462 results about "Causality" patented technology

Methods, systems, and computer program products for developing and using predictive models for predicting medical outcomes and for evaluating intervention strategies, and for simultaneously validating biomarker causality are disclosed. According to one method, clinical data from different sources for a population of individuals is obtained. The clinical data may include different physical and demographic factors regarding the individuals and a plurality of different outcomes for the individuals. Input regarding a search space including models linking different combinations of the factors and at least one of the outcomes is received. In response to receiving the input, a search for models in the search space based on predictive value of the models with regard to the outcome is performed. The identified models are processed to produce a final model linking one of the combinations of factors to the outcome. The final model indicates a likelihood that an individual having the factors in the final model will have the outcome.

A method for self-determining a root cause of a system fault in a heating, ventilation, and cooling (HVAC) system includes receiving a fault message indicative of a fault condition in an operating characteristic of the HVAC system; determining a causal relationship between the fault condition and a predetermined list of root causes associated with the fault condition; receiving information indicative of operating conditions of the HVAC system; and eliminating at least one root cause that is unrelated to the fault condition in response to the receiving of the information.

A system and method for computer assisted event based reconstruction and forensic analysis of vehicle accidents is provided. The system comprises an event capture device that records audio, video, and other information that collectively comprise one or more events related to a vehicle accident. The event data, including the audio, video, and other related information, is provided to an evaluation server where it is stored in a database for forensic analysis of the events comprising the vehicle accident. Event data for a specific automobile accident event is analyzed and compared to similar types of automobile accident event data in order to forensically analyze the specific event and correlate causal relationships with key elements of the event data to determine the likely cause of the accident or the factors contributing to the accident. Correlation information is also stored at the evaluation server to provide historical data points about causal relationships and key elements.

The invention comprises a robotic microscope system and methods that allow high through-put analysis biological materials, particularly living cells, and allows precise return to and re-imaging of the same field (e.g., the same cell) that has been imaged earlier. This capability enables experiments and testing hypotheses that deal with causality over time intervals which are not possible with conventional microscopy methods.

In a quality control system for manufacturing industrial products, the product quality history and the manufacturing process history are collected and collated to calculate the correlation magnitude between the two histories. The candidates for the cause of quality variation hidden in the manufacturing processes are listed, and the correlation magnitude between all combinations of the variates of the manufacturing process history are calculated. Further, by utilizing the manufacturing sequence history used for an input plan, a causation connecting structure model between the manufacturing processes of the manufacturing line is automatically generated and automatically analyzed thereby to automatically extract the fundamental cause of quality variation from the candidates for the cause of quality variation. By doing so, the cause of quality variation of industrial products manufactured through a complicated process can be traced in a complicated connecting structure in the manufacturing history data.

A system and method for network fault diagnosis in a network having network elements is presented. The method comprises creating a network causality model, generating Boolean expressions from the network causality model, converting the Boolean expressions into SAT sets, receiving network monitoring results, correlating these monitoring results with the SAT sets, and enumerating all possible diagnostic explanations of potential faults, properly annotated. Creating a network causality model can comprise creating, for each network element, an element-specific causality model, stitching together all network elements using the element-specific causality models and a network topology, retrieving monitoring state and propagation information, and generating the network causality model using the stitched together network elements and the monitoring state and propagation information. Stitching together network elements can comprise adding causes and implies dependency between appropriate network elements and/or adding and connecting reachable and not-reachable states. The network causality model can comprise network element states.

The invention provides a rule engine-based method and a rule engine-based system for monitoring exceptional service of bank. The method mainly comprises the followings steps: defining and describing operational risk factors of bank service flows, products and service units; determining a lost data and risk data collecting frame to analyze important lost data to determine a cause-and-effect relationship between loss events and risk factors; determining a key risk indicator (KPI); measuring a possible loss amount and a risk probability; measuring the effectiveness of the current management and control method, and making a more effective management and control scheme; deciding and implementing an efficiency and phase equilibrium-based management and control system; and effectively monitoring risk early warning indexes, risk reports aiming at senior management and the risk management and control method. Operational risks of commercial banks are comprehensively monitored, and risks are ensured to be controlled. The system is divided according to logical levels and comprises a service data layer, a data acquisition layer, a data storage layer, a risk processing layer, a risk management layer and an information presentation layer.

A virtual domain management system is provided which associates application, physical and virtual domains to enable propagation of events, symptoms and other information across the domains. The virtual domain manager collects events and symptom information across multiple domains by correlating domain topology models. Using a causality matrix and codebook technology the virtual domain manager uses the information to perform root cause and impact analysis across domains. Information from the analysis may be fed back into the domains to enhance domain management.

