Abstract: A system which observes the world through a video camera and/or other sensors, automatically learns a probabilistic model of normative behavior through the use of a Hidden Markov Model, and uses that model to infer the kind of activity currently under view and detect unusual behavior. The use of hidden Markov models is made possible by entropic training of the model with an &thgr;&thgr; entropic estimator that folds structure learning into the parameter estimation process to remove parameters from the Hidden Markov Model which have little information content, thus to permit real time robust unusual behavior detection. In one embodiment, the system consists of three components: image analysis; model learning; and signal analysis. In image analysis, each frame of video is reduced to a vector of numbers which describe motion of objects in front of the camera, with a sequence of such vectors, one for each frame of video, establishing the “signal.

Abstract: A publishing data processing method for use in a publish/subscribe data processing broker network having a plurality of broker data processing apparatuses each of which has an input for receiving published messages directly from a publisher application and/or receiving subscription data directly from a subscriber application, the method includes steps of: Publishing a message on a topic to a first broker data processing apparatus; and providing an indication as to whether the published data message is to be considered as local to the first broker apparatus. Also included are an analogous subscribing data processing method, an analogous broker data processing method, apparatuses and computer program products.

Abstract: In a publish/subscribe data processing broker network having a plurality of broker data processing apparatuses each of which has an input for receiving published messages directly from a publisher application and/or receiving subscription data from a subscriber application, a first broker apparatus has: a software unit for receiving via said input subscription data from a subscriber application; a software unit for providing an acknowledgement to said subscriber application to acknowledge that the subscription data has been received; a software unit for propagating said subscription data to a group of other broker apparatuses; a software unit for determining whether said means for propagating has propagated said subscription data to the group of other broker apparatuses; and a software unit for receiving via said input an indication from said subscriber application that said acknowledgement should not be sent to the subscriber application until the means for determining has determined that said means for prop

Abstract: A self-optimizing method and machine automatically develop computer software in real-time according a specified performance by computer-generating a knowledge base associated with the computer software, by instantly computer-coding the computer-generated knowledge base into the computer software, and by saving the developed computer software in a software storage device.

Abstract: The present invention provides a method of performing statistical classification that can resolve conflict in independent sources of information, thereby creating a robust statistical classifier that has superior performance to classifiers currently available. Additionally, the present invention is automatically trainable, yielding improved classification performance. The present invention may be embodied in a method of statistically classifying events or objects, including the steps of gathering sets of information representative of features of an object or event; creating basic probability assignments based on said sets of information; determining a coarse information set from said sets of information; performing coarsening on said sets of information; performing linear superposition on each feature; and combining all features to reach a conclusion.

Abstract: The present invention discloses a system and method for diagnosing and validating a machine with waveform data generated therefrom. In this invention, historical waveform data are obtained from machines having known faults along with corresponding actions for repairing the machines and are used to develop fault classification rules. The fault classification rules are stored in a diagnostic knowledge database. The database of classification rules are used to diagnose new waveform data from a machine having an unknown fault.

Abstract: The inventive system and method incorporates artificial intelligence concepts to create a system that automatically integrates new network elements. The system detects the connection of the new element with the system. The system identifies the new element, either directly or inferentially, by examining the protocol, the inputs, and the outputs of the new element, as compared with stored information. The inventive system then either selects the appropriate rule set from previously written rules, modifies an existing rule set from similar elements, or creates an appropriate rule set to integrate each new element into the network. The rule set produced by the system is then used to manage the new element.

Abstract: An information filtering apparatus estimates an evaluation value (suitability) of a demander with respect to an item which is not evaluated by the demander but is evaluated by users other than the demander. The information filtering apparatus estimates the suitability by studying relation among the demander and the other users with respect to an evaluation value evaluated for each item by the demander and the other users. A suitable estimating means may compute the suitability in consideration of the population density or an Leading-Edge degree. The suitability can be estimated by computing the Leading-Edge degree.

Abstract: Telecommunications processing is applied to a reference signal to generate a signal under test. A fidelity measure is generated characterizing the fidelity of the signal under test relative to the reference signal. A control signal is generated from the fidelity measure, where the control signal is used as a feedback signal to adjust the telecommunications processing. In one embodiment, the reference signal is a speech signal and the signal under test is a decoded speech signal generated by encoding, transmitting, and decoding the reference speech signal. The fidelity signal is an average mean opinion score (MOS) and the control signal is used to control the speech decoding processing. For example, the speech decoding processing may involve a speech decoder followed by a post filter, and the control signal is the cut-off frequency of the post filter.