Abstract: In a system for optically performing position detection and data communication, a transmitting apparatus has first and second light-emitting elements for position indication and data transmission. An image sensing element in a receiving apparatus senses the light-emitting elements. Position is detected from the sensed image of the first light-emitting elements using triangulation, and data communication is performed by blinking the second light-emitting element. This system is used in a hospital where the use of radio waves is restricted or outerspace where the system is exposed to strong electromagnetic waves.

Abstract: An autonomic system for updating a fuzzy neural network includes a process of calculating an estimated value based on fuzzy inference by using a neural network structure, wherein a parameter to be adjusted or identified by fuzzy inference and outputted from the neural network is made to correspond to coupling loads which are updated by learning, i.e., fuzzy rules and membership functions are adjusted by learning. This system is characterized in that the addition and deletion of fuzzy rules are conducted based on changes in output errors in an autonomic manner, thereby effectively obtaining appropriate numbers of fuzzy rules optimal for an object such as a vehicle engine having strong non-linearity. Fuzzy rules are formed by a combination of membership functions representing variables such as an engine speed and a throttle angle.

Abstract: A micro computer, constituting a signature recognition apparatus, comprises an automatic signature creating section, a data extracting section, a recognition network section, a retrieval section, and a memory section. The data extracting section creates personal data representing a plurality of personal characteristics or features based on an input signature. The recognition network section selects the data to be used for evaluation from the personal data representing personal characteristics or features, and executes an evaluation of thus chosen data. The retrieval section, using the genetic algorithm, finds out a combination pattern having preferable evaluation result. Accordingly, in recognizing signatures, it becomes possible to know beforehand what kind of personal characteristics or features data should be utilized for the recognition of the given signatures, thereby increasing the accuracy in the recognition.

Abstract: A signature recognition apparatus reduces the volume of training data needed and shortens the learning period. In the apparatus, a sample generating section generates sample data. A coupling load coefficient is determined based on the sample data, thereby obviating the need for additional sample data. The apparatus also uses a fuzzy net which implements a linear function in its output layer to shorten the learning period relative to the learning period required for a net implementing a non-linear function such as a sigmoid.

Abstract: An information medium recognition device for recognizing an information medium such as a handwritten signature inputted by performing an online input operation. The information medium recognition device is provided with an input portion for inputting the information medium (e.g.

Abstract: An information medium recognition device for recognizing an information medium such as a handwritten signature inputted by performing an offline input operation. The information medium recognition device is provided with a detection portion for scanning the information medium in different scanning directions and for detecting a stroke density corresponding to each of the scanning directions, an inference portion for converting the stroke density into a compressed fuzzy density by performing a fuzzy inference process on the stroke density corresponding to each scanning direction, which is detected by the detection portion, and a judgement portion for judging from the fuzzy density corresponding to each scanning direction whether or not the information medium is genuine.