Recognition of outer muscle's EMG and Inner muscle's EMG using support vector machine (recognition of abduction and external rotation movements of shoulder joint)

Takeshi Ando, Masakatsu G. Fujie

    Research output: Contribution to journalArticle

    Abstract

    There have been some studies of exoskeletal robots to support upper limb motion. However, it is difficult to support internal/external rotation, one of 3 DOF in the shoulder joint. This is because the internal/external rotation is performed by the activities of the rotator cuff, which consists of deep layer muscles. In other words, it is difficult to recognize the surface electromyogram (SEMG) signals, which are generated at muscles far from the skin. In this paper, our aim is to quantify the different characteristics in the SEMG between the surface layer and deep layer muscles and apply different characteristics to the discrimination of the external rotation under the experimental evaluation with twelve young subjects. Three kinds of parameters, such as Zero Crossing, MPF and coefficient of the approximate function, were selected to express the characteristic of high frequency component in the EMG signal. Specifically, the classification was shown to be 97% successful by applying two features to Support Vector Machine (SVM). Hence, it is almost possible to assume that either the deep or the surface muscle is active and discriminate the motions which their muscles involve.

    Original languageEnglish
    Pages (from-to)297-303
    Number of pages7
    JournalNihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
    Volume76
    Issue number762
    Publication statusPublished - 2010 Feb

    Fingerprint

    Support vector machines
    Muscle
    Skin
    Robots

    Keywords

    • Emg signal
    • Medical and welfare assistance
    • Muscle and skelton
    • Pattern recognition
    • Shoulder joint
    • Support vector machine

    ASJC Scopus subject areas

    • Mechanical Engineering
    • Mechanics of Materials
    • Industrial and Manufacturing Engineering

    Cite this

    @article{6db6787b90c54ebfbdcab4cc4622bba3,
    title = "Recognition of outer muscle's EMG and Inner muscle's EMG using support vector machine (recognition of abduction and external rotation movements of shoulder joint)",
    abstract = "There have been some studies of exoskeletal robots to support upper limb motion. However, it is difficult to support internal/external rotation, one of 3 DOF in the shoulder joint. This is because the internal/external rotation is performed by the activities of the rotator cuff, which consists of deep layer muscles. In other words, it is difficult to recognize the surface electromyogram (SEMG) signals, which are generated at muscles far from the skin. In this paper, our aim is to quantify the different characteristics in the SEMG between the surface layer and deep layer muscles and apply different characteristics to the discrimination of the external rotation under the experimental evaluation with twelve young subjects. Three kinds of parameters, such as Zero Crossing, MPF and coefficient of the approximate function, were selected to express the characteristic of high frequency component in the EMG signal. Specifically, the classification was shown to be 97{\%} successful by applying two features to Support Vector Machine (SVM). Hence, it is almost possible to assume that either the deep or the surface muscle is active and discriminate the motions which their muscles involve.",
    keywords = "Emg signal, Medical and welfare assistance, Muscle and skelton, Pattern recognition, Shoulder joint, Support vector machine",
    author = "Takeshi Ando and Fujie, {Masakatsu G.}",
    year = "2010",
    month = "2",
    language = "English",
    volume = "76",
    pages = "297--303",
    journal = "Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",
    issn = "0387-5024",
    publisher = "Japan Society of Mechanical Engineers",
    number = "762",

    }

    TY - JOUR

    T1 - Recognition of outer muscle's EMG and Inner muscle's EMG using support vector machine (recognition of abduction and external rotation movements of shoulder joint)

    AU - Ando, Takeshi

    AU - Fujie, Masakatsu G.

    PY - 2010/2

    Y1 - 2010/2

    N2 - There have been some studies of exoskeletal robots to support upper limb motion. However, it is difficult to support internal/external rotation, one of 3 DOF in the shoulder joint. This is because the internal/external rotation is performed by the activities of the rotator cuff, which consists of deep layer muscles. In other words, it is difficult to recognize the surface electromyogram (SEMG) signals, which are generated at muscles far from the skin. In this paper, our aim is to quantify the different characteristics in the SEMG between the surface layer and deep layer muscles and apply different characteristics to the discrimination of the external rotation under the experimental evaluation with twelve young subjects. Three kinds of parameters, such as Zero Crossing, MPF and coefficient of the approximate function, were selected to express the characteristic of high frequency component in the EMG signal. Specifically, the classification was shown to be 97% successful by applying two features to Support Vector Machine (SVM). Hence, it is almost possible to assume that either the deep or the surface muscle is active and discriminate the motions which their muscles involve.

    AB - There have been some studies of exoskeletal robots to support upper limb motion. However, it is difficult to support internal/external rotation, one of 3 DOF in the shoulder joint. This is because the internal/external rotation is performed by the activities of the rotator cuff, which consists of deep layer muscles. In other words, it is difficult to recognize the surface electromyogram (SEMG) signals, which are generated at muscles far from the skin. In this paper, our aim is to quantify the different characteristics in the SEMG between the surface layer and deep layer muscles and apply different characteristics to the discrimination of the external rotation under the experimental evaluation with twelve young subjects. Three kinds of parameters, such as Zero Crossing, MPF and coefficient of the approximate function, were selected to express the characteristic of high frequency component in the EMG signal. Specifically, the classification was shown to be 97% successful by applying two features to Support Vector Machine (SVM). Hence, it is almost possible to assume that either the deep or the surface muscle is active and discriminate the motions which their muscles involve.

    KW - Emg signal

    KW - Medical and welfare assistance

    KW - Muscle and skelton

    KW - Pattern recognition

    KW - Shoulder joint

    KW - Support vector machine

    UR - http://www.scopus.com/inward/record.url?scp=77952271865&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77952271865&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:77952271865

    VL - 76

    SP - 297

    EP - 303

    JO - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

    JF - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

    SN - 0387-5024

    IS - 762

    ER -