Abstract: The present invention relates to a system of artificial intelligence for the classification of events, objects or situations from signals and discriminant parameters produced by models comprising at least one processing branch comprising a fuzzy expert system making a decision according to high level properties and discriminant parameters of low level extracted from signals by signal processing type procedures, and capable of explaining its decision to the user through the intermediary of rules selected by order of applicability.

Abstract: A method, system and machine-readable storage medium for monitoring an engine using a cascaded neural network that includes a plurality of neural networks is disclosed. In operation, the method, system and machine-readable storage medium store data corresponding to the cascaded neural network. Signals generated by a plurality of engine sensors are then inputted into the cascaded neural network. Next, a second neural network is updated at a first rate, with an output of a first neural network, wherein the output is based on the inputted signals. In response, the second neural network outputs at a second rate, at least one engine control signal, wherein the second rate is faster than the first rate.

Abstract: The invention provides a method and apparatus for selecting desired attributes for system configuration. The invention uses one or more rule sets to define rules that are met when a configuration is valid. A rule set may specify the interrelation of attribute values within a product or between two or more products. If the combination of attribute values that specify a product conform to at least one rule in each of the rule sets that apply to that product, that combination of attribute values is considered to specify a valid product. If the combination of attribute values that specify all of the products of an assembly conform to at least one rule in each of the rule sets that apply to that assembly, that combination of attribute values is considered to specify a valid assembly.

Abstract: In a method and system for developing a neural system adapted to perform a specified task, a population of neural systems is selected, each neural system comprising an array of interconnected neurons, and each neural system is encoded into a representative genome. For a given genome, a processing gene encodes a neural output function for each neuron, and the connections from each neuron are encoded by one or more connection genes, each connection gene including a weight function. The given neural system is operated to perform the specified task during a trial period, and performance is continually monitored during the trial period. Reinforcement signals determined from the continually monitored performance are applied as inputs to the functions respectively associated with each of the processing genes and connection genes of the given neural system.

Abstract: A system and method for controlling information output based on user feedback about the information is provided that comprises a plurality of information sources providing information. The information sources may be electronic mail providers, chat participants, or page links. At least one neural network module selects one or more of a plurality of objects to receive information from the plurality of information sources based at least in part on a plurality of inputs and a plurality of weight values during that epoch. At least one server, associated with the neural network module, provides one or more of the objects to a plurality of recipients. The objects may comprise electronic mail messages, chat participants viewers, or slots within a link directory page. The recipients provide feedback about the information during an epoch.

Abstract: The methods, systems and devices of the present invention comprise use of Support Vector Machines and RFE (Recursive Feature Elimination) for the identification of patterns that are useful for medical diagnosis, prognosis and treatment. SVM-RFE can be used with varied data sets.

Abstract: A pattern recognition system, comprising a neural network formed utilizing nanotechnology and a pattern input unit, which communicates with the neural network, wherein the neural network processes data input via the pattern input unit in order to recognize data patterns thereof. Such a pattern recognition system can be implemented in the context of a speech recognition system and/or other pattern recognition systems, such as visual and/or imaging recognition systems.

Abstract: A method of emulating the human brain with its thought and rationalization processes is presented here, as well as a method of storing human-like thought. The invention provides for inclusion of psychological profiles, experience and societal position in an electronic emulation of the human brain. This permits a realistic human-like response by that emulation to the people and the interactive environment around it.

Abstract: A neural network module including an input layer having one or more input nodes arranged to receive input data, a rule base layer having one or more rule nodes, an output layer having one or more output nodes, and an adaptive component arranged to aggregate selected two or more rule nodes in the rule base layer based on the input data, an adaptive learning system having one or more of the neural network modules, related methods of implementing the neural network module and an adaptive learning system, and a neural network program.

Abstract: A collection of data is processed and information arising from the processing can be distributed in a variety of ways to support a decision-making process. A query-analyze-distribute approach can be used, and queries, analysis directives, and distribution directives can be associated into a sequence and shared. Access to interim processing is provided, allowing recipients of information to more easily understand and refine the processing. Unbound queries, unbound analysis directives, and unbound distribution directives can be used and shared so that the queries, analysis directives, and distribution directives can be tailored to a particular situation via binding. The query, analysis, and distribution processing can be loosely-coupled to allow easy interchange and combination of sequence elements. A sequence can be scheduled for periodic execution, and distribution of data can be limited to instances when data falls outside of certain expected values.

Abstract: An artificial neural network is disclosed that processes holography generated characteristic patterns of vibrating structures along with finite-element models. The present invention provides for a folding operation for conditioning training sets for optimally training forward-neural networks to process characteristic fringe patterns. The folding pattern increases the sensitivity of the feed-forward network for detecting changes in the characteristic pattern. The folding routine manipulates input pixels so as to be scaled according to the location in an intensity range rather than the position in the characteristic pattern.

Abstract: A quality of service (QOS) framework for mediating needs of software applications in the context of an application framework with capabilities of a network host platform in response to a service request from the software application. The QOS framework includes a QOS knowledge base and rules module including a specialized set of system wide rules for dynamically changing QOS behavior in response to the service request. The QOS framework also includes QOS framework service modules for negotiating between the software application and the network host platform based on the specialized set of system wide rules included in the QOS knowledge base and rules module. In addition, the QOS framework includes a plurality of QOS application platform interfaces (APIs) for interconnecting the QOS framework service modules with the QOS knowledge base and rules module, and a plurality of APIs for connecting the application with the QOS framework service modules and with the network host platform.

Abstract: A system, software module, and computer program product for performing neural network based data mining that improved performance in model building, good integration with the various databases throughout the enterprise, flexible specification and adjustment of the models being built, and flexible model arrangement and export capability.

Abstract: In order to increase a response rate, a data mining server selects an advertisement mail among a plurality of advertisement mails to be sent in a test transmission to personal computers selected at random among those owned by registered customers. The data mining server then computes learning parameters for each of sent advertisement mails from learning data created from response results of the test transmissions. Then, the data mining server applies learning parameters of each advertisement mail to original assessment data of other personal computers each serving as an object of an actual transmission to find predicted values. Subsequently, the data mining server extracts assessment data with largest advertisement-mail predicted values from the original assessment data. The data mining server then synthesizes the extracted pieces of assessment data.

Abstract: A method and system for determining the state-of-health of a nickel-metal hydride battery connected to a load comprises: detecting at least one of a real and imaginary part of an impedance of the battery at each of a first set of selected frequencies, the first set of selected frequencies including at least one frequency, and determining the state-of-health of the battery from a fuzzy system trained in a relationship between each impedance and the state-of-health, wherein the state-of-health is a function of the battery's ability to deliver power required by the load and the battery's capacity to meet load requirements.

Abstract: A framework for managing approximate models in generation-based evolution control is proposed. This framework is well suited for parallel evolutionary optimization that is able to guarantee the correct convergence of the evolutionary algorithm and to reduce the computation costs as much as possible. Control of the evolution and updating of the approximate models are based on the estimated fidelity of the approximate model. The frequency at which the original function is called and the approximate model is updated is determined by the local fidelity of the approximate model. By local fidelity the fidelity of the model for the region where the current population is located is designated. The lower the model fidelity is, the more frequently the original function should be called and the approximate models should be updated.

Abstract: An apparatus for maintaining components in neural network formed utilizing nanotechnology is described herein. A connection gap can be formed between two terminals. A solution comprising a melting point at approximately room temperature can be provided, wherein the solution is maintained in the connection gap and comprises a plurality of nanoparticles forming nanoconnections thereof having connection strengths thereof, wherein the solution and the connection gap are adapted for use with a neural network formed utilizing nanotechnology, such when power is removed from the neural network, the solution freezes, thereby locking into place the connection strengths.

Abstract: A CAI system for vehicle repair workers is disclosed. The CAI system for supporting an instruction for one group consisting of a plurality of training participants includes a storage device for storing attribute data of each participant, a keyboard for inputting degree-of-master basic data of each participant for every plurality of instruction items, and a control unit for processing the data, the control unit evaluates a degree of master of each participant for every instruction item, calculates an overall evaluation of the concerned instruction item of the target group, selects the instruction item exhibiting a low degree of master by comparing the overall evaluations of the concerned instruction item, and selects which instruction target person should be instructed with respect to the selected instruction item. The CAI system is capable of efficiently enhancing a working efficiency of one working group consisting of the plurality of workers.

Abstract: A method, system and machine-readable storage medium for monitoring an engine using a cascaded neural network that includes a plurality of neural networks is disclosed. In operation, the method, system and machine-readable storage medium store data corresponding to the cascaded neural network. Signals generated by a plurality of engine sensors are then inputted into the cascaded neural network. Next, a second neural network is updated at a first rate, with an output of a first neural network, wherein the output is based on the inputted signals. In response, the second neural network outputs at a second rate, at least one engine control signal, wherein the second rate is faster than the first rate.

Abstract: A current-mode pulse-width-modulation (PWM) circuit converts analog current signals into pulse signals. The PWM circuit includes a first I-V converter and one or more second I-V converters, each of the one or more second I-V converters being coupled to one of the current signals. Each of the first and second I-V converters is also coupled to a current generator which generates a current that linearly changes with time. For each of the first and second I-V converters, when a polarity of the input current thereof changes, an output changes between a high voltage level and a low voltage level. A logic circuit is coupled to the first and each second I-V converter to obtain a pulse signal that has a pulse width linearly proportional to the current level of the respective current signal.