Shogo Nishida

Speech recognition enhancement by lip information

Though technology in speech recognition has progressed recently, Automatic Speech Recognition (ASR) is vulnerable to noise. Lip-information is thought to be useful for speech recognition in noisy situations, such as in a factory or in a car.nThis paper describes speech recognition enhancement by lip-information. Two types of usage are dealt with. One is the detection of start and stop of speech from lip-information. This is the simplest usage of lip-information. The other is lip-pattern recognition, and it is used for speech recognition together with sound information. The algorithms for both usages are proposed, and the experimental system shows they work well. The algorithms proposed here are composed of simple image-processing. Future progress in image-processing will make it possible to realize them in real-time.

A Spatial Data Structure for the 3D Graphical Facility Management System

Abstract Geographical information systems (GISs) are now used extensively in the analysis of environmental data due to their capability to manage, manipulate, and display spatial data. However, most of the GIS applications (such as facility management system) possess data management structures that deal with only 2 dimentional space. The 3D system that enables users to explore the 3D space interactively and examine 3D spatial views of the environments would be very useful. In this paper, we propose a spatial data management method for a 3D graphical facility management system. Using this method, we have developed prototype 3D graphical management system that offers interacive operations with the 3D virtual city environments.

Knowledge acquisition driven by constructive and interactive induction

This paper describes the basic framework and the latest configuration of a knowledge acquisition system named KAISER. This system inductively learns classification knowledge in the form of a decision tree, and analyzes the results and the processes with domain and task specific knowledge to detect improper states. Then it asks suggestive questions to eliminate the improprieties and acquires new domain knowledge for the next induction cycle. One of the final objectives of this research is to frame a unified theory in the classification trees paradigm arguing: (1) what means to have a good/bad tree; (2) why it is good/bad; and (3) how to obtain a better one. To achieve this goal, KAISER has been enhanced with a meta-leamer named Meta-KAISER to accumulate the meta-knowledge by keeping track of the experts response of domain level interaction.

Autonomous Distributed Network Architecture for Control System

Abstract With the advance of information technology, control system is going to be a large and complex one. We believe that key technology to solve it is distribution and autonomy. In this paper autonomous network architecture and its software design method for distributed control systems, with such autonomous functions as fault tolerance, flexibility, evolvability, extensibility, and conversely, partitionability, etc., are discussed. First, a network architecture is described. Then, the design method of network software with autonomous functions for distributed control systems is discussed. Autonomy of the system is realized in the network software, which is separated from the application software. Finally, the proposed network architecture and its software is installed in the distributed computer system composed of INMOS Transputers. Its autonomous functions, that is fault tolerance, etc., and the performance of control are evaluated in the distributed system, when a sorting algorithm and simple model of the load frequency control are applied.

A Hypersimulation-Based Learning Environment: SIMPLE

Hypersimulator SIMPLE is a simulation-based learning environment (Fig. 1) to enhance operators understanding of dynamics of complex systems, such as electric power systems. The hypersimulator is literally a simulator fused with a concept of hypertext. Our system design approach is an interface-centered approach based on the characteristics of operators way of thinking and cognitive science.

An Approach to 3D Spacial Music Score

In this paper, we propose a spacial music score. Although many number of studies have been made on multimedia technology in the musical field over the past few decades, there is little attention to notation. The purpose of this paper is to construct more flexible and easily understandable visual music score for the music which is needed to be complicatedly controlled. The prototype system is developed for evalution, and it is confirmed that the user can make music easily by using the system.

Design of Coordinated Interfaces for Real-Time Decision Making in Hierachical Structures

This paper deals with a design of coordinated interfaces for real-time decision making in hierachical structures. Hierachical structures are often adopted to control or manage large scale real-time systems, such as power systems or transportation systems, where the whole problem is divided into small portion of sub-problems which can be managed by each member. In this paper, real-time problem solving in hierachical structures is analyzed first, and its process model is proposed. Then the coordinated interfaces are designed to support real-time decision making in hierachical structures on the basis of the process model. The coordinated interfaces are applied to the operation of power systems, and its results are evaluated.

A Case-Based Method To Support Creative Design Incorporating Intention Recognition

Abstract In this paper, we describe a method and a system to support a creative design process. This method is characterized by its ability to infer the designers intention based on case-based reasoning(CBR) methodology, so that the system can provide more useful and cooperative information on the current design.

An evaluation method of communication in a software development project and its application for diagnosis

Abstract A software development project becomes larger recently and it is difficult for the manager to understand problems of communication. This paper proposes a systematic evaluation method and the method is applied to a real project. The result of evaluation is thought to be useful to understand the communication problems in software development projects.

A knowledge acquisition inductive system driven by empirical interpretation of derived results

This paper describes the design philosophy of and current issues concerning a knowledge acquisition system namedkaiser. This system is an intelligent workbench for construction of knowledge bases for classification tasks by domain experts themselves. It first learns classification knowledge inductively from the examples given by a human expert, then analyzes the result and process based on abstract domain knowledge which is also given by the expert. Based on this analysis, it asks sophisticated questions for acquiring new knowledge. The queries stimulate the human expert and help him to revise the learned results, control the learning process and prepare new examples and domain knowledge. Viewed from an AI aspect, it aims at integrating similarity-based inductive learning and explanation-based deductive reasoning by guiding inductive inference with theoretical and/or heuristic knowledge about the domain. This interactive induce-evaluate-ask cycle produces a rational interview which promotes incremental acquisition of domain knowledge as well as efficient induction of operational and reasonable knowledge proved by the domain knowledge.