Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles

Jun Inoue, Kazuya Kawamura, Masakatsu G. Fujie

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

    2 Citations (Scopus)

    Abstract

    The objective of this study is to develop an estimation model of foot-ankle muscular activity for designing an ankle-foot orthosis with a training function. We built a Bayesian network model [1] and chose three muscles to confirm its effectiveness. Such a model needs to include all factors affecting the gait, for example, speed reflex movements, joint angles and so forth. In an experiment, we examined the normal gait of a non-disabled subject. We measured the muscular activity of the lower foot muscles by electromyography, the joint angles by using statistical methods, and the sole pressure on each part of the sole. From this data, we obtained the causal relationship at every 10% level of these factors. Our model has three advantages. First, it can express the influences, which change throughout the gait, because we use 10% level nodes of each factor. Second, it can express the influences of factors, which are different for low and high muscular activity levels. Last, the model can compensate the missed estimations by estimating every 10% level muscle activity. In an evaluation of this model, we confirmed that this model can estimate all muscular activity level with an accuracy rate greater than 90%.

    Original languageEnglish
    Title of host publicationProceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
    Pages431-436
    Number of pages6
    DOIs
    Publication statusPublished - 2012
    Event2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012 - Rome
    Duration: 2012 Jun 242012 Jun 27

    Other

    Other2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012
    CityRome
    Period12/6/2412/6/27

    Fingerprint

    Muscle
    Electromyography
    Bayesian networks
    Statistical methods
    Experiments

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Biomedical Engineering
    • Mechanical Engineering

    Cite this

    Inoue, J., Kawamura, K., & Fujie, M. G. (2012). Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles. In Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics (pp. 431-436). [6290295] https://doi.org/10.1109/BioRob.2012.6290295

    Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles. / Inoue, Jun; Kawamura, Kazuya; Fujie, Masakatsu G.

    Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. p. 431-436 6290295.

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

    Inoue, J, Kawamura, K & Fujie, MG 2012, Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles. in Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics., 6290295, pp. 431-436, 2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012, Rome, 12/6/24. https://doi.org/10.1109/BioRob.2012.6290295
    Inoue J, Kawamura K, Fujie MG. Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles. In Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. p. 431-436. 6290295 https://doi.org/10.1109/BioRob.2012.6290295
    Inoue, Jun ; Kawamura, Kazuya ; Fujie, Masakatsu G. / Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles. Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. pp. 431-436
    @inproceedings{76dae06668324b7ba286cce76a75289a,
    title = "Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles",
    abstract = "The objective of this study is to develop an estimation model of foot-ankle muscular activity for designing an ankle-foot orthosis with a training function. We built a Bayesian network model [1] and chose three muscles to confirm its effectiveness. Such a model needs to include all factors affecting the gait, for example, speed reflex movements, joint angles and so forth. In an experiment, we examined the normal gait of a non-disabled subject. We measured the muscular activity of the lower foot muscles by electromyography, the joint angles by using statistical methods, and the sole pressure on each part of the sole. From this data, we obtained the causal relationship at every 10{\%} level of these factors. Our model has three advantages. First, it can express the influences, which change throughout the gait, because we use 10{\%} level nodes of each factor. Second, it can express the influences of factors, which are different for low and high muscular activity levels. Last, the model can compensate the missed estimations by estimating every 10{\%} level muscle activity. In an evaluation of this model, we confirmed that this model can estimate all muscular activity level with an accuracy rate greater than 90{\%}.",
    author = "Jun Inoue and Kazuya Kawamura and Fujie, {Masakatsu G.}",
    year = "2012",
    doi = "10.1109/BioRob.2012.6290295",
    language = "English",
    isbn = "9781457711992",
    pages = "431--436",
    booktitle = "Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics",

    }

    TY - GEN

    T1 - Developing an ankle-foot muscular model using Bayesian estimation for the influence of an ankle foot orthosis on muscles

    AU - Inoue, Jun

    AU - Kawamura, Kazuya

    AU - Fujie, Masakatsu G.

    PY - 2012

    Y1 - 2012

    N2 - The objective of this study is to develop an estimation model of foot-ankle muscular activity for designing an ankle-foot orthosis with a training function. We built a Bayesian network model [1] and chose three muscles to confirm its effectiveness. Such a model needs to include all factors affecting the gait, for example, speed reflex movements, joint angles and so forth. In an experiment, we examined the normal gait of a non-disabled subject. We measured the muscular activity of the lower foot muscles by electromyography, the joint angles by using statistical methods, and the sole pressure on each part of the sole. From this data, we obtained the causal relationship at every 10% level of these factors. Our model has three advantages. First, it can express the influences, which change throughout the gait, because we use 10% level nodes of each factor. Second, it can express the influences of factors, which are different for low and high muscular activity levels. Last, the model can compensate the missed estimations by estimating every 10% level muscle activity. In an evaluation of this model, we confirmed that this model can estimate all muscular activity level with an accuracy rate greater than 90%.

    AB - The objective of this study is to develop an estimation model of foot-ankle muscular activity for designing an ankle-foot orthosis with a training function. We built a Bayesian network model [1] and chose three muscles to confirm its effectiveness. Such a model needs to include all factors affecting the gait, for example, speed reflex movements, joint angles and so forth. In an experiment, we examined the normal gait of a non-disabled subject. We measured the muscular activity of the lower foot muscles by electromyography, the joint angles by using statistical methods, and the sole pressure on each part of the sole. From this data, we obtained the causal relationship at every 10% level of these factors. Our model has three advantages. First, it can express the influences, which change throughout the gait, because we use 10% level nodes of each factor. Second, it can express the influences of factors, which are different for low and high muscular activity levels. Last, the model can compensate the missed estimations by estimating every 10% level muscle activity. In an evaluation of this model, we confirmed that this model can estimate all muscular activity level with an accuracy rate greater than 90%.

    UR - http://www.scopus.com/inward/record.url?scp=84867423254&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84867423254&partnerID=8YFLogxK

    U2 - 10.1109/BioRob.2012.6290295

    DO - 10.1109/BioRob.2012.6290295

    M3 - Conference contribution

    AN - SCOPUS:84867423254

    SN - 9781457711992

    SP - 431

    EP - 436

    BT - Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics

    ER -