131 results about "Causal relations" 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 processor architecture for a learning machine is presented which uses a massive array of processing elements having local, recurrent connections to form global associations between functions defined on manifolds. Associations between these functions provide the basis for learning cause-and-effect relationships involving vision, audition, tactile sensation and kinetic motion. Two arbitrary images hold each other in place in a manifold association processor and form the basis of short-term memory.

The present invention relates to control, monitoring, and automation. The present invention more specifically relates to pattern-based intelligent control, monitoring and automation. The invention performs pattern-based monitoring. It collects signal data from one or more signals. The signal data define signal data streams. It then transforms each of the signal data streams into trends. It also discovers patterns based on the trends within each signal data stream and/or across the signal data streams. The patterns are optionally used for diagnostics and root cause analysis, online plant monitoring and operation control, plant optimization, and other environments where a causal link or correlation may exist between related inputs, states and/or outputs.

The invention provides an online anomaly monitoring and diagnosis method and system. The method comprises the steps that the causal relation and conditional relation among all signals are defined based on a directed graph model; based on definitions of the signals by the directed graph model, the signals in acquired historical data are classified, and a training set of the historical data is established to perform model training and determine model parameters; and based on real-time data theoretical values of the signals in real-time data obtained after the real-time data acquired through online monitoring is input into a trained model, whether the signals in the real-time data are abnormal is determined. The system adopting the method and a computer readable medium storing a program executing the method are also included. Through the method, the system and the computer readable medium, a complete logic relation and casual relation are constructed for the whole process of industrial production and operation through the directed graph model, and more reasonable, more correct, more accurate and efficient production online anomaly diagnosis prediction is realized in combination with machine learning.

A process for generating a performance model from a functional model for a system including a plurality of distributed hardware and software entities that engage to provide a service to at least one user. The process distributes the representative system requests in a finite number of groups and identifies, for each request group, the corresponding execution flow, formalizes the execution flows by a notation that makes it possible to highlight the causal relationships between the different software entities of the system that are involved in the execution flows and the data characterizing the system's resource consumption, develops an intermediate model, and automates the conversion of the developed intermediate model into a performance model.

The invention discloses a workflow mining method based on subsequent tasks. The workflow mining based on an event log takes the event log as an input and takes a workflow model described by a Petri network as an output result; by the method, event types are introduced to ensure that the workflow log comprises a subsequent task of the current task, and the subsequent task refers to an aggregate of the tasks to which an execute permission is transferred after the current task is finished; and the method comprises the following steps of: (1) setting an initial value for a workflow process model to be mined; (2) analyzing the event log W, and calculating a task set TW, an initial task and an end task TO; (3) calling a relation Preprocess process to obtain a causal relation matrix M2 and a potential concurrency relation and concurrency relation matrix M3; and (4) calculating an initial task relation set XW according to the matrixes M2 and M3. By the invention, an integrated workflow mining method based on the subsequent tasks is formed.

The present disclosure relates to power system sensitivities as computed from power flow parameters and control parameters of a Power Flow Control Device (PFC). To this end, control parameter variations are applied to or generated by a PFC, and comprise variations in a control input u, a control effort e (injected series voltage, inserted series reactance), or a control effect q (power flow, active power transfer, phase-shift, current). A power flow response measuring unit measures a variation of a power flow response such as current, active or apparent power, in a way sufficiently synchronized with the control parameter variation to allow establishing an unambiguous causal relationship or correspondence in the form of a power system sensitivity. The latter may be on-line adapted to continuously reflect an updated aspect of the power system behaviour, and thus enable an improved, fast and reliable power flow control in power systems comprising a meshed power network with two parallel flow paths or corridors connecting two areas or sub-systems.

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 and method for identifying, monitoring, and analyzing various trends and patterns of interest within an organization in order to maximize aspects thereof, including, for example, productivity, efficiency, and employee health and safety. The invention utilizes a centralized data repository to accessibly store and maintain data; date gap analysis to avoid aggregation on calender or other artificial boundaries; control chart analysis to allow for easy understanding of the data; workload adjustments to avoid false indicators; tabular and graphical data displays which facilitates identifying anomalous data and monitoring for data quality; and a drill down mechanism for investigating trends and anomalous data points in detail. Analysis may be performed on various normalized data sets and the results simultaneously displayed to allow comparison and easier identification of interrelated variables and, thereby, of cause and effect. The effectiveness of remedies and intervention schemes may also be monitored and analyzed.

A method for constructing a database to deduce a disease and constructing a Bayesian network for U-Health application, the method including the steps of analyzing U-Health information, which includes a disease, a symptom, and a treatment, and constructing a plurality of U-Health ontologies required for service provision, setting a meta-model defining cause-and-effect relationships between the constructed U-Health ontologies and selecting at least two specific U-Health ontologies from among the plurality of U-Health ontologies, setting the selected U-Health ontologies as nodes, and generating a Bayesian network by applying the meta-model to the set nodes.

[Object] To provide a question-answering system capable of appropriately answering to a non-factoid question.