A system, method and computer program product for improving the delivery of healthcare services may include, e.g., but not limited to, in an exemplary embodiment, a) capturing data associated with at least one health care services event, wherein said data comprises at least one aspect of said at least one health care services event; b) categorizing, into at least one category, said at least one aspect of said at least one health care services event; c) analyzing said data associated with said categorized health care services event comprising: i) determining a correlation between said at least one aspect of said data to said at least one category, and ii) determining any cause and effect relationship between said at least one aspect and said at least one category; and d) recommending at least one course of action based on said at least one aspect having said correlation and said cause and effect relationship to said at least one category, is disclosed.

A method of determining correlations and causality between media program content and consumer responsiveness involves identifying and storing media and commercial program time occurrence and content information and consumer media reviewing actions which occur in connection with the media and commercial program time occurrence and content information. The information is correlated to obtain and assign responsiveness probability values corresponding to type and intensity of consumer response for each of the media and commercial program time occurrence and content information. These responsiveness probability values are then applied to a second media program to place product advertising at a specific time within specific content therein as determined by the responsiveness probability values thus facilitating creation of new ads and modification of existing ones and further, directing placement of those advertisements within any and all broadcast and Internet media programming.

In a network that includes intermediary nodes, such as WAN accelerators, that transform messages between nodes, an end-to-end path of the messages is determined. The determined end-to-end path is used in subsequent analyses of message traces, to identify timing and other factors related to the performance of the network relative to the propagation of these messages, including the propagation of the transformed messages. A variety of techniques are presented for determining the path of the messages, depending upon the characteristics of the collected trace data. Upon determining the message path, the traces are synchronized in time and correlations between the connections along the path are determined, including causal relationships. In a preferred embodiment, a user identifies an application process between or among particular nodes of a network, and the system provides a variety of formats for viewing statistics related to the performance of the application on the network.

A system for problem resolution in network and systems management includes a database of trouble ticket data including information fields for checked components and affected components, an automated model builder system that processes the trouble ticket data to construct a causality model to represent causality information between system components identified in the checked component and affected component fields of the trouble ticket data, and an automated problem analysis system that receives information indicative of a problem event and determines a cause of the problem event using the causality model.

A method and apparatus for constructing a neuroscience-inspired artificial neural network (NIDA) or a dynamic adaptive neural network array (DANNA) or combinations of substructures thereof comprises one of constructing a substructure of an artificial neural network for performing a subtask of the task of the artificial neural network or extracting a useful substructure based on one of activity, causality path, behavior and inputs and outputs. The method includes identifying useful substructures in artificial neural networks that may be either successful at performing a subtask or unsuccessful at performing a subtask. Successful substructures may be implanted in an artificial neural network and unsuccessful substructures may be extracted from the artificial neural network for performing the task. The method and apparatus supports constructing, using and reusing components and structures of a neuroscience-inspired artificial neural network dynamic architecture in software and a dynamic adaptive neural network array.

Methods and systems for designing an experiment using a computer to determine whether the experiment is a true experiment are described. These approaches allow a user who is unsophisticated in the complexities of true experimental design to design and deploy an experiment that produces substantially confound-free results and can be used to determine and quantify any causal relationship between independent and dependent variables. The computer may select one or more independent and/or dependent variables of the experiment or may assist the user in selection of independent and/or dependent variables. Formation of control and treatment groups, randomization and/or blocking to reduce the effects of confounding variables may be performed by the computer with or without input from the user.

This patent describes a method and apparatus to automatically and accurately winnow down arbitrarily large amounts of electronic information created by a particular population of actors to only those subsets of particular interest by having a causal relationship, even when retrieved documents containing this information do not individually satisfy the search criteria used. An actor in this context is defined as any entity, single or aggregate, capable of creating, distributing, modifying, or receiving digital information. Once identified, this subset of information may, for example, be processed, analyzed, redacted, or destroyed, depending on the context of the system's use.

The disclosed embodiments provide a system for processing data. During operation, the system generates, from a set of traces of an asynchronous workflow, a graph-based representation of the asynchronous workflow. Next, the system uses a set of causal relationships in the asynchronous workflow to update the graph-based representation. The system then analyzes the updated graph-based representation to identify a set of high-latency paths in the asynchronous workflow. Finally, the system uses the set of high-latency paths to output an execution profile for the asynchronous workflow, wherein the execution profile includes a subset of tasks associated with the high-latency paths in the asynchronous workflow.

