Abstract: The invention concerns a method for determining competing risks for objects following an initial event based on previously measured or otherwise objectifiable training data patterns, in which several signals obtained from a learning capable system are combined in an objective function in such a way that said learning capable system is rendered capable of detecting or forecasting the underlying probabilities of each of the said competing risks.

Abstract: A method is described for improving the prediction accuracy and generalization performance of artificial neural network models in presence of input-output example data containing instrumental noise and/or measurement errors, the presence of noise and/or errors in the input-output example data used for training the network models create difficulties in learning accurately the nonlinear relationships existing between the inputs and the outputs, to effectively learn the noisy relationships, the methodology envisages creation of a large-sized noise-superimposed sample input-output dataset using computer simulations, here, a specific amount of Gaussian noise is added to each input/output variable in the example set and the enlarged sample data set created thereby is used as the training set for constructing the artificial neural network model, the amount of noise to be added is specific to an input/output variable and its optimal value is determined using a stochastic search and optimization technique, namely, gen

Abstract: The invention involves generating and presenting, typically electronically, a number of design alternatives to persons who are participating in the design, selection, or market research exercise. The participants (referred to as “selectors”) transmit data indicative of their preferences among or between the presented design alternatives, and that data is used to derive a new generation of design alternatives or proposals. The new designs are generated through the use of a computer program exploiting a genetic or evolutionary computational technique. The process is repeated, typically for many iterations or cycles.

Abstract: A hybrid cascade Model-Based Predictive control (MBPC) and conventional control system for thermal processing equipment of semiconductor substrates, and more in particular for vertical thermal reactors is described. In one embodiment, the conventional control system is based on a PID controller. In one embodiment, the MBPC algorithm is based on both multiple linear dynamic mathematical models and non-linear static mathematical models, which are derived from the closed-loop modeling control data by using the closed-loop identification method. In order to achieve effective dynamic linear models, the desired temperature control range is divided into several temperature sub-ranges. For each temperature sub-range, and for each heating zone, a corresponding dynamic model is identified. During temperature ramp up/down, the control system is provided with a fuzzy control logic and inference engine that switches the dynamic models automatically according to the actual temperature.

Abstract: A reconfigurable digital processing system for space includes the utilization of field programmable gate arrays utilizing a hardware centric approach to reconfigure software processors in a space vehicle through the reprogramming of multiple FPGAs such that one obtains a power/performance characteristic for signal processing tasks that cannot be achieved simply through the use of off-the-shelf processors. In one embodiment, for damaged or otherwise inoperable signal processors located on a spacecraft, the remaining processors which are undamaged can be reconfigured through changing the machine language and binary to the field programmable gate arrays to change the core processor while at the same time maintaining undamaged components so that the signal processing functions can be restored utilizing a RAM-based FPGA as a signal processor.

Abstract: Methods are provided for developing medical diagnostic tests using decision-support systems, such as neural networks. Patient data or information, typically patient history or clinical data, are analyzed by the decision-support systems to identify important or relevant variables and decision-support systems are trained on the patient data. Patient data are augmented by biochemical test data, or results, where available, to refine performance. The resulting decision-support systems are employed to evaluate specific observation values and test results, to guide the development of biochemical or other diagnostic tests, too assess a course of treatment, to identify new diagnostic tests and disease markers, to identify useful therapies, and to provide the decision-support functionality for the test.

Abstract: One aspect of the invention is the construction of mixtures of Bayesian networks. Another aspect of the invention is the use of such mixtures of Bayesian networks to perform inferencing. A mixture of Bayesian networks (MBN) consists of plural hypothesis-specific Bayesian networks (HSBNs) having possibly hidden and observed variables. A common external hidden variable is associated with the MBN, but is not included in any of the HSBNs. The number of HSBNs in the MBN corresponds to the number of states of the common external hidden variable, and each HSBN is based upon the hypothesis that the common external hidden variable is in a corresponding one of those states. In one mode of the invention, the MBN having the highest MBN score is selected for use in performing inferencing.

Abstract: An apparatus and method for controlling trajectory of an object (47) to a first predetermined position. The apparatus has an input layer (22) having nodes (22a-22f) for receiving input data indicative of the first predetermined position. First weighted connections (28) are connected to the nodes of the input layer (22). Each of the first weighted connections (28) have a coefficient for weighting the input data. An output layer (26) having nodes (26a-26e) connected to the first weighted connections (28) determines trajectory data based upon the first weighted input data. The trajectory of the object is controlled based upon the determined trajectory data.

Abstract: In an analysis of a set of discrete multidimensional data which can be represented in an array with a topology, where the array that can be mapped to an image space of discrete elements, such as digitized image data, seismic data and audio data, genotype/phenotype classifications are imposed on the topology, and then molecular biological-like processes (annealing, fragmentation, chromatographic separation, fingerprinting, footprinting and filtering) are imposed upon that topology to perceive classifiable regions such as edges. More specifically, an image feature probe constructed of strings of contiguous image fragments of the class of N-grams called linear N-grams, anneals genotypes of topological features by complementary biological-like techniques in the same manner that complex biological systems are analyzed by genetic mapping, sequencing and cloning techniques. For example, molecular biological probes anneal with molecular biological genotypes and then are used to classify those genotypes.

Abstract: A non-linear dynamic predictive device (60) is disclosed which operates either in a configuration mode or in one of three runtime modes: prediction mode, horizon mode, or reverse horizon mode. An external device controller (50) sets the mode and determines the data source and the frequency of data. In prediction mode, the input data are such as might be received from a distributed control system (DCS) (10) as found in a manufacturing process; the device controller ensures that a contiguous stream of data from the DCS is provided to the predictive device at a synchronous discrete base sample time. In prediction mode, the device controller operates the predictive device once per base sample time and receives the output from the predictive device through path (14). In horizon mode and reverse horizon mode, the device controller operates the predictive device additionally many times during base sample time interval. In horizon mode, additional data is provided through path (52).

