Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter

Ioannis Papavasileiou, Wenlong Zhang, Song Han

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

    3 Citations (Scopus)

    Abstract

    The world is experiencing an unprecedented enduring, and pervasive aging process. With more people who need walking assistance, the demand for gait rehabilitation has increased rapidly over the years. Effective gait rehabilitation requires a comprehensive gait analysis, in which gait phase detection plays an important role. Although many specialized sensing systems have been developed for gait monitoring, most existing gait phase detection algorithms rely on significant input from medical professionals, which are subjective, manual and inaccurate. To address these problems, this paper presents a datadriven approach for real-time gait phase detection. The approach combines an infinite Gaussian mixture model (IGMM) to classify different gait phases based on the ground contact force (GCF) measurement, and a parallel particle filter to estimate and update the model parameters. Effective particle sharing mechanisms are further designed to distribute particles among different working nodes judiciously and thus strike a good balance between computational overhead and estimation accuracy. The proposed algorithm is implemented in our gait monitoring and analysis platform developed on Microsoft Azure, and examined using the data trace collected from a healthy human subject. The algorithm effectiveness is validated through extensive experiments.

    Original languageEnglish (US)
    Title of host publicationProceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages302-311
    Number of pages10
    ISBN (Electronic)9781509009435
    DOIs
    StatePublished - Aug 16 2016
    Event1st IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016 - Washington, United States
    Duration: Jun 27 2016Jun 29 2016

    Other

    Other1st IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016
    CountryUnited States
    CityWashington
    Period6/27/166/29/16

    Fingerprint

    Patient rehabilitation
    Gait analysis
    Monitoring
    Force measurement
    Aging of materials
    Gaussian mixture model
    Particle filter
    Experiments
    Rehabilitation
    Microsoft
    Node
    Experiment

    ASJC Scopus subject areas

    • Computer Science Applications
    • Information Systems and Management
    • Biomedical Engineering
    • Computer Networks and Communications
    • Hardware and Architecture

    Cite this

    Papavasileiou, I., Zhang, W., & Han, S. (2016). Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter. In Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016 (pp. 302-311). [7545845] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CHASE.2016.25

    Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter. / Papavasileiou, Ioannis; Zhang, Wenlong; Han, Song.

    Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 302-311 7545845.

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

    Papavasileiou, I, Zhang, W & Han, S 2016, Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter. in Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016., 7545845, Institute of Electrical and Electronics Engineers Inc., pp. 302-311, 1st IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016, Washington, United States, 6/27/16. https://doi.org/10.1109/CHASE.2016.25
    Papavasileiou I, Zhang W, Han S. Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter. In Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 302-311. 7545845 https://doi.org/10.1109/CHASE.2016.25
    Papavasileiou, Ioannis ; Zhang, Wenlong ; Han, Song. / Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter. Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 302-311
    @inproceedings{8b57d2f856f94357946052ffb8ab428b,
    title = "Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter",
    abstract = "The world is experiencing an unprecedented enduring, and pervasive aging process. With more people who need walking assistance, the demand for gait rehabilitation has increased rapidly over the years. Effective gait rehabilitation requires a comprehensive gait analysis, in which gait phase detection plays an important role. Although many specialized sensing systems have been developed for gait monitoring, most existing gait phase detection algorithms rely on significant input from medical professionals, which are subjective, manual and inaccurate. To address these problems, this paper presents a datadriven approach for real-time gait phase detection. The approach combines an infinite Gaussian mixture model (IGMM) to classify different gait phases based on the ground contact force (GCF) measurement, and a parallel particle filter to estimate and update the model parameters. Effective particle sharing mechanisms are further designed to distribute particles among different working nodes judiciously and thus strike a good balance between computational overhead and estimation accuracy. The proposed algorithm is implemented in our gait monitoring and analysis platform developed on Microsoft Azure, and examined using the data trace collected from a healthy human subject. The algorithm effectiveness is validated through extensive experiments.",
    author = "Ioannis Papavasileiou and Wenlong Zhang and Song Han",
    year = "2016",
    month = "8",
    day = "16",
    doi = "10.1109/CHASE.2016.25",
    language = "English (US)",
    pages = "302--311",
    booktitle = "Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Real-Time Data-Driven Gait Phase Detection Using Infinite Gaussian Mixture Model and Parallel Particle Filter

    AU - Papavasileiou, Ioannis

    AU - Zhang, Wenlong

    AU - Han, Song

    PY - 2016/8/16

    Y1 - 2016/8/16

    N2 - The world is experiencing an unprecedented enduring, and pervasive aging process. With more people who need walking assistance, the demand for gait rehabilitation has increased rapidly over the years. Effective gait rehabilitation requires a comprehensive gait analysis, in which gait phase detection plays an important role. Although many specialized sensing systems have been developed for gait monitoring, most existing gait phase detection algorithms rely on significant input from medical professionals, which are subjective, manual and inaccurate. To address these problems, this paper presents a datadriven approach for real-time gait phase detection. The approach combines an infinite Gaussian mixture model (IGMM) to classify different gait phases based on the ground contact force (GCF) measurement, and a parallel particle filter to estimate and update the model parameters. Effective particle sharing mechanisms are further designed to distribute particles among different working nodes judiciously and thus strike a good balance between computational overhead and estimation accuracy. The proposed algorithm is implemented in our gait monitoring and analysis platform developed on Microsoft Azure, and examined using the data trace collected from a healthy human subject. The algorithm effectiveness is validated through extensive experiments.

    AB - The world is experiencing an unprecedented enduring, and pervasive aging process. With more people who need walking assistance, the demand for gait rehabilitation has increased rapidly over the years. Effective gait rehabilitation requires a comprehensive gait analysis, in which gait phase detection plays an important role. Although many specialized sensing systems have been developed for gait monitoring, most existing gait phase detection algorithms rely on significant input from medical professionals, which are subjective, manual and inaccurate. To address these problems, this paper presents a datadriven approach for real-time gait phase detection. The approach combines an infinite Gaussian mixture model (IGMM) to classify different gait phases based on the ground contact force (GCF) measurement, and a parallel particle filter to estimate and update the model parameters. Effective particle sharing mechanisms are further designed to distribute particles among different working nodes judiciously and thus strike a good balance between computational overhead and estimation accuracy. The proposed algorithm is implemented in our gait monitoring and analysis platform developed on Microsoft Azure, and examined using the data trace collected from a healthy human subject. The algorithm effectiveness is validated through extensive experiments.

    UR - http://www.scopus.com/inward/record.url?scp=84987623746&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84987623746&partnerID=8YFLogxK

    U2 - 10.1109/CHASE.2016.25

    DO - 10.1109/CHASE.2016.25

    M3 - Conference contribution

    AN - SCOPUS:84987623746

    SP - 302

    EP - 311

    BT - Proceedings - 2016 IEEE 1st International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2016

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -