Abstract: A method and system for patient generation and evolution for a computer-based testing system and/or expert system. One or more belief networks, which describe parallel health state networks are accessed by a user or a computer. A knowledge base, at least in part, is scripted from the one or more belief networks by the computer. A model patient at least in part, is instantiated by the computer from the scripted knowledge base. Optionally, the model patient is evolved by the computer in accordance with the parallel health state networks and responsive to a received course of action.

Abstract: A human-computer interface system and methods for providing intelligent, adaptive, multimodal interaction with users while accomplishing tasks on their behalf in some particular domain or combination of domains. Specifically, this system accepts user input via natural language text, mouse actions, human speech, whistles, gestures, pedal movements, facial or postural changes, and conveys results via natural language text, automatically-generated speech, and displays of graphs, tables, animation, video, and mechanical and chemical effectors that convey heat, tactile sensation, taste and smell.

Abstract: A Collection Knowledge System provides context-sensitive knowledge delivery services to application programs, thereby enabling application programs to effectively support variant computational processes. In operation, a Collection Knowledge System receives knowledge requests from application programs, performs local and remote lookups into structured trees of knowledge, and returns requested knowledge to requesting application programs. Collection Knowledge Systems can manage knowledge for entire variant computational processes, thereby enabling application programs to calculate and execute many variant computational processes in fully automated, scalable ways that were not previously possible. As a consequence of automated process construction and execution, associated human labor costs are effectively reduced to zero.

Abstract: A robotic system which controls the movement of a surgical instrument in response to voice commands from the user. The robotic system has a computer controlled arm that holds the surgical instrument. The user provides voice commands to the computer through a microphone. The computer contains a phrase recognizer that matches the user' speech with words stored in the computer. Matched words are then processed to determine whether the user has spoken a robot command. If the user has spoken a recognized robot command the computer will move the robotic arm in accordance with the command.

Abstract: Sensors are selected from a sensor network for tracking of at least one target. The sensors are selected using a genetic algorithm construct having n chromosomes, wherein each chromosome represents one sensor, defining a fitness function based on desired attributes of the tracking, selecting one or more of the individuals for inclusion in an initial population, executing a genetic algorithm on the initial population until defined convergence criteria are met, wherein execution of the genetic algorithm has the steps of choosing the fittest individual from the population, choosing random individuals from the population and creating offspring from the fittest and randomly chosen individuals. In one embodiment, only i chromosomes are mutated during any one mutation, wherein i has a value of from 2 to n?1.

Abstract: Systems and methods are discussed that allow profile information to be reused by various versions of a program. One illustrative aspect includes a method for comparing versions of a program in binary format. The method includes finding equivalent contents in portions of two versions of the program, finding equivalent structure in the portions of the two versions, and forming a match when a portion of one of the two versions is an equivalence of a portion of the other of the two versions.

Abstract: A prosthetic system may use a decoder to predict an intended action, such as a reach, from processed signals generated from measured neural activity. The decoder may included a cognitive state machine, which transitions between cognitive states based on transition rules.

Abstract: A method and apparatus are disclosed for recommending items of interest by fusing a plurality of recommendation scores from individual recommendation tools using one or more Radial Basis Function neural networks. The Radial Basis Function neural networks include N inputs and at least one output, interconnected by a plurality of hidden units in a hidden layer. A unique neural network can be used for each user, or a neural network can be shared by a plurality of users, such as a set of users having similar characteristics. A neural network training process initially trains each Radial Basis Function neural network using data from a training data set. A neural network cross-validation process selects the Radial Basis Function neural network that performs best on the cross-validation data set. A neural network program recommendation process uses the selected neural network(s) to recommend items of interest to a user.

Abstract: The Neuron network modeling compares neuron behavior in terms of electrical properties to predict the propagation of capacitative, or inductive current/potential along a nerve fiber. Membrane ion channels act as capacitor-inductor circuits, similar to a radio receiver and transmitter. Therefore, a single circuit, including the membrane capacitor, the ion channel, inductors and resistors, nerve fibers, neurons, and the whole CNS may be modeled as radio receivers and transmitters A speech process for the hearing impaired is disclosed as one example embodiment.

Abstract: A method (100) for cascading system level target to component level design objectives using machine learning and design synthesis techniques. The method (100) of the present invention uses machine learning techniques to build (106, 108) surrogate models from given system targets (102). The method then employs design synthesis methods to determine (110) a range of component level design objectives for the given system level targets using the surrogate models. The range of component level design objectives is fed back (112) to one of the surrogate models to determine (114) the component design objectives.

