Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
Online ISSN : 1881-7203
Print ISSN : 1347-7986
ISSN-L : 1347-7986
Volume 16 , Issue 5
Showing 1-22 articles out of 22 articles from the selected issue
Regular
Original Papers
  • Toshiaki NONAKA, Yasunori ENDO, Hiroshi YOSHIKAWA
    Type: Article
    2004 Volume 16 Issue 5 Pages 431-440
    Published: October 15, 2004
    Released: May 29, 2017
    JOURNALS FREE ACCESS
    From the viewpoint of safety and noise reduction, the study on anti-lock braking systems of rolling stock is very important. But, the skid of wheels of rolling stock is strongly uncertain phenomenon so that it is too hard to control it and there are no general guides to construct anti-lock braking systems. By the way, it is well-known that fuzzy reasoning is available to controlled systems with strong uncertainty. Thus, we can consider that fuzzy reasoning is also available to braking systems of rolling stock. In this paper, we propose a new anti-lock braking system with fuzzy reasoning for rolling stock in order to shorten braking distance. The proposed system can realize not only shortening of braking distance but also reduction of calculational volume and facilitation of tuning. Moreover, we show that the proposed system can shorten braking distance through numerical simulation.
    Download PDF (1135K)
  • Takashi YAMAMOTO, Hisao ISHIBUCHI
    Type: Article
    2004 Volume 16 Issue 5 Pages 441-451
    Published: October 15, 2004
    Released: May 29, 2017
    JOURNALS FREE ACCESS
    In This paper, we examine the performance of heuristic methods for rule weight specification in fuzzy rule-based classification systems. First we describe two existing rule weight specification methods using the terminology in data mining. We explain fuzzy versions of two measures of association rules in data mining: confidence and support. Next we propose two heuristic methods for rule weight specification. Diffierences among the four heuristic methods are visually demonstrated through computer simulations on an artificial test problem. Then we examine the classification performance of fuzzy rule-based systems designed by each weight specification method through computer simulations on six real world data sets. Simulation results show that the proposed two heuristic methods clearly outperform the existing ones. Finally we show that a small number of simple fuzzy rules with rule weights, which are selected by a genetic algorithm, have high interpretability and high classification ability.
    Download PDF (1183K)
  • Kohei NOMOTO, Kozo SHIMA, Masaharu WAKAMATSU, Yutaka SHIMIZU
    Type: Article
    2004 Volume 16 Issue 5 Pages 452-462
    Published: October 15, 2004
    Released: May 29, 2017
    JOURNALS FREE ACCESS
    Though NC (Numerical Control) manufacturing tool is an automated machine, the efficiency of the manufacturing work is strongly affected by check and supervision before unmanned operation. Since the worker should maintain the efficiency and should find out undesirable motion at the same time, attention allocation is an important skill for him. This paper shows an analysis of the way of paying attention during program check. The authors carried out an experiment with subjects and observed to which parts of the program each worker paid much attention. Next, these program parts were characterized by attribute parameters and were classified into types. Since every worker's judgments, whether he payed much attention or not to the particular type, were always consistent, the relation between every worker's way of paying attention and each attribute parameter was obtained. Then, three axes characterized each worker's way of paying attention by quantification theory type III. The first axis was the balance between attention to the hole process and attention to immediate action, the second axis was the degree of paying attention to logical reasoning, and the third axis was tendency to demand the efficiency. Finally, every worker's way of paying attention was mapped into a space consisted of the second axis and the third axis and its position meant his level of skill and feature of skill. The result of this analysis makes it possible to provide novice workers with training that fits their abilities and demands of business.
    Download PDF (1399K)
  • Masaaki OHKITA, Yoshinobu SUGANO, Tomoyuki MIYANO, Makoto OHKI
    Type: Article
    2004 Volume 16 Issue 5 Pages 463-471
    Published: October 15, 2004
    Released: May 29, 2017
    JOURNALS FREE ACCESS
    This paper presents a method of obstacle detection using a SOM-based template matching approach. The SOM is the clustering technique with the training function. By the training of the SOM, the resemble images with several images taken from the working environment of the robot are generated, where the resulting image database is called the template image set. The detection of the obstacles is implemented within a preliminary divided region in front of the camera on the robot. On the obstacle detection, the query image taken from the environment is compared with the template images using a simple matching algorithm in order to determine the template image associated with it. By carrying out the template matching, it is clarified that the presence and the location of an obstacle can be determined within an accuracy in a use of a mobile robot. Our approach is tested by a number of experimentations in an indoor environment setting.
    Download PDF (1272K)
feedback
Top