202 results about "Model system" patented technology

Embodiments described herein provide for a healthcare ecosystem of computing devices participating as nodes of a distributed ledger (e.g., blockchain). The distributed ledger includes NFTs representing corresponding patients, where the initial NET behaves logically as a token scaffold that represents a “digital twin” of the particular patient. The initial patient token represents personal profile data of patient personal data for the patient. The nodes may generate new data and / or new sub-tokens (or other blockchain entry type) representing new data, which the nodes associate with the token scaffold. The sub-tokens contain data for representing physical or digital specimens, health data, and data derived from the health data (e.g., cell lines, organoids, other model systems). As the nodes generate and associate new sub-tokens to the patient's token scaffold over time, the token scaffold graphs and facilitates integration of patient-specific data and evolves into a robust electronic health record (EHR) and digital twin.

The invention provides a method for training an end-to-end automatic driving strategy, and the method comprises the following steps: S1, data collection and preprocessing, S2, defining a loss function and an optimizer, and constructing a model, S3, data division, S4, model training, S5, evaluation on a verification set, S6, model adjustment and optimization, and S7, test set evaluation. S8, weight pruning and evaluation: calculating and evaluating the importance of each weight by adopting a gradient norm calculation mode, evaluating the model after weight pruning by using the test set in the step S7 according to an importance evaluation result, starting from a relatively small proportion, gradually increasing and removing unimportant weights, and if the performance of the model does not reach the standard at the moment, evaluating the model after weight pruning by using the test set in the step S7. According to the method, through weight pruning, the applicability of a model system is wider, and the training efficiency of the system is higher.

The invention provides a cement production management and control platform PHM model system, and the system comprises the steps: obtaining the monitoring data and production management data of a cement production process, and enabling the monitoring data and production management data to form an original data set; performing data cleaning and preprocessing on the original data set, and removing noise and abnormal values to obtain a standardized data set; inputting the feature component into a preset deep learning model, and outputting a prediction result of the equipment state; the prediction result is compared with a set threshold range, and if the prediction result exceeds the threshold range, early warning information is generated; classifying the early warning information in combination with historical fault data and current production environment parameters, and distinguishing normal production fluctuation and potential faults; if the classification result is a potential fault, a fault mode is analyzed, a fault type is determined, a pre-training model is finely adjusted by using a fault sample, and the generalization ability of the model is improved; new data are continuously collected in the production process, the model is periodically updated, and the accuracy of model fault early warning is improved.

The invention belongs to the technical field of wind power generation, and discloses a wind power plant digital twin modeling system and a use method, the system comprises an equipment module, the equipment module comprises a biological bionic adaptive fan blade system, a quantum sensing network, a laser radar system, a high-resolution multi-modal imaging system and an intelligent autonomous flying robot group system; the network module comprises a 5G private network, a quantum communication network and an edge computing network; the data module comprises a distributed database system, a big data processing platform and an AI training platform; the AI module comprises a wind regime prediction model, a power prediction model, an equipment health state monitoring model and a self-adaptive control algorithm model; the application module comprises a digital twinborn visualization platform, a holographic mixed reality operation and maintenance system and an intelligent scheduling system. Modeling and intelligent management of the wind power plant can be realized, the power generation efficiency can be improved, the operation and maintenance cost can be reduced, and the service life of equipment can be prolonged.

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 hydrodynamic model system based on an MIKE 21FM model and an automatic parameter judging, setting, selecting and testing method, and belongs to the technical field of hydrodynamic simulation. In order to solve the problems that in the prior art, MIKE 21FM model parameters are complex to set, difficult to select and tedious in verification process, an automatic parameter judging and setting system is constructed; the system can automatically judge and set model parameters according to model characteristics and hydrological conditions of a research area, and meanwhile, automatically select proper parameters and verify and check the parameters, so that the rationality and reliability of the parameters are ensured. By means of the method, the efficiency and accuracy of MIKE 21FM model parameter setting can be remarkably improved, and powerful support is provided for hydrodynamic simulation; in addition, the method is also combined with a machine learning technology to further optimize a parameter selection process and improve a simulation effect; the method is widely applied to hydrodynamic simulation of rivers, lakes, offshore water areas and the like, and has remarkable practical application value.

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.