Abstract: A chaotic signal generator includes a set of elements connected together for generating chaotic signals. The connection scheme may correspond to the circuit generally referred to as Chua's circuit, particularly when implemented as a cellular neural network. Interposed in the connection scheme is at least one switch, such as a MOS transistor. Opening and closing of the switch causes variation in the chaotic dynamics of the generated signals. A command signal applied to the switch may correspond to a modulating signal for transmission on a channel, such as a high noise channel. The modulating signal may be a binary signal, and the command signal may be a switching signal having a frequency that increases or decreases depending on the logic level of the binary signal.

Abstract: A computer-aided method and apparatus to access information is disclosed. According to one embodiment, the apparatus includes a selector, a mapper and a generator. Through the selector, a person can select concepts and/or elements in the concepts. The mapper maps the selected concepts and elements to an inquiry. Then, the generator generates a response to the inquiry. The response can remain the same, independent of the order of the concepts selected by the person.

Abstract: A knowledge management database system and method for building such a system relies on input from various subject matter experts to review and validate the structure of the database (in terms of substantive subject matter areas included in the database, their definitions, focus) and the various items stored in the database. The review and validation renders the database as “easy to use” by a novice in the particular situation, allowing that user to easily navigate through the database system and find a response to a particular issue or problem. Such a database management system is particularly useful in a large organization, or one with rapid turnover in certain jobs, allowing a user who may be unfamiliar with various aspects of a particular issue to readily find the relevant information.

Abstract: A nonlinear signal mapper that can implement any continuous one-to-one nonlinear map of baseband or intermediate-frequency digital signals. The mapping method follows a “divide-and-conquer” approach in that a nonlinear map to be implemented is piecewise decomposed into a set of simpler nonlinear component maps. The component maps are implemented using code-enabled feed-forward neural networks (FF-NNs). Each code-enabled feed-forward neural network only operates on samples of a digital input signal that lie in a specified interval of the real-valued number line. Code-enabled FF-NNs are controlled by codewords produced by a scalar quantization encoder. The quantization encoder also controls a multiplexer that directs values produced by the FF-NNs to the nonlinear mapper's output.

Abstract: In an automatic decision-making system, a method and a tool for the reduction of the dimension of data mining, which is automatically coupled to an empirical predictor of the system. The method includes a qualitative modeling of the interrelations between various objects whose attributes are relevant to a score made by the predictor according to which decisions are made, wherein this relevancy is determined by an input of a domain expert to the problem in hand. The model is called a Knowledge-Tree and its conclusions are represented by a graphical symbolization called the Knowledge-Tree map. Data mining, which follows the construction of the Knowledge-Tree map regards only datasets which are associated with logical and validated branches of the knowledge tree. Because the expert input which reduces the dimension of data mining was completed prior to data mining, interception by human reasoning is not needed after data mining and the decision making process can proceed automatically.

Abstract: Methods and systems for finding a low rank approximation for an m×n matrix A are described. The described embodiments can independently sample and/or quantize the entries of an input matrix A, and can thus speed up computation by reducing the number of non-zero entries and/or their representation length. The embodiments can be used in connection with Singular Value Decomposition techniques to greatly benefit the processing of high-dimensional data sets in terms of storage, transmission and computation.

Abstract: A computer implemented method and apparatus for simulating an intelligent tutor for interactive adaptive training of learners in any domain includes a Domain Module, a Tutor Module and an Interface. Items to be learned, and their prerequisite and other dependency relationships are represented in a fuzzy graph, together with a fuzzy logic computational engine, which dynamically adapts the available sequence of training actions (such as presentations/explanations, simulations, exercises and tasks/questions) to a current assessment of the learner's knowledge skill, the level of difficulty of the presented material, and preferences and learning style of the individual learner. Fuzzy logic is used as the basis of arc weightings, and the computations, but the general methodology is applicable to other approaches to weighting in computation.

Abstract: A method for assessing a condition of an organism having body waves corresponding to states of the organism. The method includes the step of recording signals corresponding to a body wave, output by a portion of the organism in a first state, to provide a first record. In a similar manner, signals are recorded during a time period in which the organism is in a second state, to provide a second record. The first and second records, are processed by applying feature expansion procedures thereto. The results of the feature expansion procedures are evaluated to identify first selected feature expansion procedures effective to distinguish values of the first signals corresponding to the first state from values of the first signals corresponding to the second state.

Abstract: A neural network system including a plurality of tiers of interconnected computing elements. The plurality of tiers includes an input tier whereto a sequence of input speech vectors is applied at a first rate. Two of the plurality of tiers are interconnected through a decimator configured to reduce the first rate of the sequence of input vectors. Alternatively, two of the plurality of tiers are interconnected through an interpolator configured to increase the first rate of the sequence of input vectors.

Abstract: A membership function unit includes a membership function setting section for adjusting positions or shapes of membership functions depending on inputs of elements influencing human senses so as to set the membership functions and a membership value computing section for computing membership function values associated with input variables in the membership functions attained by the membership function setting section. The invention also relates to a fuzzy control system development support apparatus. The invention also relates to a method of developing a fuzzy control system.