Abstract: A controller for a switched reluctance machine utilizing a feedforward neural network in combination with either a fuzzy logic controller or a proportional-integral controller to provide output control signals (e.g., turn-ON angle, turn-OFF angle and peak current) for controlling the energization of a switched reluctance machine. In an alternate embodiment, a fuzzy logic controller is utilized by itself to control a switched reluctance machine.

Abstract: Neural computing techniques are used to optimize route selection in a communication network, such as an ATM network. Output measurements of the network are used to provide optimal routing selection and traffic management. Specifically, link data traffic is monitored in the network to obtain traffic history data. An autoregressive backpropagation neural network is trained using the traffic history data to obtain respective predicted traffic profiles for the links. Particular links are then selected for carrying data based on the predicted traffic profiles. A cost function, limits on network parameters such as link cost and cell rate, and other quality of service factors are also considered in selecting the optimal route.

Abstract: One aspect of the invention is the construction of mixtures of Bayesian networks. Another aspect of the invention is the use of such mixtures of Bayesian networks to perform inferencing. A mixture of Bayesian networks (MBN) consists of plural hypothesis-specific Bayesian networks (HSBNs) having possibly hidden and observed variables. A common external hidden variable is associated with the MBN, but is not included in any of the HSBNs. The number of HSBNs in the MBN corresponds to the number of states of the common external hidden variable, and each HSBN is based upon the hypothesis that the common external hidden variable is in a corresponding one of those states. In one mode of the invention, the MBN having the highest MBN score is selected for use in performing inferencing.

Abstract: An iterative method enabling a request plan to be established for an observation satellite. A plan consists in a succession of requests which are associated with pluralities of opportunities for satisfying said requests. The plan must also comply with a plurality of constraints. Each iteration k of the iterative method is made up of the following steps: new opportunity is selected; a provisional plan is derived from the preceding plan k-1 as calculated in-the preceding iteration, and from the new opportunity; provisional plan is verified for compliance with said plurality of constraints; the quality of said provisional plan is evaluated; and it is determined whether the provisional plan should be confirmed as plan k as a function of the quality of said provisional plan and of the quality of said preceding plan k-1.

Abstract: An artificial neural network-based system and method for determining desired concepts and relationships within a predefined field of endeavor, including a neural network portion, which neural network portion includes an artificial neural network that has been previously trained in accordance with a set of given training exemplars, a monitor portion associated with the neural network portion to observe the data outputs produced by the previously trained artificial neural network, and a perturbation portion for perturbing the neural network portion to effect changes, subject to design constraints of the artificial neural network that remain unperturbed, in the outputs produced by the neural network portion, the perturbation portion operable such that production of an output by the neural network portion thereafter effects a perturbation of the neural network portion by the perturbation portion, the monitor portion responsive to detection of the data outputs being produced by the previously trained neural networ

Abstract: A multi-user system for creating and maintaining a knowledge base is implemented on a variety of computer systems, including single-user personal computers, networked personal computers, and data communications networks, including the Internet. The system has a graphic user interface which can be easily learned by non-programmers. The knowledge base is displayed as a hierarchical multiplicity of nodes, in which each node is related to one or more superior nodes. Title of text, rules, references, and attributes associated with each node are displayed, and may be modified. Simulation is used to verify the knowledge base once generated. Data may be extracted from the bases in the form of hard-copy books, databases for downloading into Web browsers, and databases for downloading into hand-held computers including a multiplicity of grids, and a multiplicity of branches in the form of a logic tree.

Abstract: Matching (e.g., via correlation or similarity process) entities having attributes, some of which have associated values. The values of the attributes may be adjusted based on number of entities that have values for a particular attribute so that the values decrease as the number increases. The attributes of the entities may be harmonized and provided with default values so that entities being matched have common attributes defined by the union of the attributes of the entities being matched. The attributes of the entities may be expanded and provided with default values so that the entities being matched have attributes that neither had originally. Match values may be normalized to provide a weight value which may be used to predict an attribute value of a new entity based on known attribute values of known entities. The weight values may be tuned such that relatively high weights are amplified and relatively low weights are suppressed.

Abstract: A system and method are disclosed for partitioning a real-value windowed attribute into ranges, wherein the values within each range generally correspond to a particular class of results associated with runs of a process. The system and method determines a low range having attribute values generally corresponding to a first class, a middle range having attribute values generally corresponding to a second class, and an upper range having attribute values generally corresponding to the first class. The system and method may be used in a system that produces an induction tree useful in developing an indication of a cause of a particular result of a process from values associated with at least one real-valued, windowed attribute that arises during the runs of the process.

Abstract: The fuzzy filtering of a noise signal comprising a plurality of signal samples [s(t,k)] is carried out using as variables the variation of the signal in the considered window and the distance of the samples from a sample to be reconstructed, to distinguish the typical variations of the original signal from those due to the noise and to identify the signal fronts. The method comprises the steps of defining a current signal sample [s(t)] from among the plurality of signal samples, calculating a plurality of difference samples [D(t,k)] as the difference in absolute value between the current signal sample and each signal sample and defining distance values (k) between the current signal sample and each signal sample.

Abstract: A system for interfacing a human user to a data processor which receives inputs from the user and includes associated storage resource information. The data processor generates outputs to the user and associated output devices. The interface system includes structure for receiving a statement generated by the human user in natural language on a word-by-word basis. The system analyzes the statement to identify a subject and object and searches the stored resource information for data related to the identified subject. Output devices are provided for generating to the user the data from the stored resource information related to the identified subject.