The invention belongs to the technical field of benign and malignant diagnosis model systems for solid pulmonary nodules, and particularly relates to a benign and malignant diagnosis deep learning model system for solid pulmonary nodules. Comprising an overall architecture system of the model, a data set introduction system, a data set preprocessing system, a lung CT image segmentation system, a lung nodule detection system, a lung nodule category system, an experiment parameter setting system, an evaluation index system and an experiment setting and result system. A lower half branch of the network is mainly designed, the lower half branch network extracts multi-scale feature information of a lung CT image through an Inception module, and convolutional attention modules such as ECA and CBAM are introduced to enhance the extraction effect of the lower half branch network on position and shape features of the lung CT image.

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 provides an otological disease auxiliary diagnosis large model construction method and a large model system, and relates to the technical field of multi-modal learning modeling, and the method comprises the following steps: building four diagnosis sub-models, comprising a hearing loss evaluation model, an auditory meatus and tympanic membrane / middle ear state or lesion evaluation model, an auditory meatus and middle ear structure evaluation model and a medical history and medical record model. The four diagnosis sub-models are trained; the outputs of the four diagnosis sub-models are fused, and a large ear disease clinical diagnosis model is constructed; evaluating and optimizing the performance of the otological disease clinical diagnosis large model; according to the method, multiple sub diagnosis models are fused, multi-source heterogeneous data are used for training, the generalization ability of the model can be improved, the model can adapt to different application scenes, the decision process of the model can be better understood by analyzing the output of each sub diagnosis model, and the credibility of the model is improved.

The invention provides a method and a device for configuring a motion intention decoding model based on electroencephalogram signal data, which are used for providing a set of novel training mechanism of the motion intention decoding model, and performing conjoint analysis on the electroencephalogram signal data and motion posture data obtained by analyzing videos in the training process. A model system can quickly capture association between neural signals and motion tracks and comprehensively capture motion intentions, the recognition precision of the model for various complex motion modes is remarkably improved, meanwhile, computing resources needed by model processing are reduced, the whole decoding process is more efficient, individual adaptability and generalization are considered, and the method is suitable for popularization and application. And the real-time application requirement of intrusive brain-computer interface research can be well met.

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 present invention relates to a method for preparing a mammalian vascular network or mature mammalian bone marrow organoid. Also provided is the use of the prepared vascular network or mammalian bone marrow organoid in the treatment of bone marrow-related diseases, in vitro generation of BMO or mammalian blood cells, as a model system for the pathogenesis of bone marrow-related diseases, and as a system for identifying and / or testing pharmaceutically effective compounds for the treatment or prevention of bone marrow-related diseases.

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.

Methods and systems for foveal avascular zone (FAZ) segmentation of a retina. A three dimensional optical coherence tomography angiography (OCTA) volume of a retina of a subject is received. The OCTA volume comprising a plurality of layers. A slab input for a model system is formed using the OCTA volume. The model system comprising a deep learning model. A set of mask images is generated, via the model system, based on the slab input. The set of mask images includes an area mask image that accurately and reliably identifies an area of a foveal avascular zone captured by the OCT volume.

Systems and methods for determining an impact value for an event are disclosed. A method comprises ingesting one or more ingesting one or more agronomic event, decomposing the one or more agronomic event into a series of activities, translating the series of activities into a corresponding set of reference activities, reading a precomputed reference matrix, wherein the precomputed reference matrix comprises a plurality of precalculated impact values corresponding to the reference activity, computing an impact value for each activity of the series of activities, wherein said computing comprises determining a weight for each of the plurality of values of the reference matrix, aggregating an impact value for each agronomic event to determine a total impact value, based on the determined weight and the precomputed reference matrix, and outputting the aggregated impact value.

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.

Systems and methods are provided for risk management in an expert system. A distribution of feature values within a training dataset for the expert system and each of a plurality of baseline datasets are determined, and Kullback-Leibler divergences between the baseline dataset and the training dataset to provide set of Kullback-Leibler divergence values. Measures of central tendency and statistical dispersion of the set of Kullback-Leibler divergence values are determined, and a threshold Kullback-Leibler divergence value is determined from these values and a desired confidence interval for new datasets. A Kullback-Leibler divergence value between the feature values of novel dataset and the training dataset is determined and it is determined that the second dataset represents an unacceptable divergence if this Kullback-Leibler divergence value exceeds the threshold value.

