based on a structural similarity metric. Example methods and systems can be applied to solve bioinformatics and treatment development problems. The present disclosure also relates to compositions that involve isolated peptides, e.g., MAGEA3168-176 and / or WT1126-134 off-target peptides, and the use of such compositions in methods for assessing off-target effects of antigen-recognition molecules that target a MAGEA3168-176 and / or WT1126-134 peptide, as well as for selecting antigen-recognition molecules and enriching samples for antigen-recognition molecules that specifically bind the MAGEA3168-176 and / or WT1126-134.

An oncological foundation model is trained with broad, multimodal data to make predictions concerning a variety of different types of cancers. For example, the foundation model may make use of medical images drawn from radiology and pathology, as well as immunohistochemistry data; the presence or absence of biomarkers for particular diagnoses; patient history data; patient demographic data; and other forms of medical data. When using medical images, whole medical images as well as feature sets derived from the medical images may be used. The foundation model may have both causal predictive abilities as well as generative abilities.

The present application relates to a kind of model systems, methods and media based on non-ideal diode analog heart valve, belong to computational fluid dynamics and cardiovascular system modeling technical field;Including the following steps: S1: establishing cross-domain physical parameter analogy relationship, the physical position where heart valve is defined as two-dimensional simulation interface;S2: construct non-ideal diode valve mathematical model, define the constitutive equation of "pressure-flow" relationship described by valve;S3: construct valve dynamics equation;S4: based on clinical data adjustment parameter to adapt normal or pathological state;S5: valve model is integrated to CFD solver and realizes coupling calculation, exports hemodynamics and valve function index.The present application establishes the profound physical analogy between fluid system and circuit system, constructs a valve model using the mathematical expression of non-ideal diode, which is computationally efficient, numerically stable, has clear physical meaning of parameters and can simulate various pathological states.

Systems, apparatuses, and methods are described for a positive / negative / unknown (PNU) model. The PNU model may be used to make predictions based on partially observed systems. For example, the PNU model may directly train on auction data, and / or unlabeled data to classify the probability of each of the PNU labels and calculate an ideal bid amount based on the classification.

In some implementations, a model system may receive an indication of the set of models that are associated with a set of data points. Each model in the set of models may have been selected using a grid search. The model system may receive, from a user device, a query associated with a selected data point in the set of data points. The selected data point may be associated with a corresponding model in the set of models. The model system may provide information included in the query to the corresponding model in order to receive a result associated with the selected data point. The model system may transmit, to the user device, the result in response to the query.

The invention relates to the technical field of public health management and decision-making, and discloses a public health risk comprehensive evaluation and decision-making optimization method based on multi-source information, and a constructed emergent public health event analysis model comprises a medical resource competition sub-model and an infectious disease diffusion sub-model. Model calibration, a nonlinear generalized predictive adaptive control law and comprehensive overflow effect evaluation based on data envelope analysis are adopted to deeply integrate infectious diseases, a resource competition theory, an optimal control theory, operational research and an information theory method; a comprehensive model system capable of reflecting complex system interaction of'epidemic situation-resource-decision-society 'in public health events is constructed, strong robustness and dynamic optimization capability for dealing with uncertainty are achieved, the model precision and reliability are remarkably improved, errors are reduced, the defect that traditional evaluation is single is overcome, and the method is suitable for popularization and application. The overall effect of emergency decision making can be comprehensively evaluated from multiple aspects of medical treatment, society, economy and the like, and efficient and comprehensive decision making support is achieved.

The application is based on a blood vessel risk assessment model system based on a multi-modal fusion strategy and deep learning: an acquisition module acquires examination and test data, image data, gene detection data and clinical data of a plurality of historical patients, and labels various blood vessel disease conditions; a preprocessing module standardizes numerical data, one-hot encodes or entity embedding of category data, converts time series data into fixed length vectors, extracts imaging features from image data and / or learns deep image features from the image data, extracts features from text data, reduces SNPs data, normalizes gene expression profile data and selects features; a feature sample construction module constructs a training set and a validation set using the multi-modal preprocessed features of each historical patient; a model construction module constructs a multi-task deep learning model; a multi-task learning training module trains and validates the model, optimizes the hyperparameters of the model using an optimization algorithm, and adjusts the hyperparameters to the optimal to obtain a target multi-task deep learning model.

A system may be configured to generate an estimate of value at risk and may include a processor to process instructions that cause the system to generate a rolling time series of value data having a plurality of dimensions, perform a transformation of the time series, perform variance scaling and correlation scaling on transformed time series, reverse transform the results of the scaling, and estimate of a value-at-risk for the value data.