61 results about "Causal model" patented technology

The systems and methods described herein utilize a probabilistic modeling framework for reverse engineering an ensemble of causal models, from data and then forward simulating the ensemble of models to analyze and predict the behavior of the network. In certain embodiments, the systems and methods described herein include data-driven techniques for developing causal models for biological networks. Causal network models include computational representations of the causal relationships between independent variables such as a compound of interest and dependent variables such as measured DNA alterations, changes in mRNA, protein, and metabolites to phenotypic readouts of efficacy and toxicity.

A system and method are provided for extracting a set of data from a system user descriptive of the complete health snapshot of the user's to interact with a database of numerous other users so as to generate a cluster of similar user's exhibiting a similar (within some system defined distance metric) health snapshot. The system guides the user to present his or her data via a complex questionnaire based upon a novel descriptive taxonomy, based upon the principles of "cyberhealth" as opposed to the standard medical "disease oriented" singular cause and effect model. The system generates the cluster of similar users, analyzes the cluster to obtain a ranked list of possible remedies or therapies to assist the user in dealing with health problems. The system further creates a computer networked virtual community of users with common health problems/interests, facilitates online chat, discussion groups, and the trading of health information. Additionally, the system provides listings of and links to health care providers and medical testing laboratories who are able to assist users of the system.

A computing system initializes a first frontier to be a root of a multi-dimensional hierarchical data structure representing an entity. The system acquires first data corresponding to the first frontier. The system performs modeling on the first data to obtain a first model and a corresponding first statistic. The system expands a dimension of the first frontier. The system gathers second data corresponding to the expanded frontier. The system applies the data modeling on the second data to obtain a second model and a corresponding second statistic. The system compares the first statistic of the first model and the second statistic of the second model. The system sets the second model to be the first model in response to determining that the second model statistic is better than the first model statistic. The system outputs the first model.

A new application of machine vision for process industries is proposed. The invention consists of: (1) estimation of visual quality of products, (2) modeling causal relationship between estimated quality and process variables, and (3) optimization of visual quality using the causal model. This invention can handle the stochastic nature in visual appearance of products that process industries provide, which has been a main obstacle for the success of machine vision in process industries. Also, it opens new tasks in machine vision such as modeling and optimization of visual quality of products.

A system, method, and computer program product for combining causal domain models with reasoning and text processing for knowledge driven decision support are provided. A knowledge driven decision support system is capable of creating a domain model, extracting and processing quantities of text according to the domain model, and generating understanding of the content and implications of information sensitive to analysts. An interface may be used to receive input to model complex relationships of a domain, establish implications of interest or request a query, and update the causal model. A processing element can capture and process text into text profiles by incorporating the domain model and process the text profiles in accordance with the domain model by applying formal reasoning to the information to derive trends, predict events, or arrive at other query results. An output element can provide a user the resulting information related to the domain model.

A method (and system) for causal modeling includes modeling a data set using a reverse Bayesian forest.

The invention relates to the technical field of simulated modeling of a rotor dynamics system and in particular to an object-oriented nonlinear and non-causal modeling and simulation method for the rotor dynamics system. The modeling and simulation method is based on an object-oriented non-causal multi-field modeling language Modelica; the modeling language Modelica is used for writing the simulated modeling program of the rotor dynamics system; the simulated modeling of the rotor dynamics system is formed by components and faults; the components comprises a turntable component, shaft section components and a bearing component; the turntable component, the shaft section components and the bearing component comprise two connector elements respectively; the faults comprise crack fault, rubbing fault and foundation loosening fault; and by the modeling and simulation method, the rotor dynamics systems with various structures can be modeled, system characteristics and working condition of the rotor dynamics systems can be truly reflected, the faults such as crack, rubbing and foundation loosening can be introduced to perform system analysis, and a convenient analysis measure is provided for engineering technical persons and scientific researchers.

A method for dynamic human reliability analysis of a multi-unit nuclear power plant comprises that follow steps: first, modeling a human error event by using a dynamic event tree, analyzing human error of an operator of the multi-unit nuclear power plant, and determining a type of human error and a potential human error; 2, construct a causal model of human error based on that Bayesian network andthe data guide modeling technology, and calculating nominal human error probabilities of various human error by using the model; 3, establish a function of that behavior forming factor with respect to the time variable base on the numerical solution method of the inverse problem, and establishing a calculation format of the dynamic human error probability according to the obtained function relation; 4, analyze that dynamic feedback loop in the model established in the step 1 by use the system dynamics, and combining the calculation result in the step 2 and the calculation format of the dynamic human error probability established in the step 3, constructing a dynamic reliability quantitative analysis model, and calculate the quantitative calculation value of the human factor reliability.

