Katsunori Shimohara

EMG pattern analysis and classification by neural network

It is proposed that electromyographic (EMG) patterns can be analyzed and classified by neural networks for EMG-controlled prosthetic members. The thrust of this work is that neural networks make EMG pattern recognition much easier and more efficient; thus, use of EMG control in a prosthetic arm/hand would involve much less physical and mental effort on the part of the subject. The FFT-analyzed pattern for a one-channel surface EMG of the flexor digitorium superficialis can be recognized by the standard back-propagation neural network. Classification of the five finger movements based on the recognition of their patterns is successfully accomplished.<<ETX>>

Development and Evolution of Hardware Behaviors

A new system is proposed towards the computational frame-work of evolutionary hardware that adaptively changes its structure and behavior according to the environment. In the proposed system, hardware specifications, which produce hardware structures and behaviors, are automatically generated as Hardware Description Language (HDL) programs. Using a rewriting system, the system introduces a program development process, that imitates the natural development process from pollinated egg to adult and gives the HDL-program flexible evolvability. Also discussed is a method to evolve the language itself by modifying the corresponding rewriting system. This method is intended to serve as hierarchal mechanism of evolution and to contribute to the evolvability of large-scale hardware. Although this papers discussion is mainly involves in HDL-programs because our goal is hardware evolution, the techniques described here are applicable to ordinary computer programs written in such conventional formats as “C” language.

EEG topography recognition by neural networks

Electroencephalography (EEG) pattern-recognition studies were carried out using EEG topography (readiness potential, or RP, spatiotemporal patterns) generated the moment before voluntary movements of muscles. RPs generated prior to pronouncing syllables and controlling a joystick were studied by experiments and simulation. The spatiotemporal patterns of RPs were measured by multichannel surface electrodes pasted on the subjects scalp. Backpropagation neural networks were used for RP pattern recognition. The results show that RPs generated prior to syllable pronouncement contain some information about those syllables, and that RPs generated prior to joy stick movements contain information on the direction of intended movement. They also show that neural networks can be used to recognize EEG information and so create a new type of man-machine interface for data input.<<ETX>>

Numerical analysis of a thin-film waveguide by mode-matching method

A new numerical analysis is proposed to investigate accurately the propagation characteristics of a dielectric thin-film waveguide, and its algorithm is presented. In this method, the Rayleigh principle previously used in conventional mode-matching techniques is extended to the Fourier transform of the wave field in the boundary-value problem for an unbounded object. Successful numerical results for dispersion relations and field distributions in a rib waveguide are obtained in detail, accompanied by their error estimations. The propagation characteristics, including field distributions in an optical rib waveguide, are investigated precisely for several geometries, and it is confirmed that the mode-matching method is accurate and effective for numerical analysis, not only with bounded objects, but also with unbounded objects such as thin-film waveguides in integrated optics.

Production genetic algorithms for automated hardware design through an evolutionary process

Production genetic algorithms is proposed to enable grammar structure as well as hardware description language (HDL) programs to evolve, toward an automated hardware design system through an evolutionary process. Evolutionary computation and methods make it possible to design hardware that works in unknown and non-stationary environments without explicit design knowledge. In the proposed system, hardware specifications, which produce circuit behaviors, are automatically generated as HDL programs according to the grammar defined as in a rewriting system and then evolve through production genetic algorithms (PGAs), also proposed here. The PGAs introduce new chromosome representation and genetic operators to create self-genesis mechanisms in hardware design similar to living systems. An experimental result shows that through an evolutionary process based on the PGAs, a hardware specification program expands its circuit scale and as a result increases its functionality.<<ETX>>

EMG pattern recognition by neural networks for multi fingers control

This paper proposes that EMG patterns can be analyzed and classified by neural networks. Through experiments and on-line simulations, it Is demonstrated that recognition of not only finger movement but also joint angles in continuously finger movement, based on EMG patterns, can be successfully accomplished. We also demonstrate a EMG controlled 5 fingers 10 joints robot hand.

Personal telephone services using IC-cards

An IC-card is a memory card that can be substituted for existing magnetic-striped cards. It is suggested that the IC-card, which can store various information for telephone calls, will become a useful device in multifunction telephone sets because of its portability, security, and large memory capacity. The information that should be stored on an IC-card is discussed, and the practicality of creating personal telephone services by combining telephone services with the stored user information is addressed. An experimental telephone set with an IC-card reader/writer developed to verify feasibility is presented. Service grades of IC-cards, according to their level of functionality versus the functionality of the terminal equipment, are discussed.<<ETX>>

An Analysis of Two-Parent Recombinations for Real-Valued Chromosomes in an Infinite Population

This paper concerns recombinations which produce offspring from two parents. We assume an infinite population and regard recombinations as transformations of stochastic variables represented as chromosomes. We then formalize recombinations with the probability density functions of stochastic variables represented as the parameters and describe the change of the probability density functions of chromosomes before and after recombination. Our formalization includes various proposed recombinations, such as multi-point, uniform, and linear crossover, as well as BLX-. We also derive certain properties of the operators, such as diversification and decorrelation.

Making Organizational Learning Operational: Implications from Learning Classifier Systems

The concepts of organizational learning in organization and management science cover a very wide range of organization-related activities in organization. Since socially situated intelligence is one of such activities, this paper makes the concept of organizational learning operational from the computational viewpoint for investigating socially situated intelligence. In particular, this paper focuses on the characteristics of multiagent learning as one kind of socially situated intelligence, and analyzes them using four operationalized learning mechanisms in organizational learning. A careful investigation on the characteristics of multiagent learning has revealed the following implications: (1) there are two levels in the learning mechanisms for multiagent learning (the individual level and organizational level) and each mechanism is divided into two types (single- and double-loop learning). The integration of these four learning mechanisms improves socially situated intelligence; and (2) the following properties support socially situated intelligence: (a) different dimensions in learning mechanisms, (b) interaction among various levels and types of learning mechanisms in addition to interaction among agents, and (c) combination of exploration at an individual level and exploitation at an organizational level.

AdAM: a hardware evolutionary system

AdAM (Adaptive Architecture Methodology) is a hardware evolutionary system making electronic circuits autonomously acquire required functionalities. Among the systems aiming for this same goal, this system is unique in building up a system-oriented methodology rather than a device-oriented technique; AdAM is designed to be a high-level behavior-oriented evolutionary system framework with an extremely high operation/evolution speed. This paper overviews the architecture of the AdAM system and investigates the methodology used in the system. Some research projects based on AdAM are also presented.