Optimal design of a Micro macro neural network to recognize rollover movement

Takeshi Ando, Jun Okamoto, Masakatsu G. Fujie

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    4 Citations (Scopus)

    Abstract

    Many motion support robots of the elderly and disable were studies all over the world. We have developed the rollover support system, which is one of the ADL. 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 EMG signals from the trunk muscle. A Time Delay Neural Network (TDNN) is the traditional method for recognizing EMG signals. However, response delay and false recognition are the problem of the traditional neural network. We previously proposed a new neural network, called the Micro-Macro Neural Network (MMNN), to recognize the rollover movement earlier and with more accuracy than is possible with TDNN. 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. However, the methodology to determine the structure of the MMNN was not established. In this paper, the optimal structure of the MMNN is determined. A comparison of each of the 360 sets of test times of MMNN versus TDNN was done. These results showed that recognition using MMNN is 40 (msec) (S.D. 49) faster than recognition using TDNN. Additionally, the number of false recognitions using MMNN is one-third of that using TDNN. By comparing the output using only the Micro part and Macro part in MMNN, it was found that the combination of quick response of the Micro part and stable recognition of the Macro part are advantages of MMNN. In the future, we plan to test the effectiveness of the total system in clinical tests with cancer patients in terminal care.

    Original languageEnglish
    Title of host publication2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
    Pages1615-1620
    Number of pages6
    DOIs
    Publication statusPublished - 2009 Dec 11
    Event2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 - St. Louis, MO
    Duration: 2009 Oct 112009 Oct 15

    Other

    Other2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
    CitySt. Louis, MO
    Period09/10/1109/10/15

    Fingerprint

    Macros
    Neural networks
    Time delay
    Optimal design
    Muscle
    Pneumatics
    Rubber
    Bone
    Robots

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction
    • Control and Systems Engineering

    Cite this

    Ando, T., Okamoto, J., & Fujie, M. G. (2009). Optimal design of a Micro macro neural network to recognize rollover movement. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 (pp. 1615-1620). [5354540] https://doi.org/10.1109/IROS.2009.5354540

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

    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 1615-1620 5354540.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ando, T, Okamoto, J & Fujie, MG 2009, Optimal design of a Micro macro neural network to recognize rollover movement. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009., 5354540, pp. 1615-1620, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, MO, 09/10/11. https://doi.org/10.1109/IROS.2009.5354540
    Ando T, Okamoto J, Fujie MG. Optimal design of a Micro macro neural network to recognize rollover movement. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 1615-1620. 5354540 https://doi.org/10.1109/IROS.2009.5354540
    Ando, Takeshi ; Okamoto, Jun ; Fujie, Masakatsu G. / Optimal design of a Micro macro neural network to recognize rollover movement. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. pp. 1615-1620
    @inproceedings{b57ad3092422401e96988acf4663b241,
    title = "Optimal design of a Micro macro neural network to recognize rollover movement",
    abstract = "Many motion support robots of the elderly and disable were studies all over the world. We have developed the rollover support system, which is one of the ADL. 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 EMG signals from the trunk muscle. A Time Delay Neural Network (TDNN) is the traditional method for recognizing EMG signals. However, response delay and false recognition are the problem of the traditional neural network. We previously proposed a new neural network, called the Micro-Macro Neural Network (MMNN), to recognize the rollover movement earlier and with more accuracy than is possible with TDNN. 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. However, the methodology to determine the structure of the MMNN was not established. In this paper, the optimal structure of the MMNN is determined. A comparison of each of the 360 sets of test times of MMNN versus TDNN was done. These results showed that recognition using MMNN is 40 (msec) (S.D. 49) faster than recognition using TDNN. Additionally, the number of false recognitions using MMNN is one-third of that using TDNN. By comparing the output using only the Micro part and Macro part in MMNN, it was found that the combination of quick response of the Micro part and stable recognition of the Macro part are advantages of MMNN. In the future, we plan to test the effectiveness of the total system in clinical tests with cancer patients in terminal care.",
    author = "Takeshi Ando and Jun Okamoto and Fujie, {Masakatsu G.}",
    year = "2009",
    month = "12",
    day = "11",
    doi = "10.1109/IROS.2009.5354540",
    language = "English",
    isbn = "9781424438044",
    pages = "1615--1620",
    booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

    }

    TY - GEN

    T1 - Optimal design of a Micro macro neural network to recognize rollover movement

    AU - Ando, Takeshi

    AU - Okamoto, Jun

    AU - Fujie, Masakatsu G.

    PY - 2009/12/11

    Y1 - 2009/12/11

    N2 - Many motion support robots of the elderly and disable were studies all over the world. We have developed the rollover support system, which is one of the ADL. 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 EMG signals from the trunk muscle. A Time Delay Neural Network (TDNN) is the traditional method for recognizing EMG signals. However, response delay and false recognition are the problem of the traditional neural network. We previously proposed a new neural network, called the Micro-Macro Neural Network (MMNN), to recognize the rollover movement earlier and with more accuracy than is possible with TDNN. 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. However, the methodology to determine the structure of the MMNN was not established. In this paper, the optimal structure of the MMNN is determined. A comparison of each of the 360 sets of test times of MMNN versus TDNN was done. These results showed that recognition using MMNN is 40 (msec) (S.D. 49) faster than recognition using TDNN. Additionally, the number of false recognitions using MMNN is one-third of that using TDNN. By comparing the output using only the Micro part and Macro part in MMNN, it was found that the combination of quick response of the Micro part and stable recognition of the Macro part are advantages of MMNN. In the future, we plan to test the effectiveness of the total system in clinical tests with cancer patients in terminal care.

    AB - Many motion support robots of the elderly and disable were studies all over the world. We have developed the rollover support system, which is one of the ADL. 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 EMG signals from the trunk muscle. A Time Delay Neural Network (TDNN) is the traditional method for recognizing EMG signals. However, response delay and false recognition are the problem of the traditional neural network. We previously proposed a new neural network, called the Micro-Macro Neural Network (MMNN), to recognize the rollover movement earlier and with more accuracy than is possible with TDNN. 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. However, the methodology to determine the structure of the MMNN was not established. In this paper, the optimal structure of the MMNN is determined. A comparison of each of the 360 sets of test times of MMNN versus TDNN was done. These results showed that recognition using MMNN is 40 (msec) (S.D. 49) faster than recognition using TDNN. Additionally, the number of false recognitions using MMNN is one-third of that using TDNN. By comparing the output using only the Micro part and Macro part in MMNN, it was found that the combination of quick response of the Micro part and stable recognition of the Macro part are advantages of MMNN. In the future, we plan to test the effectiveness of the total system in clinical tests with cancer patients in terminal care.

    UR - http://www.scopus.com/inward/record.url?scp=76249115035&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=76249115035&partnerID=8YFLogxK

    U2 - 10.1109/IROS.2009.5354540

    DO - 10.1109/IROS.2009.5354540

    M3 - Conference contribution

    AN - SCOPUS:76249115035

    SN - 9781424438044

    SP - 1615

    EP - 1620

    BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

    ER -