Input of cause-and-effect model information where the coefficients at which three evaluated values, i.e., the evaluated values of business strategy, research-and-development strategy, and intellectual property strategy influence the company evaluated value, the coefficients at which the three evaluated values and the company evaluated value influence the observable indexes respectively, the error variables with which the factors other than the three evaluated values and the company evaluated value give variations to the company evaluated value and the observable indexes respectively are assumed is received. From the inputted the cause-and-effect model information and the observable indexes, the estimates of the coefficients are calculated by covariance structure analysis. From the coefficients and the observable indexes, the three evaluated values and the company evaluated value are calculated. With this, the relationship among the three strategies which are directly nonobservable abstract factors, i.e., the business strategy, the research-and-development strategy, and intellectual property strategy and the company value is verified, and company evaluation based on these three strategies can be performed.

The invention provides a dyskinesia non-intrusive rehabilitative closed-loop brain-computer integrated system based on an FPGA. The FPGA is used as a control core of the system, nuclei basales and thalamic-cortical prosthesis hardware model is set up, data obtained through calculation of a self-adaptation control algorithm based on the FPGA is used as input to control model parameter setting and force feedback and adjustment until an expected control result is achieved, the self-adaptation control algorithm based on the dynamic causal model is realized, force feedback signals are output, and therefore rehabilitation of patients with the dyskinesia nervous system diseases is achieved. Rehabilitation of the patients with dyskinesia nervous system diseases is achieved, and the complex nuclei basales and thalamic-cortical neuron network and the self-adaptation control algorithm of the dynamic causal model are modeled. The platform provides the effective theoretical basis and technical support for rehabilitation of the dyskinesia nervous system diseases and has important practical value in research on control and treatment on nerve diseases such as Parkinson's disease, epilepsia and alzheimer's disease.

The invention discloses a model-based dynamic analysis method for an extruded two-component liquid power system. An object-oriented declarative liquid power system modeling method is formed by combining a liquid power system modeling simulation theory with a Modelica technical system and used for guiding a modeling process of a non-causal model library of the liquid power system. For a complex system such as the liquid power system, the system does not need to be decoupled, and component input/output and equation solving sequences do not need to be defined, so that the difficulty and complexity of system modeling are greatly lowered, the workload is reduced, an error caused by manually specifying the solving sequence is avoided, and the reusability, expandability, flexibility and knowledge accumulation capability of models are remarkably improved.

The invention relates to the fields of machine learning, natural language processing, causal reasoning and the like, in particular to a judicial decision reasoning method based on an interpretable causal model. The judicial decision reasoning method comprises the steps of analyzing and representing judicial data, defining a judicial decision inference framework, and constructing a judicial decision inference cause and effect model. Wherein defining of the judicial decision inference framework comprises the steps of extracting fact elements, identifying the fact elements and obtaining a decision result. The model construction comprises the steps of obtaining a reason variable, obtaining a result variable, constructing a correlation function, and constructing a judicial decision reasoning cause and effect graph. According to the judicial decision reasoning method, causal reasoning of judicial judgment is realized, and the problems that an existing judicial judgment reasoning method lacksa reasoning mechanism and is poor in interpretability can be effectively solved, and the accuracy of a case judgment result easy to confuse can be obviously improved.

The invention belongs to the field of big data and machine learning, particularly relates to a data-driven complex system mechanism automatic learning method, a system and equipment, and aims to solve the problems that an existing system modeling technology is difficult to predict a behavior trend from field observation data, a reconstructed mechanism model is not matched with physical observation data, the robustness is poor and the like. The method comprises the steps of obtaining historical multi-modal data and real-time multi-modal data, constructing a time sequence long-range correlation hypergraph model through airspace circulation memory coding, performing normalized combination on the hypergraph model through a neural differential equation model, and performing automatic iterative search on a continuous game network structure to obtain a system mechanism continuous dynamic model, and performing biological evolution simulation to obtain a causal model, and recalculating an association weight to obtain an active early warning system. According to the method, non-linearity, emergence, balance step, adaptability and special property description of a feedback loop of a complex system are realized, and the prediction accuracy of the model is improved.

Systems and methods for predictive network modeling are disclosed. The systems and methods disclosed compute a top-down causal model and a bottom-up predictive model and utilize those models to determine the conditional independence among multiple variables and causality among equivalent variable structures. Before or during modeling, the data is passed through Markov Chain Monte Carlo sampling.

