Abstract: An intersection ontology may comprise a root node, representing an entire data set, and a second “layer” of nodes, groups of which may be used to represent different types of classifications of the data set. The intersection ontology may then contain one or more layers of nodes that may be represented by intersections of two or more of the second-layer nodes, as may be needed according to a desired application (that is, the intersections may be formed, essentially, on demand). There may be a single layer of intersection nodes, or there may be multiple layers of intersection nodes. In a multiple layer embodiment, each intersection node may be represented as an intersection of second-layer nodes and/or intersection nodes.

Abstract: During a total temporal interval a plurality of characteristic values of the technical system are determined. The total temporal interval is divided into a plurality of partial intervals, each partial interval being between a partial interval starting point and a partial interval end point in the total interval. According to said method, for each partial interval, at least one parameter of a pre-determined predictive model is adapted to the characteristic values determined in the partial interval in such a way as to obtain a partial adaptation with which a partial interval and the end point of the partial interval are associated. Respectively one modification measure is determined for the partial adaptations in such a way as to indicate the modifications of the parameters of the respective partial adaptation in relation to the parameters of at least one adjacent partial adaptation.

Abstract: A method of anomaly detection applicable to telecommunications or retail fraud or software vulnerabilities uses inductive logic programming to develop anomaly characterization rules from relevant background knowledge and a training data set, which includes positive anomaly samples of data covered by rules. Data samples include 1 or 0 indicating association or otherwise with anomalies. An anomaly is detected by a rule having condition set which the anomaly fu,lfils. Rules are developed by addition of conditions and unification of variables, and are filtered to remove duplicates, equivalents, symmetric rules and unnecessary conditions. Overfitting of noisy data is avoided by an encoding cost criterion. Termination of rule construction involves criteria of rule length, absence of negative examples, rule significance and accuracy, and absence of recent refinement.

Abstract: The present invention interrogates computer systems prior to software installations to ensure software installations operate correctly and do not conflict with existing hardware and software. An agent application is first installed on a user's system. When a new program is about to be installed on the user's system, the agent checks if certain prerequisite requirements are met. The prerequisite requirements are downloaded from an expert system library, and the agent interrogates the user's system to determine if it passes the downloaded requirements. If the system passes, then the software is installed. If the system does not pass, then a report is sent to the user and/or a remediation script is initiated to repair the problem. After software is installed, if errors arise that were not previously detected, a feedback mechanism sends the errors to the expert system library so future errors are detected preemptively.

Abstract: In a method for thermally managing a data center housing at least one electronic component, the heat generated by a heat generating device of the at least one electronic component is estimated. In addition, a temperature detected by a first temperature sensor positioned to detect an interior temperature of the at least one electronic component is received. The estimated heat generated by the at least one heat generating device is substantially masked out from the temperature detected by the first temperature sensor and an inlet temperature of the at least one electronic component is determined from a difference between the substantially masked out temperature and the temperature detected by the first temperature sensor.

Abstract: A system that can integrate activities across machines and/or devices is disclosed. The innovation can be used in an “asynchronous” manner that enables a user to move or direct a set of activities and/or tasks within an activity from one device to another. Further, the system can facilitate adapting user interface factors with respect to a particular device such that a user can “synchronously” utilize all devices for the given activities and/or tasks. In other words, the “synchronous” scenario enables a user to share activity information between devices when simultaneously utilizing multiple devices in accordance with a particular activity.

Abstract: An apparatus and method for controlling a portable device. An apparatus for controlling a portable device includes: a touch sensor which comprises at least one touch cell which is chosen by a touch of a user; a first calculation unit which calculates a first probability value while taking dependency relationships among the chosen at least one touch cell into consideration; a second calculation unit which calculates a second probability value without taking the dependency relationships among the chosen at least one touch cell into consideration; a determination unit which determines whether a current touch cell combination of the chosen at least one touch cell is a registered touch cell combination or an unregistered touch cell combination with reference to the first probability value and the second probability value; and an output unit which outputs a function execution signal according to the results of the determining.

Abstract: Real-time video images of a human subject's face are processed by a plurality of classification algorithms developed in an off-line training process to determine the open vs. closed eye state of the subject. The off-line training process utilizes a genetic programming loop embedded within an adaptive boosting loop, and forms the classification algorithms and weighting factors for combining their classification scores. In the real-time process, the individual classification scores are combined and compared to a threshold to determine the open vs. closed eye state.

Abstract: Methods and systems are provided for feature selection in machine learning, in which the features selected for inclusion in a prediction rule are selected based on statistical metric(s) of feature contribution and/or model fitness.

Abstract: A system, method and computer program product for dynamically enhancing and measuring a software application, such as a video game, executing on a computing device, without having to change and recompile the original application code. The system includes a staging environment that monitors the execution of the application and indexes items of graphical and/or audio information generated by the application into a first database. A system administrator or other entity then populates a second database by manual or automated means with one or more business rules, wherein each business rule is associated with one or more of the objects indexed in the first database.