The present invention is directed to computer-based methods and system to perform root-cause analysis on an industrial process. The methods and system load process data for an industrial process from a historian database and build a hybrid first-principles and inferential model. The methods and system then executes the hybrid model to generate KPIs for the industrial process using the loaded process variables. The methods and system then selects a subset of the KPIs to represent an event occurring in the industrial process, and divides the data for the subset into multiple subset of time series. The system and methods select time intervals from the time series based on the data variability in the selected time intervals and perform a cross-correlation between the loaded process variables and the selected time interval, resulting in a cross-correlation score for each loaded process variable. The methods and system then select precursor candidates from the loaded process variables based on the cross-correlation scores and execute a parametric model for performing quantitative analysis of the selected precursor candidates, resulting in a strength of correlation score for each precursor candidate. The methods and system select root-cause variables from the selected precursor candidates based on the strength of correlation scores for analyzing the root-cause of the event.

The system and method for determining fuzzy cause and effect relationships in an intelligent workload management system described herein may combine potential causes and effects captured from various different sources associated with an information technology infrastructure with substantially instantaneous feedback mechanisms and other knowledge sources. As such, fuzzy correlation logic may then be applied to the combined information to determine potential cause and effect relationships and thereby diagnose problems and otherwise manage interactions that occur in the infrastructure. For example, information describing potential causes and potential effects associated with an operational state of the infrastructure may be captured and combined, and any patterns among the information that describes the multiple potential causes and effects may then be identified. As such, fuzzy logic may the be applied to any such patterns to determine possible relationships among the potential causes and the potential effects associated with the infrastructure operational state.

A method and apparatus for determining the number and location of monitoring entities in a distributed system is disclosed. The method comprising the steps of automatically generating a causality mapping model of the dependences between causing events at the nodes of the distributed system and the detectable events associated with a subset of the nodes, the model suitable for representing the execution of at least one system operation, reducing the number of detectable events in the model, wherein the reduced number of detectable events is suitable for substantially representing the execution of the at least one system operation; and placing at least one of the at least one monitoring entities at selected ones of the nodes associated with the detectable events in the reduced model. In another aspect, the processing described herein is in the form of a computer-readable medium suitable for providing instruction to a computer or processing system for executing the processing claimed.

Solutions for responding to security-related incidents in a computer network, including a security server, and a client-side arrangement. The security server includes an event collection module communicatively coupled to the computer network, an event analysis module operatively coupled to the event collection module, and a solution module operatively coupled to the event analysis module. The event collection module is configured to obtain incident-related information that includes event-level information from at least one client computer of the plurality of client computers, the incident-related information being associated with at least a first incident which was detected by that at least one client computer and provided to the event collection module in response to that detection. The event analysis module is configured to reconstruct at least one chain of events causally related to the first incident and indicative of a root cause of the first incident based on the incident-related information. The solution module is configured to formulate at least one recommendation for use by the at least one client computer, the at least one recommendation being based on the at least one chain of events, and including corrective/preventive action particularized for responding to the first incident.

Analyzing an event chronology record to permit identification of periods of a production sequence that correspond to a high probability of failure. Systems and methods include receiving an event chronology for a particular machine in the production sequence and for a particular time interval. A reliability analysis system accesses process flow information to determine whether a particular event in the event chronology is related to a subsequent adverse event within a predefined event window.

Computer-implemented methods and systems for determining causation of a dangerous condition in premises liability for an accident are provided. In one embodiment, a set of characteristics of the accident may be provided to a computer system. In some embodiments, a cause in fact of a claimant's harm may be determined from at least one of the characteristics. In certain embodiments, a proximate cause of the claimant's harm may be determined from at least one of the characteristics.

A method providing simple fine-grain hardware primitives with which software engineers can efficiently implement enforceable separation of programs into modules and constraints on control flow, thereby providing fine-grain locality of causality to the world of software. Additionally, a mechanism is provided to mark some modules, or parts thereof, as having kernel privileges and thereby allows the provision of kernel services through normal function calls, obviating the expensive prior art mechanism of system calls. Together with software changes, Object Oriented encapsulation semantics and control flow integrity in hardware are enforced.

A method for creating a predictive model is disclosed herein, including the steps of determining trends and patterns in electronic data, using at least a first machine language algorithm, refining the determination of the algorithm, searching for social models that describe the identified trends and patterns using at least a second machine language algorithm, verifying causal links, constructing at least one model about human node behavior and interactions, utilizing the social models to do at least one of the following: validate hypotheses, predict future behavior, and examine hypothetical scenarios, and automatically updating predictions when new data is introduced.