Myoelectric-controlled exoskeletal elbow robot to suppress essential tremor: Extraction of elbow flexion movement using STFTs and TDNN

Takeshi Ando, Masaki Watanabe, Keigo Nishimoto, Yuya Matsumoto, Masatoshi Seki, Masakatsu G. Fujie

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    Essential tremor is the most common of all involuntary movements. Many patients with an upper-limb tremor have serious difficulties in performing daily activities. We developed a myoelectric-controlled exoskeletal robot to suppress tremor. In this article, we focus on developing a signal processing method to extract voluntary movement from a myoelectric in which the voluntary movement and tremor were mixed. First, a Low-Pass Filter (LPF) and Neural Network (NN) were used to recognize the tremor patient's movement. Using these techniques, it was difficult to recognize the movement accurately because the myoelectric signal of the tremor patient periodically oscillated. Then, Short-Time Fourier Transformation (STFT) and NN were used to recognize the movement. This method was more suitable than LPF and NN. However, the recognition timing at the start of the movement was late. Finally, a hybrid algorithm for using both short and long windows' STFTs, which is a kind of "mixture of experts," was proposed and developed. With this type of signal processing, elbow flexion was accurately recognized without the time delay in starting the movement.

    Original languageEnglish
    Pages (from-to)141-149
    Number of pages9
    JournalJournal of Robotics and Mechatronics
    Volume24
    Issue number1
    Publication statusPublished - 2012 Feb

    Fingerprint

    Low pass filters
    Robots
    Neural networks
    Signal processing
    Time delay

    Keywords

    • EMG
    • Exoskeleton
    • Myoelectric signal
    • Tremor
    • Voluntary movement

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Computer Science(all)

    Cite this

    Myoelectric-controlled exoskeletal elbow robot to suppress essential tremor : Extraction of elbow flexion movement using STFTs and TDNN. / Ando, Takeshi; Watanabe, Masaki; Nishimoto, Keigo; Matsumoto, Yuya; Seki, Masatoshi; Fujie, Masakatsu G.

    In: Journal of Robotics and Mechatronics, Vol. 24, No. 1, 02.2012, p. 141-149.

    Research output: Contribution to journalArticle

    Ando, Takeshi ; Watanabe, Masaki ; Nishimoto, Keigo ; Matsumoto, Yuya ; Seki, Masatoshi ; Fujie, Masakatsu G. / Myoelectric-controlled exoskeletal elbow robot to suppress essential tremor : Extraction of elbow flexion movement using STFTs and TDNN. In: Journal of Robotics and Mechatronics. 2012 ; Vol. 24, No. 1. pp. 141-149.
    @article{5084bcb3ae6d4c8c861c93e54e44b96d,
    title = "Myoelectric-controlled exoskeletal elbow robot to suppress essential tremor: Extraction of elbow flexion movement using STFTs and TDNN",
    abstract = "Essential tremor is the most common of all involuntary movements. Many patients with an upper-limb tremor have serious difficulties in performing daily activities. We developed a myoelectric-controlled exoskeletal robot to suppress tremor. In this article, we focus on developing a signal processing method to extract voluntary movement from a myoelectric in which the voluntary movement and tremor were mixed. First, a Low-Pass Filter (LPF) and Neural Network (NN) were used to recognize the tremor patient's movement. Using these techniques, it was difficult to recognize the movement accurately because the myoelectric signal of the tremor patient periodically oscillated. Then, Short-Time Fourier Transformation (STFT) and NN were used to recognize the movement. This method was more suitable than LPF and NN. However, the recognition timing at the start of the movement was late. Finally, a hybrid algorithm for using both short and long windows' STFTs, which is a kind of {"}mixture of experts,{"} was proposed and developed. With this type of signal processing, elbow flexion was accurately recognized without the time delay in starting the movement.",
    keywords = "EMG, Exoskeleton, Myoelectric signal, Tremor, Voluntary movement",
    author = "Takeshi Ando and Masaki Watanabe and Keigo Nishimoto and Yuya Matsumoto and Masatoshi Seki and Fujie, {Masakatsu G.}",
    year = "2012",
    month = "2",
    language = "English",
    volume = "24",
    pages = "141--149",
    journal = "Journal of Robotics and Mechatronics",
    issn = "0915-3942",
    publisher = "Fuji Technology Press",
    number = "1",

    }

    TY - JOUR

    T1 - Myoelectric-controlled exoskeletal elbow robot to suppress essential tremor

    T2 - Extraction of elbow flexion movement using STFTs and TDNN

    AU - Ando, Takeshi

    AU - Watanabe, Masaki

    AU - Nishimoto, Keigo

    AU - Matsumoto, Yuya

    AU - Seki, Masatoshi

    AU - Fujie, Masakatsu G.

    PY - 2012/2

    Y1 - 2012/2

    N2 - Essential tremor is the most common of all involuntary movements. Many patients with an upper-limb tremor have serious difficulties in performing daily activities. We developed a myoelectric-controlled exoskeletal robot to suppress tremor. In this article, we focus on developing a signal processing method to extract voluntary movement from a myoelectric in which the voluntary movement and tremor were mixed. First, a Low-Pass Filter (LPF) and Neural Network (NN) were used to recognize the tremor patient's movement. Using these techniques, it was difficult to recognize the movement accurately because the myoelectric signal of the tremor patient periodically oscillated. Then, Short-Time Fourier Transformation (STFT) and NN were used to recognize the movement. This method was more suitable than LPF and NN. However, the recognition timing at the start of the movement was late. Finally, a hybrid algorithm for using both short and long windows' STFTs, which is a kind of "mixture of experts," was proposed and developed. With this type of signal processing, elbow flexion was accurately recognized without the time delay in starting the movement.

    AB - Essential tremor is the most common of all involuntary movements. Many patients with an upper-limb tremor have serious difficulties in performing daily activities. We developed a myoelectric-controlled exoskeletal robot to suppress tremor. In this article, we focus on developing a signal processing method to extract voluntary movement from a myoelectric in which the voluntary movement and tremor were mixed. First, a Low-Pass Filter (LPF) and Neural Network (NN) were used to recognize the tremor patient's movement. Using these techniques, it was difficult to recognize the movement accurately because the myoelectric signal of the tremor patient periodically oscillated. Then, Short-Time Fourier Transformation (STFT) and NN were used to recognize the movement. This method was more suitable than LPF and NN. However, the recognition timing at the start of the movement was late. Finally, a hybrid algorithm for using both short and long windows' STFTs, which is a kind of "mixture of experts," was proposed and developed. With this type of signal processing, elbow flexion was accurately recognized without the time delay in starting the movement.

    KW - EMG

    KW - Exoskeleton

    KW - Myoelectric signal

    KW - Tremor

    KW - Voluntary movement

    UR - http://www.scopus.com/inward/record.url?scp=84857323153&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84857323153&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:84857323153

    VL - 24

    SP - 141

    EP - 149

    JO - Journal of Robotics and Mechatronics

    JF - Journal of Robotics and Mechatronics

    SN - 0915-3942

    IS - 1

    ER -