The present disclosure provides, inter alia, methods for treating hemophilia A as well as computer-based-systems, including software-based pharmacokinetic model systems, and their use to determine dosing information for subjects who have hemophilia A.

The invention discloses a knee arthritis image measurement model system and method based on deep learning, particularly relates to the technical field of image processing, and is used for solving the problem of low image measurement accuracy. According to the method, the image preprocessing technology and the deep learning segmentation method are integrated, high-precision automatic segmentation and analysis are performed on the knee joint image, the contrast ratio and the resolution ratio of the image are enhanced, meanwhile, the image quality is further improved through biased field correction and non-local mean value noise reduction, and the image segmentation is performed by adopting the U-Net model, so that the image quality is improved. A complex structure in the joint is effectively recognized, segmentation precision is improved, a segmentation strategy is dynamically adjusted according to measurement influence information generated in the segmentation process, the processing flow is optimized in real time through different regulation and control signals, diagnosis efficiency and accuracy are improved, and therefore the automation level and reliability of medical image processing are improved, and the medical image processing efficiency is improved. Efficient and accurate support is provided for clinic, and the accuracy of osteoarthritis image measurement is improved.

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.

The invention belongs to the technical field of medical large models, and relates to a lightweight medical large model system driven by a knowledge graph. Comprising a questioning large model for collecting patient information through multiple rounds of dialogues, a summarizing model for comprehensively analyzing symptoms and medical history of a patient from the patient information and providing a preliminary diagnosis result and treatment suggestions, and a symptom entity and a disease entity from the patient information and the diagnosis result. Constructing a first candidate disease entity list by using the extracted disease entities, and constructing a second candidate disease entity list by acquiring related disease entities from a knowledge graph according to the extracted symptom entities, according to all the candidate disease entities, obtaining an extraction verification summary model of supplementary knowledge information of all the candidate disease entities from the knowledge graph; according to the method, the diagnosis process is perfected, the illusion problem is relieved, the interpretability is enhanced, and quick response and low-cost iteration are realized.

Systems and methods are provided for risk management in an expert system. A distribution of feature values within a training dataset for the expert system and each of a plurality of baseline datasets are determined, and Kullback–Leibler divergences between the baseline dataset and the training dataset to provide set of Kullback–Leibler divergence values. Measures of central tendency and statistical dispersion of the set of Kullback–Leibler divergence values are determined, and a threshold Kullback–Leibler divergence value is determined from these values and a desired confidence interval for new datasets. A Kullback-Leibler divergence value between the feature values of novel dataset and the training dataset is determined and it is determined that the second dataset represents an unacceptable divergence if this Kullback–Leibler divergence value exceeds the threshold value.

Systems and methods include techniques associated with one or more machine learning systems to predict peptide binding interactions for a relevant target. The one or more machine learning systems may be used to generate a ranked set of results that can be tested and then used to retrain the one or more machine learning systems as part of a validation process. The trained model may then be deployed to predict peptides for a given target condition.

Systems and techniques are described herein for executing a machine learning model. For instance, a process can include: receiving input data; processing the input data using a first machine learning (ML) block to generate intermediate data, the first ML block including a first set of parameters; processing the intermediate data using a second ML block to generate processed data, the second ML block including a second set of parameters matching the first set of parameters; and outputting the processed data.

The invention relates to the technical field of strategy evaluation simulation systems, in particular to an urban sustainable development evaluation simulation system and method, and the system comprises a strategy module, an industrial module, a social economy module, an energy module, a water resource module, an agriculture module, an ecological environment module, a land module and a region welfare climate scene module. The module is used for predicting changes of different social ecosystem elements in the future and providing quantitative support for sustainable development. According to the invention, a meta-model system is established, integration of multiple modules and multiple methods is realized, and a complete and advanced evaluation system and integration framework are formed. According to the invention, the elements of each module and the mutual relation among the modules can comprehensively consider multiple aspects of urban development, and comprehensively consider the welfare levels of three dimensions of economy, society and environment, thereby reflecting the comprehensiveness of sustainable development, and improving the development efficiency through the positive cycle of welfare-investment-growth. And interaction and mutual promotion among elements of sustainable development are emphasized, and the accuracy and reliability of evaluation are improved.