ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
Search
Advanced search
OR
Browse
Search
22.33
Displaying 1-15 of 15 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • [title in Japanese]
    Article type: Cover
    Pages Cover1-
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_Cover1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (15K)
  • [title in Japanese]
    Article type: Index
    Pages Toc1-
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_Toc1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (63K)
  • The Facial Image Retrieval System Using Human Interaction
    Yoshinobu Takara, Satoshi Endo, Koji Yamada, Azuma Ouchi, Masaomi Oda
    Article type: Article
    Pages 1-6
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Facial image retrieval problem is one of te typical example of information processing based on sensibility. The main reason is that this problem has some difficulties about ambiguities of retrieval targets and non-determinateness of effective search-key. In this paper, we propose a facial image retrieval system with extended C4.5 algorithm as a retrieval mechanism. Some computer simulations are designed to investigate the performance of our system. The results of simulations represent that the our system shows good performance for the facial image retrieval problem.
    View full abstract
    Download PDF (689K)
  • Adaptive Feature Extraction by Using Gabor Filters and its Application to Facial Images
    Itaru Nagayama, Atsushi Murakami, Hiroyuki Fukushima, Tomio Takara
    Article type: Article
    Pages 7-12
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_7
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper discribes a basic concept and some experimental results on adaptive image processing for feature extraction ty using Gabor filters. Properties of the Gabor filter are controllable by its system parameters. We attempt to develop a new approach for adaptive feature extraction scheme using the Gabor filter and multiple regression analysis. The method is applied to face images to detect their facial features and its results are shown.
    View full abstract
    Download PDF (775K)
  • Performance Estimation of Resistors by Using Statistical Approaches
    Hirotaka HANEJI, Itaru NAGAYAMA, Tomio TAKARA
    Article type: Article
    Pages 13-18
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_13
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper describes a basic concept and some experimental results on performance estimation of resistors by using statistical approaches. We need to estimate deterioration of resistance used device in an electronic component to carry out appropriate maintenance of electronic circuit. We attempt to develop a new approach for performanceestimation of resistors using least square method and statistics model. These methods are applied to carbon filmed resistors to estimate their deterioration performance and its results are shown.
    View full abstract
    Download PDF (749K)
  • Automatic Speech Recognition by Evolution of Word Set
    Tomio Takara, Eiji Nagaki, Itaru Nagayama
    Article type: Article
    Pages 19-24
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_19
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Recently, automatic speech recognition method which determines the best structure of HMM by GA was proposed. Availability of the method has been shown. This method was extended to be a new method in which an individual was defined as a collection of the categories. However, better recognition structure was hard to be found because the rate of death-gene increased from one out of thirty in the former method to eleven in the extended method, then search area became narrow. Therefore we revise the method and adopt the death-gene removal algorithm. We show the result of our experiment showing the effectiveness of the revised method.
    View full abstract
    Download PDF (557K)
  • A study on composited picture of stereoscopic program production
    Mineo Bitoh, Tutomu Sina
    Article type: Article
    Pages 25-30
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_25
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    The problem in screen of a stereoscopic program, performed on editing or switching of program work, was examined. By composited picture, since two or more images which differ in their parametersexist in the same screen, if the parameters of the images which constitute a composed picture does not have adjustment, and unpleasant feeling will be given to an observer.Then by screen composition, examined the influence on vision and a mutual restriction which are caused by the difference in the parameters of the images to compound.
    View full abstract
    Download PDF (817K)
  • Real-Time Composition of Stereo Images for Mixed Reality
    Masayuki Kanbara, Takashi Okuma, Haruo Takemura, Naokazu Yokoya
    Article type: Article
    Pages 31-36
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_31
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper describes a video see-through mixed reality system with stereo cameras. In a mixed reality system. exact registration of real and virtual environments is a very important issue. The system estimates camera parameters from three markers whose position are unknown in image sequences captured by stereo cameras mounted on a HMD. In addition, the system calculates the depth of a hand in the images, and generates the composed image in which the hand correctly occludes virtual objects.
