Abstract: A analog data neural network processing system is provided in which there is a self optimization capability that varies the signal processing factors in response to a detected contrast in the system output patterns. The system provides feedback type guidance in varying such processing factors as sampling rate, frame length, signal transformation, neural network vigilance and architecture, each in a direction that will maximize or minimize the contracts with patterns used to train the network. The processing system is useful in all signal classification tasks.

Abstract: An autonomous device behaving adaptively to a user includes a sensing unit; a recognition unit for recognizing user's command, a current user-related status, and a current user-unrelated status based on the sensed signals; a pseudo-personality-forming unit for establishing a pseudo-personality based on the result of the preceding recognition; a pseudo-emotion-forming unit for establishing pseudo-emotions based on the result of the preceding recognition and the pseudo-personality; an autonomous behavior-establishing unit for selecting autonomous behavior based on the result of the preceding recognition, the pseudo-personality, and the pseudo-emotions; a new behavior pattern generation unit for generating new patterns of autonomous behavior, linked to the autonomous behavior-establishing unit; a commanded behavior-establishing unit for constituting commanded behavior in accordance with the user's command; a behavior control unit for controlling behavior by combining the autonomous behavior and the com

Abstract: An adaptive fuzzy feature mapping (AFFM) technique provides a method for identifying and matching a new data pattern against a set of known data patterns using a combination of distance measurements and fuzzy logic functions. Known data patterns are stored as organized nodes in a pattern map wherein each organized node is defined by one or more attribute coefficients. As distance measurement is computed between a new data pattern and each organized node of the pattern map using distance measurement wherein the organized node having the smallest distance measurement to the new data pattern receives the highest ranking. Traversing the organized nodes according to the ranking, the new data pattern is compared to each organized node using fuzzy logic functions. If the new data pattern matches an organized node based on an acceptable degree of fuzziness, the attribute coefficients of the organized node are updated to reflect those coefficients of the new data pattern.

Abstract: According to an aspect of the disclosed invention, characteristic portions of graphic images to be used for machining in the form of profiles of a plurality of templates are first registered in advance along with machining design data corresponding to the respective profiles of the templates and including machining methods adapted to the respective profiles of the templates in the form of template machinings. Then, a specific characteristic portion is extracted out of the graph image given for a machining operation and the extracted characteristic portion is collated with each of the registered template profiles. Thereafter, the template machinings for the template profile recognized to be corresponding to the extracted characteristic portion as a result of the collation are read out from the registered data.

Abstract: An improved expert system is disclosed wherein rules are organized into domains and subdomains, and objects are passed to rules to be operated upon. Prior to operating upon any object, the domain determines if the object is of the type which is to be operated upon by rules within the rule domain. If not, the rules are not applied to the object.

Abstract: A method for building a model of a system includes first extracting data from a historical database (310). Once the data is extracted, a dataset is then created, which dataset involves the steps of preprocessing the data. This dataset is then utilized to build a model. The model is defined as a plurality of transforms which can be utilized to run an on-line model. This on-line model is interfaced with the historical database such that the variable names associated therewith can be downloaded to the historical database. This historical database can then be interfaced with a control system to either directly operate the plant or to provide an operator an interface to various predicted data about the plant. The building operation will create the transform list and then a configuration step is performed in order to configure the model to interface with the historical database. When the dataset was extracted, it is unknown whether the variables names are still valid.

Abstract: The subject of the present invention is to cause an agent to smoothly respond to an user's request to utilize an agent function of accessing software more effectively than in the prior art. An agent computer block 16 selects an appropriate one of a plurality of agents corresponding to an accessing user on the basis of an agent table where the plurality of agents are recorded from voice data provided by an input/output interface computer block 15, reads out from a storage device 17 agent set information on the selected agent, transfers this set information to the input/output interface computer block 15, displays the selected agent's peculiar figure (mainly, face) on a display device 13 in accordance with the agent set information, and outputs from a voice output device 11 a message in the agent's peculiar voice.

Abstract: We describe an efficient algorithm for evaluating the (weighted bipartite graph of) associations between two sets of data with gaussian error, e.g., between a set of measured state vectors and a set of estimated state vectors. First a general method is developed for determining, from the covariance matrix, minimal d-dimensional error ellipsoids for the state vectors which always overlap when a gating criterion is satisfied. Circumscribing boxes, or d-ranges, for the data ellipsoids are then found and whenever they overlap the association probability is computed. For efficiently determining the intersections of the d-ranges a multidimensional search tree method is used to reduce the overall scaling of the evaluation of associations. Very few associations that lie outside the predetermined error threshold or gate are evaluated. Empirical testing for variously distributed data in both three and eight dimensions indicate that the scaling is significantly reduced from N2, where N is the size of the data set.

Abstract: The invention relates to a method of handling event recordings in a service database system. The database contains measurement tables (MT) which include consecutive rows (Ri). A single row contains data about a single measurement object. So that recording of a large counter group could be performed efficiently and, nonwithstanding, the measurement could be started without delay for all objects, (a) a single measurement counter is maintained copied to N copies on the row corresponding to each measurement object of the measurement table (b) time domain is divided into consecutive recording intervals so that only the values of a selected counter group located on the row are incremented during each recording interval, and (c) the recording and zeroing of the counter values is handled during a recording interval one measurement object at a time.

