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

    Fingerprint

    Macros
    Neural networks
    Time delay
    Muscle
    Pneumatics
    Rubber
    Bone
    Robots

    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

    Cite this

    Micro macro neural network to recognize rollover movement. / Ando, Takeshi; Okamoto, Jun; Fujie, Masakatsu G.

    In: Advanced Robotics, Vol. 25, No. 1-2, 01.01.2011, p. 253-271.

    Research output: Contribution to journalArticle

    Ando, Takeshi ; Okamoto, Jun ; Fujie, Masakatsu G. / Micro macro neural network to recognize rollover movement. In: Advanced Robotics. 2011 ; Vol. 25, No. 1-2. pp. 253-271.
    @article{fe4fe4206b5b46c49b4e13b7607c73d7,
    title = "Micro macro neural network to recognize rollover movement",
    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.",
    keywords = "motion recognition, Neural network, rollover, trunk orthosis and cancer bone metastasis",
    author = "Takeshi Ando and Jun Okamoto and Fujie, {Masakatsu G.}",
    year = "2011",
    month = "1",
    day = "1",
    doi = "10.1163/016918610X538570",
    language = "English",
    volume = "25",
    pages = "253--271",
    journal = "Advanced Robotics",
    issn = "0169-1864",
    publisher = "Taylor and Francis Ltd.",
    number = "1-2",

    }

    TY - JOUR

    T1 - Micro macro neural network to recognize rollover movement

    AU - Ando, Takeshi

    AU - Okamoto, Jun

    AU - Fujie, Masakatsu G.

    PY - 2011/1/1

    Y1 - 2011/1/1

    N2 - 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.

    AB - 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.

    KW - motion recognition

    KW - Neural network

    KW - rollover

    KW - trunk orthosis and cancer bone metastasis

    UR - http://www.scopus.com/inward/record.url?scp=78650112094&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=78650112094&partnerID=8YFLogxK

    U2 - 10.1163/016918610X538570

    DO - 10.1163/016918610X538570

    M3 - Article

    AN - SCOPUS:78650112094

    VL - 25

    SP - 253

    EP - 271

    JO - Advanced Robotics

    JF - Advanced Robotics

    SN - 0169-1864

    IS - 1-2

    ER -