• DocumentCode
    1859929
  • Title

    Growing neural gas for information extraction in gesture recognition and reproduction of robot partners

  • Author

    Botzheim, Janos ; Kubota, Naoyuki

  • Author_Institution
    Grad. Sch. of Syst. Design, Tokyo Metropolitan Univ., Hino, Japan
  • fYear
    2012
  • fDate
    4-7 Nov. 2012
  • Firstpage
    149
  • Lastpage
    154
  • Abstract
    One of the great problems of the aging of society is the increased number of elderly people who live alone and separate from their children. Such elderly people often do not even experience daily conversation, and this can lead to cognitive decline and a high risk of dementia. Human-friendly robots can be used to support the mental and physical care for elderly people. Robotic conversation can activate the brain of such elderly people and improve their concentration and memory abilities. However, voice recognition is not enough in the daily conversation, the recognition of human gestures is also important in order to perform smooth communication. In this paper growing neural network is applied for information extraction in gesture recognition and reproduction by robot partners.
  • Keywords
    geriatrics; gesture recognition; human-robot interaction; medical computing; neural nets; speech recognition; cognitive decline; concentration ability; dementia; elderly people; human gesture recognition; human-friendly robots; information extraction; memory ability; neural gas; neural network; robot partners; robotic conversation; voice recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Micro-NanoMechatronics and Human Science (MHS), 2012 International Symposium on
  • Conference_Location
    Nagoya
  • Print_ISBN
    978-1-4673-4811-9
  • Type

    conf

  • DOI
    10.1109/MHS.2012.6492471
  • Filename
    6492471