Setsuo Ohsuga

Web Intelligence: Research and Development

This paper is about a new research field called Web Intelligence (WI for short). We try to explain the needs for coining the term as a sub-discipline of computer science for systematic studies on advanced Web related theories and technologies, as well as the design and implementation of Intelligent Web Information Systems (IWIS). Background information and related topics are discussed in an attempt to demonstrate why we consider WI to be a subject worthy of study and, at the same time, to establish a starting point for the further development of WI.

Web Intelligence (WI) Research Challenges and Trends in the New Information Age

This paper is about a new research field called Web Intelligence (WI for short). We try to explain the needs for coining the term as a sub-discipline of computer science for systematic studies on advanced Web related theories and technologies, as well as the design and implementation of Intelligent Web Information Systems (IWIS). Background information and related topics are discussed in an attempt to demonstrate why we consider WI to be a subject worthy of study and, at the same time, to establish a starting point for the further development of WI.

Toward intelligent CAD systems

Abstract Existing CAD systems cannot satisfy all the requirements of ‘real’ design. Many people would like to have more powerful and capable CAD systems. To achieve this goal, it is necessary to make CAD systems ‘intelligent’, because the limitations of current CAD systems result from the limitations inherent in the underlying conventional information processing technology. The conditions that allow systems to be considered as intelligent are discussed in the paper and some ideas are presented as to how to make such systems useful. The first half of the paper analyses why current conventional CAD systems are limited in their capabilities and consideration is given to overcoming these limitations. The author concludes that CAD systems must be ‘intelligent’ in the sense that they must be able to use knowledge dynamically to achieve the users goals. The conditions, key concepts and a possible approach are discussed with a view to designing an intelligent CAD system. The second half of the paper presents an implementation of an intelligent CAD system developed along the lines suggested. Some examples are given. The system is called KAUS and it shows a potential, once fully implemented, to aid the human designer that has not been achieved by conventional CAD systems.

Multi-layer logic—A predicate logic including data structure as knowledge representation language

A new generation computer is expected to be the knowledge processing system of the future. However, many aspects are yet unknown regarding this technology, and a number of fundamental concepts, directly concerning knowledge processing system design need investigation, such as knowledge, data, inference, communication, information management, learning, and human interface.These concepts are closely related to knowledge representation. In particular, methodology to materialize such concepts as above in computers are completely dependent upon them. Thus, knowledge representation is a key concept in the design of knowledge processing systems and, consequently, of new generation computer systems.Knowledge representation design is a very important task affecting the performance of new generation computer systems to be developed. We should first investigate the requirements for precise knowledge representation, considering its effects on system performance, then design knowledge representations to satisfy these requirements.This paper discusses (1) a new style of information processing, (2) requirements for knowledge representation and (3) a knowledge representation satisfying these requirements, a knowledge processing system designed on this basis and a new style of problem solving using this system.

Peculiarity Oriented Multi-database Mining

The paper proposes a way of mining peculiarity rules from multiply statistical and transaction databases. We introduce the peculiarity rules as a new type of association rules, which can be discovered from a relatively small number of the peculiar data by searching the relevance among the peculiar data. We argue that the peculiarity rules represent a typically unexpected, interesting regularity hidden in statistical and transaction databases. We describe how to mine the peculiarity rules in the multi-database environment and how to use the RVER (Reverse Variant Entity-Relationship) model to represent the result of multi-database mining. Our approach is based on the database reverse engineering methodology and granular computing techniques.

Framework of knowledge-based systems: Multiple meta-level architecture for representing problems and problem-solving processes

Abstract Currently available expert systems have a performance limit because of the lack of capability to describe problems and problem-solving methods. It is closely related with knowledge representation language, but this is not the only concern with this issue. Real world problems and problem-solving methods are not so simple as to be represented always in the same way by the same language. Their representations must be different depending on various factors involved in the problems themselves and the situations these problems are surrounded with. In this paper, the author discusses first the intrinsic nature of problem representation and problem-solving process representation. The requirements for and the conceptual framework of a knowledge-based system that is suited for dealing with various problems then become apparent quite naturally. The author asserts that a multiple meta-level architecture is necessary as well as a knowledge-representation language that can describe complex data structures as the basic framework of knowledge-based systems.

Using Rough Sets with Heuristics for Feature Selection

Practical machine learning algorithms are known to degrade in performance when faced with many features that are not necessary for rule discovery. To cope with this problem, many methods for selecting a subset of features with similar-enough behaviors to merit focused analysis have been proposed. In such methods, the filter approach that selects a feature subset using a preprocessing step, and the wrapper approach that selects an optimal feature subset from the space of possible subsets of features using the induction algorithm itself as a part of the evaluation function, are two typical ones. Although the filter approach is a faster one, it has some blindness and the performance of induction is not considered. On the other hand, the optimal feature subsets can be obtained by using the wrapper approach, but it is not easy to use because the complexity of time and space. In this paper, we propose an algorithm of using the rough set methodology with greedy heuristics for feature selection. In our approach, selecting features is similar as the filter approach, but the performance of induction is considered in the evaluation criterion for feature selection. That is, we select the features that damage the performance of induction as little as possible.

An incremental, probabilistic rough set approach to rule discovery

Introduces an incremental, probabilistic rough set approach to rule discovery in very large, complex databases with uncertainty and incompleteness. The approach is based on the combination of generalization distribution table (GDT) and rough set methodology. A GDT is a table in which the probabilistic relationships between concepts and instances over discrete domains are represented. By using a GDT as an hypothesis search space and combining the GDT with the rough set methodology, noises and unseen instances can be handled, biases can be flexibly selected, background knowledge can be used to constrain rule generation, and the rules with strengths can be effectively acquired from very large, complex databases in an incremental, bottom-up mode. We focus on basic concepts and an implementation of our methodology.

Discovering concept clusters by decomposing databases

Abstract This paper introduces an approach of discovering concept clusters by decomposing databases. This approach is the fundamental one for developing DBI which is one of sub-systems of the GLS discovery system implemented by us. A key feature of this approach is the formation of concept clusters or sub-databases through analysis and deletion t of noisy data in decomposing a database. Its development is based on the concept of Simon and Andos near-complete decomposability that has been most explicitly used in economic theory. In this approach, the process of discovering concept clusters from databases is a process based on incipient hypothesis generation and refinement, are many kinds of learning methods, in which the methods of data-driven and knowledge-driven are included, are cooperatively used in multiple learning phases, so that a more robust, general discovery system can be developed.

Peculiarity Oriented Mining and Its Application for Knowledge Discovery in Amino-Acid Data

The paper proposes a way of peculiarity oriented mining and its application for knowledge discovery in the amino-acid data set. We introduce the peculiarity rules as a new type of association rules, which can be discovered from a relatively small number of peculiar data by searching the relevance among the peculiar data. We argue that the peculiarity rules represent a typically unexpected, interesting regularity hidden in the amino-acid data set.