The invention relates to a brain link mining system and method based on document analysis and functional nuclear magnetic resonance imaging analysis, and belongs to the fields of computer technologies and cognitive neuroscience technologies. The system comprises a dynamic causal model module, an activation analysis module, a document link analysis module, a seeking sub-network module, a document database and a brain network link database. The method comprises the steps of firstly, by calculating the activated probabilities of all brain coordinates in all documents, figuring out the activated probabilities of corresponding anatomical areas to obtain activated brain areas, mining modes which frequently appear in the brain areas through the association rules algorithm, calculating confidence coefficients to obtain a trusted brain function network, establishing the corresponding documents to generate a brain network database, then collecting corresponding functional nuclear magnetic resonance imaging data by utilizing a functional nuclear magnetic resonance imaging system, and verifying the actual link direction and weight numbers of a network edge by utilizing the dynamic causal model module. In this way, the problem that calculating is overlong in time and low in accuracy in the brain link analysis process is solved.

The invention relates to a method for generating a big data causal model in a corresponding power grid operation environment, and belongs to the technical field of power grid automatic scheduling. Themethod comprises the following steps: 1) obtaining a correlation factor set of events occurring in the operation process of current power grid equipment; 2) screening out high-probability associationfactors of which the correlation with the event is greater than a preset value from the association factor set; 3) performing causal relationship detection on the high-probability association factorsand the events, and determining strong association factors; 4) generating a big data causal model by utilizing a Bayesian causal network and regulation big data based on the strong correlation factors; and 5) carrying out matching combination on the big data causal model and a preset experience model to generate a regulation and control business big data causal model of the current power grid equipment. By applying the method, the causal relationship between the defect event of the power grid equipment and each factor influencing the time can be intuitively reflected, so that an observer canquickly obtain the cause of the defect of the power grid equipment in an emergency situation.

A system for generating a genotypic causal model of a disease state includes a computing device that generates a causal graph containing genotypic causal nodes and connected symptomatic causal nodes, which contains causal paths from gene combinations to symptomatic datums. Genotypic causal nodes and/or connected symptomatic causal nodes may be generated by feature learning algorithms from training data.

The invention discloses a main effect factor analysis method and equipment based on a causal model. The main effect factor analysis method based on the causal model comprises the following steps: constructing a Bayesian network model, and obtaining direct influence factors of a result node; obtaining an influence path set of influence of each direct influence factor on a result node; when the influence path set comprises indirect influence paths, analyzing the influence degree of the direct influence factors on the result nodes jointly based on the node interaction effect, and otherwise, calculating the influence degree of the direct influence factors on the result nodes directly by adopting an independent influence degree analysis method; and selecting the direct influence factor corresponding to the maximum value from all the influence degrees as a main effect factor. According to the method, the problem of factor isolation of a single-factor analysis method is solved, the main effect factor is extracted on the basis of fully analyzing the linkage interaction influence between the factors, and the reasonability and credibility of the main effect factor analysis conclusion are improved.

The invention discloses a network security information processing method and system based on a causal model. The method comprises the following steps: acquiring a group of data packets received within a preset time period before the current time; judging whether a plurality of data packets conforming to a preset rule exist in the group of data packets or not, the preset rule being the rule that the data packets appear before a preset type of network attack, and the preset rule being obtained by summarizing data packets obtained before the network attack of the preset type occurs after the network attack of the same preset type occurs; under the condition that the judgment result is that the plurality of data packets conforming to the preset rule appear, obtaining the preset type corresponding to the preset rule; and sending the alarm message. According to the method and the system, the problem in the prior art that the cause of the network attack cannot be known is solved, so that support is provided for improving the security of the network.

The invention discloses a nuclear power plant organization behavior reliability assessment method, device and equipment. The method comprises the steps of obtaining an organization error causal modelobtained through scene environment analysis under a preset scene and behavior forming factors influencing organization behaviors in the model and a causal influence relation of the behavior forming factors; obtaining the state level of the behavior forming factor; according to a preset organization behavior reliability assessment model, obtaining a fault probability of the organization behavior tobe assessed by utilizing the state level so as to assess the reliability of the organization behavior, wherein the preset organization behavior reliability assessment model is a model containing corresponding relations between different state level levels of the behavior forming factors and organization behavior fault probabilities. Namely, the state grade level of the behavior forming factor isutilized, the error probability of the to-be-evaluated organization behavior is obtained according to the preset organization behavior reliability evaluation model, quantitative evaluation on the organization behavior reliability is achieved, and theoretical and data support is further provided for prevention of organization errors and risks.

Embodiments of the disclosure relate to a method and apparatus for training a causal model, and a computer readable storage medium. For example, the method for training the causal model includes steps: establishing the causal model based on a plurality of observation variables and at least one hidden variable, wherein the causal model comprises a first parameter and a second parameter which are tobe determined, the first parameter indicates first relations between the plurality of observation variables, and the second parameter indicates second relations between the at least one hidden variable and the plurality of observation variables; determining the second parameter and a third parameter associated with the first parameter by employing a probability principal component analysis; determining noise of the causal model based on the second parameter and the third parameter; and determining the first parameter based on the noise. The embodiment of the disclosure also provides an apparatus capable of realizing the above method and a computer readable storage medium.