Abstract: A device and a method for creation of emotions are provided for an interface of information, such as an artificial agent and a personified agent, intervened between a human being (i.e., user) and an electronic apparatus. For instance, an emotion creating device is configured by a neural network, a behavior determination engine and a feature determination engine. The neural network inputs user information, representing conditions of the user, and apparatus information, representing conditions of the apparatus, so as to produce emotional states. Herein, a present set of emotional states are produced in consideration of a previous set of emotional states. The emotional states represent prescribed emotions such as pleasure, anger, sadness and surprise. The behavior determination engine refers to a behavior determination database using the user information and the emotional states of the neural network so as to determine a behavior of the interface.

Abstract: The fuzzy inference circuit includes a sensor sensing a state of a control object, and a charge coupled device storing fuzzy rule function values for at least one fuzzy rule function. The charge coupled device further performs a fuzzy inference on output of the sensor using the fuzzy rule function values to generate a control signal for controlling the control object.

Abstract: A method and apparatus for training and operating a neural network using gated data. The neural network is a mixture of experts that performs “soft” partitioning of a network of experts. In a specific embodiment, the technique is used to detect malignancy by analyzing skin surface potential data. In particular, the invention uses certain patient information, such as menstrual cycle information, to “gate” the expert output data into particular populations, i.e., the network is soft partitioned into the populations. An Expectation-Maximization (EM) routine is used to train the neural network using known patient information, known measured skin potential data and correct diagnosis for the particular training data and patient information. Once trained, the neural network parameters are used in a classifier for predicting breast cancer malignancy when given the patient information and skin potentials of other patients.

Abstract: An adaptive run-time controller is used to adjust the run-time of a fabrication and assembly process simulation model based on inputs generated by outside forces. The run-time controller utilizes fuzzy logic to evaluate the outside forces against existing control rules to determine new simulation run-times based upon this evaluation. The run-time controller then analyzes and adjusts the existing control rules based on current, historical and trend data. The new rules are integrated into the run-time controller to accurately reflect the current status of the fabrication and assembly process for subsequent simulation runs. As such, the run-time controller inputs and evaluates outside forces that were impossible or impracticable to integrate in the simulation model.

Abstract: A neuroprocessor architecture employs a combination of bit-serial and serial-parallel techniques for implementing the neurons of the neuroprocessor. The neuroprocessor architecture includes a neural module containing a pool of neurons, a global controller, a sigmoid activation ROM look-up-table, a plurality of neuron state registers, and a synaptic weight RAM. The neuroprocessor reduces the number of neurons required to perform the task by time multiplexing groups of neurons from a fixed pool of neurons to achieve the successive hidden layers of a recurrent network topology.

Abstract: An improved method and system for training and classifying using a low complexity and high accuracy multiresolutional polynomial classifier (412) is presented. A method of training an multiresolutional polynomial classifier which reduces the complexity of existing classifiers allows models representing subgroups of classes to easily be created. The models which represent subgroups of classes are applied to an unidentified input to produce a coarse classification of the unidentified input using a low order classifier. Once a coarse classification of the unidentified input is performed, a more detailed classification is performed using another low complexity classifier.

Abstract: An interface that allows a surgeon to remotely control surgical devices and conditions of an operation room. The surgeon views a video image that is displayed by a monitor. The monitor may be coupled to a video device such as a laparoscopic camera that is attached to the end of an endoscope. Static graphic images and a dynamic graphic cursor are overlayed onto the video image. The graphic cursor has a pixel location on the monitor which corresponds to a spatial location of a pointer signal. The pointer signal is transmitted by a transmitter worn on the head of the surgeon. The pointer signal may be a laser which is directed to a screen that is located adjacent to a detection camera. The surgeon may move the graphic cursor relative to the video image by tilting his head and varying the spatial location of the pointer signal. The interface may have a controller which generates output signals in response to the movement of the pointer signal.

Abstract: A robotic system that moves a surgical instrument in response to the actuation of a foot pedal that can be operated by the foot of a surgeon. The robotic system has an end effector that is adapted to hold a surgical instrument such as an endoscope. The end effector is coupled to a robotic arm assembly which can move the endoscope relative to the patient. The system includes a computer which controls the movement of the robotic arm in response to input signals received from the foot pedal.

Abstract: A robot includes an obstacle sensing mechanism for sensing an angle formed between a first wall and a forward travel direction of the robot. The robot then travels parallel to the first wall while the obstacle sensing mechanism senses a front distance of the robot from a wall located in front of the robot and sideward distances of the robot from walls located to respective sides of the robot. In response to the sensing of changes in the sideward distances, the robot is able to divide the area into separate cells which together define an environmental map of the area. That map is stored in the robot's memory.

Abstract: A method employing fuzzy logic for identifying a detected object in LADAR data is disclosed. The method includes extracting a feature of the object; determining a confidence level in the extracted feature; comparing the extracted feature to a corresponding feature of a potential identification using a fuzzy logic process, and identifying the object. The comparison includes weighting at least one rule according to the confidence level in the extracted feature employed by the rule; shifting a membership function for the extracted feature responsive to the confidence level for the extracted feature; and executing the fuzzy logic process to obtain an indication of whether the segmented object corresponds to the potential identification.

Abstract: In a cooperative reasoning apparatus comprises a plurality of problem solving units for cooperatively solving various problems and replication unit for replicating a corresponding problem solving unit in responsive to a replication request from one of the plurality of problem solving units, each problem solving unit determines whether or not its own reasoning unit has an ability of reasoning a given problem. If NO, the problem solving unit requests another problem solving unit to solve the problem. Further, each problem solving unit determines whether or not its own reasoning unit is performing reasoning of another problem. If YES, the problem solving unit requests the replication unit to replicate the problem solving unit, so that the problem is solved by the replicate.