Micro macro neural network to recognize rollover movement

Takeshi Ando, Jun Okamoto, Masakatsu G. Fujie

    Research output: Contribution to journalArticle

    6 Citations (Scopus)

    Abstract

    Many motion support robots for the elderly and disabled have been studied all over the world. We have developed a rollover support system (rollover is one of the activities of daily living). Our ultimate goal is to develop an effective rollover support system for patients with cancer bone metastasis. The core of this system is a pneumatic rubber muscle that is operated by electromyogram (EMG) signals from the trunk muscle. Thr traditional neural network, the time delay neural network (TDNN), used to recognize movement shares the problems of response delay and false recognition. In this paper, we proposed a new neural network, called the micro macro neural network (MMNN), to recognize the rollover movement earlier and with more accuracy. The MMNN is composed of a micro part, which detects rapid changes in the strength of the EMG signal, and a macro part, which detects the tendency of the EMG signal to continually increase or decrease. As a result, recognition using the MMNN with an optimized structure is 40 ± 49 ms faster than recognition using the TDNN. Additionally, the number of false recognitions using the MMNN is one-third of that using the TDNN.

    Original languageEnglish
    Pages (from-to)253-271
    Number of pages19
    JournalAdvanced Robotics
    Volume25
    Issue number1-2
    DOIs
    Publication statusPublished - 2011 Jan 1

    Keywords

    • motion recognition
    • Neural network
    • rollover
    • trunk orthosis and cancer bone metastasis

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Human-Computer Interaction
    • Computer Science Applications
    • Hardware and Architecture
    • Software

    Fingerprint Dive into the research topics of 'Micro macro neural network to recognize rollover movement'. Together they form a unique fingerprint.

  • Cite this