    View full abstract
    Download PDF (1089K)
  • Dynamic Positioning Method Using Neural Network
    Tadashi Tamashiro, Satoshi Endo, Koji Yamada
    Article type: Article
    Pages 37-42
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_37
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    One of the important issues in intelligent systems and robotics is to develop an efficient method to control multi-agent system. In order to work the multi-agent system well as the problem solver, it's so significant to create cooperative behaviors among the agents. In the multi-agent system, the behaviors of cooperation emerged as the results of suitable position learning by each agent. In this paper, we design dynamic positioning method based on the Neural network and Competitive co-evolution model further more We applied this method to Soccer Server.
    View full abstract
    Download PDF (825K)
  • Potential Field for Multiagent System in Dynamic Environment
    Hirotaka Yamashiro, Takahiro Yokoyama, Koji Yamada, Satoshi Endo
    Article type: Article
    Pages 43-48
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_43
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper shows a dynamic environment model for multiagent system using potential field method. In this model, agents and its working space are defined by potential fields. Then this model can represent a multiple restriction problem by the potential interaction. In this paper, a pursuer agent as typical multiagent system is constructed by potential functions. And, pursuit simulator of potential field model is presented.
    View full abstract
    Download PDF (679K)
  • Study of Combinatorial Optimization Algorithm Based on Immune System
    Naruaki Toma, Satoshi Endo, Koji Yamada
    Article type: Article
    Pages 49-54
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_49
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    The immune system is one of the adaptive biological system whose functions are to identify and to eliminate foreign material. Applying this system to the engineering problems, these processes are regard as the effective search and optimization. In this paper, we propose an optimization algorithm based on immune system with two memory mechanisms. The one is used to change search scope effectivly and the other is used to solve similar problems repeatedly. Some computer simulations are designed to investigate the performance of the immune algorithm. The rsults of simulations represent that the immune algorithm shows good performance for TSP.
    View full abstract
    Download PDF (780K)
  • An Agreement for the Multi-Asent System Using Focal Point Technique
    Ryo Taira, Koji Yamada, Satoshi Endo
    Article type: Article
    Pages 55-60
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_55
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In this paper, we discuss an automatic programing for game strategy acquisition using genetic programming (GP). This paper shows an implementation of MOO game. MOO is a guessing game. In this game, the codemaker picks a number consisting of three distinct decimal digits. Then the codebreaker guesses tree distinct digits being scored on each guess. We show and evaluate the codebreaker program that is created automatically by the GP. Genetic Programming, game strategy, MOO, Hit Blow
    View full abstract
    Download PDF (625K)
  • An Agreement for the Multi-Agent System Using Focal Point Technique
    Satoru Yonaha, Satoshi Endo, Koji Yamada
    Article type: Article
    Pages 61-66
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_61
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In order to process a task by several agents, each agent must behave systematically. And there is an agreement issue for suitable decision making in multi-agent system. In real world, it is difficult to communicate to other agent because of noise or limited sensor. Focal points is a technique of sharing information without specified communication between multiple autonomous agents. For example, real soccer players can often do contactless passing and know where the teammate goes on the next situation as focal points. In this paper, we describe that acquisition and search of focal point using reinforcement learning method in order to process a cooperative task in multi-agent environment like a soccer.
    View full abstract
    Download PDF (685K)
  • Fundamental Monograph in Multi Agent System
    Takuya Maeda, Satoshi Endo, Koji Yamada
    Article type: Article
    Pages 67-72
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_67
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper shows a traffic light control model using a concept of iterated prisoner's dilemma (IPD). A traffic flow is controlled by traffic lights. It is to be desired that the light should be controlled according to the traffic conditions. The light should be controlled according to the traffic of each direction. Then each light get into the dilemma condition that which direction should be passed. Consequently, to avoid the traffic jam, cooperation of each traffic light in the city is required. First in this paper, traffic light control problem is explained. Then multiagent of IPD is applied to this. Finally, control model is discussed by computer simulation.
    View full abstract
    Download PDF (573K)
  • [title in Japanese]
    Article type: Appendix
    Pages App1-
    Published: June 19, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.33.0_App1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (75K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top