• Title/Summary/Keyword: Fuzzy Max-Min neural network

Search Result 32, Processing Time 0.016 seconds

On-line Motion Control of Avatar Using Hand Gesture Recognition (손 제스터 인식을 이용한 실시간 아바타 자세 제어)

  • Kim, Jong-Sung;Kim, Jung-Bae;Song, Kyung-Joon;Min, Byung-Eui;Bien, Zeung-Nam
    • Journal of the Korean Institute of Telematics and Electronics C
    • /
    • v.36C no.6
    • /
    • pp.52-62
    • /
    • 1999
  • This paper presents a system which recognizes dynamic hand gestures on-line for controlling motion of numan avatar in virtual environment(VF). A dynamic hand gesture is a method of communication between a computer and a human being who uses gestures, especially both hands and fingers. A human avatar consists of 32 degree of freedom(DOF) for natural motion in VE and navigates by 8 pre-defined dynamic hand gestures. Inverse kinematics and dynamic kinematics are applied for real-time motion control of human avatar. In this paper, we apply a fuzzy min-max neural network and feature analysis method using fuzzy logic for on-line dynamic hand gesture recognition.

  • PDF

Development of Gas Measurement System for the Harmful Gases at Livestock Barn (축산생육환경 유해가스 모니터링을 위한 무선가스측정시스템 개발)

  • Kim, Young Wung;Paik, Seung Hyun;Park, Hong Bae
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.49 no.9
    • /
    • pp.314-321
    • /
    • 2012
  • Harmful gases which are generated from various rout at growth environment of livestock ban have a direct and indirect bad influence to the livestock and farmers, and also step-up breeding density and long-term exposure to the sealed environment of winter can be fatal. In this paper, we propose a gas measurement system for monitoring gases of ammonia, hydrogen sulfide, volatile organic compounds, etc. which arise from the muck. The measurement system consist of both wireless gas sensor node and gas recognition software using a Fuzzy Min-Max neural network. To evaluate the performance of suggested system, gas measurement experiments are performed in laboratory environment by using the designed wireless gas sensor node. And we show the performance through classification test for the target gases by the designed gas recognition software.