Abstract: A system, method and computer program product for dynamically enhancing a software application, such as a video game, executing on a computing device, without having to change and recompile the original application code. The system includes a staging environment that monitors the execution of the application and indexes each item of graphical and/or audio information generated by the application into a first database. A system administrator or other entity then populates a second database by manual or automated means with one or more business rules, wherein each business rule is associated with one or more of the objects indexed in the first database.

Abstract: Enhancements to Bayesian prediction models for network location traffic provide increased accuracy in web traffic predictions. The enhancements include implementing user advertising target queries to determine preferred edges of a Bayesian model, employing hierarchical data structures to cleanse training data for a Bayesian model, and/or augmenting existing data with new training data to enhance a previously constructed Bayesian model. Preferred edge enhancements for the Bayesian model utilize target attribute derived preferred edges and/or explicitly specified preferred edges. Training data is cleansed utilizing tag hierarchies that can employ parent-child relationships, ancestor relationships, and/or network location specific parameters. New training data can also be employed to adjust probabilities in a previously constructed Bayesian model. The new training data can be weighted differently than data represented by the previously constructed Bayesian model.

Abstract: A method of combinatorial multimodal optimization uses a genetic algorithm to find simultaneous global optimal solutions to combinatorial problems. Each individual within the population is associated not only with a fitness value but with a fitness vector, using which the persistence of all of the best individuals into the next generation can be guaranteed. Phenotype as well as genotype analysis is an integral part of the method.

Abstract: A network architecture of radial basis function neural network system utilizes a blocking layer (4) to exclude successfully mapped neighborhoods from later node influence. A signal is inserted into the system at input nodes (I1, I2, . . . In), which then promulgates to a non-linear layer (2). The non-linear layer (2) comprises a number of non-linear activation function nodes (10). After passing through the non-linear layer (2), the signal passes through the blocking layer (4) that is comprised of either binary signal blocking nodes, or inverted symmetrical Sigmoidal signal blocking nodes (12) that act in a binary fashion. Finally, the signal is weighted by a weighting function (6a, 6b, 6c, 6n), summed at a summer (8) and outputted at (O).

Abstract: A method for solving a constraint satisfaction problem (CSP) comprises identifying a first illegal combination associated with at least one variable, wherein the first illegal combination contradicts at least one constraint; grouping the first illegal combination with a second illegal combination, in response to determining that the first and second illegal combinations contradict the same constraint; identifying at least one failure explanation for each group of illegal combinations, wherein the failure explanation is associated with at least one illegal combination in said group to provide a reason for a contradicted constraint associated with the illegal combination; assigning a value to each variable in the given domain to solve the CSP within the limitations defined by the constraints in a solution path; and generating a result, in response to determining that at least one assigned value to a variable contradicts a constraint.

Abstract: Discloses are a method of and a system for identifying a motif in a graph. The graph has multiple vertices, and the vertices have one or more attributes. The method comprises the steps of, for each of the vertices that have at least a defined one attribute, identifying a set of vertices, if any, adjacent to said each vertex and having at least one specified attribute; and forming a first list comprised of said identified sets. The method comprises the further steps of determining the unique intersections of the sets of said first list; computing compact forms of the sets on said first list; and identifying a motif of the graph from said unique intersections.

Abstract: A method and system of selecting reviews for display are described. Reviews for a subject are identified and organized into two or more clusters. Reviews are selected from each cluster. A response that includes content from the selected reviews is generated. The content may include the full content or snippets of at least some of the selected reviews.

Abstract: A self managed ad hoc communications network nodes and node mobility management. Nodes include an Artificial Neural Network (ANN) that determines connection to other network nodes. The ANN may use free space propagation link life estimation, inverse modeling for partition prediction, Stochastic Approximation, and/or coarse estimation. The node includes storage storing network tables and matrices indicating network connectivity and connection to other nodes. Also, a wireless communications unit provides for wireless communicating with other nodes.

Abstract: The invention provides a method and system by which research data can be collected and analyzed during the course of the research testing, and the research testing itself possibly modified to account for conclusions drawn from the research data. In a first aspect of the invention, a research subject can respond to a protocol stored on a server by manipulating input keys on a remotely located client device onto which a research protocol has been installed. The protocol can include questions concerning the subject's physical or mental well being such as whether their symptoms are relieved or not, or even exacerbated. The protocol can also include calling for data obtained by coupling the client device with another medical device such as a glucose monitor. In a preferred embodiment, the subject is presented with narrowly structured questions and suggested answers provided by the protocol. The set of possible answers is restricted.

Abstract: A method and system is provided for predicting loads within a power system through the training of on-line and an off-line neural networks. Load data and load increments are used with an on-line load prediction scheme to generate predicted load values to optimize power generation and minimize costs. This objective is achieved by employing a method and system which predicts short term load trends through the use of historical load data and short term load forecast data.