[Solution]

A question-answering system 30 includes: a related document searching unit 54 responsive to a question, for taking out answer candidates from an object document storage unit 32; an answer candidate extracting unit 56 extracting plausible ones from the answer candidates; a causal relation recognizing unit 60 recognizing causal relation expression included in extracted answer candidates; causal relation relevancy determining unit 64 determining whether or not a recognized causal relation is relevant as an answer; a feature vector generating unit 66 generating a feature vector related to a combination of the question and the searched answer candidate using the results of processing up to the causal relation relevancy determining unit 64; and a feature vector generating unit 66 for calculating, when a feature vector is given, a score indicating a degree of how correct an answer candidate is as an answer to the question, for the question and the answer candidate as a source of the feature vector, and for outputting, as the answer to the question, an answer candidate having the highest score.

Systems, methods and recordable media for facilitating user-guidance of computational analysis and knowledge extraction tools for use with biological data for disambiguation and determination of causation in representations of the data. Systems, methods, tools and computer readable media for user-guided expansion of biological networks and manipulations of the same. Tools for qualitative simulation of network models, for identifying interactions between multiple networks and form maintaining knowledge about multiple alternative biological networks. Combinations of portions of networks may be constructed to provide optimal networks. Networks may be evaluated against experimental data and networks of interest may be identified based on experimental data.

The present invention provides a method for extracting relationships between words in textual data. Initially, a classifier is trained to identify text data having a specific format, such as situation-response or cause-effect, using a training corpus. The classifier receives input identifying components of the text data having the specified format and then extracts features from the text data having the specified format, such as the part of speech for words in the text data, the semantic role of words within the text data and sentence structure. These extracted features are then applied to text data to identify components of the text data which have the specified format. Rules are then extracted from the text data having the specified format.

Conventionally, there is a technique to conduct a cause analysis in which a single evaluation axis, such as a performance time, is used to configure a problem point network. However, in particular, in a system to visualize a management problem in which problems are intricately-intertwined with one another, information on multiple evaluation axes, collected from a business system, are utilized, and units are different for respective evaluation axes. Therefore, it is difficult to simply specify a cause of problem occurrence. In view of this situation, an object of the present invention is to extract and present factor which has a significant influence on the problem occurrence. The present invention is directed to an apparatus which stores causal relation information specifying the causal relation and the relation level between the indexes, business goal achievement level information, and an influence level of the causal relation, calculates the influence level by using the business goal achievement level information and the relation level of the causal relation, specifies as the causal index the index having a large influence, and generates screen information for displaying a graph and/or table relating to the causal index.

Described is a novel, new, inexpensive approach to screen, perform early diagnosis (on asymptomatic and symptomatic subjects for example), diagnose, establish root causes, and treat subjects. A series of medical steps, each of which is designed to provide the administering healthcare provider with both subjective and objective risk, health and cause evaluation information provides a guide a practitioner to treatments that prevent, slow, delay, stop, or reverse the chronic disease conditions at the root of their cause. Each step in the process provides intelligence about cause and effect. The sum of the steps, when evaluated based on patient outcome, is the basis of a chronic disease health learning engine that leads to continuous improvement of medical knowledge, disease, and methods of healing and treatments to improve patient outcomes.

In one embodiment, a method is contemplated. The method includes exposing at least three dimensions of a protection system to a user. The three dimensions are interrelated. The method further includes receiving user input indicating a modification in a first dimension of the at least three dimensions; and determining an effect of the modification in each other dimension of the at least three dimensions. A computer accessible medium comprising a plurality of instructions which, when executed, implement the method and a system implementing the method are also contemplated.

Method and apparatus for determining causal relations between a plurality of intercommunicating nodes. In various embodiments, trace data is input that describe inter-node communication. The trace data may include for each message sent between nodes a timestamp that indicates a time at which the message was sent, a source identifier that identifies a node from which the message was sent, and a destination identifier that identifies a node to which the message was sent. For each of one or more nodes, a determination may be made as to whether one or more causal relations exist between a first set of messages destined to the node and a second set of messages sourced from the node and destined to at least one other node. A causal relation may exist as a function of a probability distribution of delay values that are differences between timestamps of messages in the second set and timestamps of messages in the first set. From the nodes and causal relations a processor-readable representation is generated.

The invention discloses an analyzing method and an analyzing device for operator state assessment reliability. The method comprises the steps of determining a plurality of PSFs, wherein the PSFs are used for state assessment; determining the incidence relation between each PSF and all the other PSFs in the plurality of PSFs except the PSF itself and the incidence relation between each PSF and a state assessment reliability node; and according to the incidence relations, establishing an analyzing model of the operator state assessment reliability based on the PSF causal relations so as to analyze the reliability of an operator. Through the application of the analyzing method and the analyzing device, the problems that in the prior art, due to the fact that influences of situational environmental factors to the operator and influence causal relations of the factors are not considered, the possibility of repetitive computation of the influences is brought, and false assessment can be caused to state assessment miss probability are solved, therefore a qualitative and quantitative method is provided for analyzing the operator state assessment reliability and strategies are provided for lowering operator state assessment failure probability for an electric power plant.