Intelligent human activity recognition scheme for ehealth applications

Girija CHETTY, Mohammad Yamin

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. In this paper, we present a novel data analytic scheme for intelligent Human Activity Recognition (AR) using wireless body sensors and smartphone inertial sensors which use information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Further, we propose a novel multimodal scheme based on combining multimodal three dimensional (x, y, z) accelerometer and gyro data from smart phone inertial sensors. Extensive experiments using different publicly available database of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.
    Original languageEnglish
    Pages (from-to)59-69
    Number of pages11
    JournalMalaysian Journal of Computer Science
    Volume28
    Issue number1
    Publication statusPublished - 2015

    Fingerprint

    Sensors
    Monitoring
    Smartphones
    Information theory
    Accelerometers
    Classifiers
    Experiments

    Cite this

    @article{7942733225f944aeb4db40f158514b64,
    title = "Intelligent human activity recognition scheme for ehealth applications",
    abstract = "Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. In this paper, we present a novel data analytic scheme for intelligent Human Activity Recognition (AR) using wireless body sensors and smartphone inertial sensors which use information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Further, we propose a novel multimodal scheme based on combining multimodal three dimensional (x, y, z) accelerometer and gyro data from smart phone inertial sensors. Extensive experiments using different publicly available database of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.",
    keywords = "Activity recognition, Assisted living, Body sensor, Machine learning, Smart phone",
    author = "Girija CHETTY and Mohammad Yamin",
    year = "2015",
    language = "English",
    volume = "28",
    pages = "59--69",
    journal = "Malaysian Journal of Computer Science",
    issn = "0127-9084",
    publisher = "Faculty of Computer Science and Information Technology",
    number = "1",

    }

    Intelligent human activity recognition scheme for ehealth applications. / CHETTY, Girija; Yamin, Mohammad.

    In: Malaysian Journal of Computer Science, Vol. 28, No. 1, 2015, p. 59-69.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Intelligent human activity recognition scheme for ehealth applications

    AU - CHETTY, Girija

    AU - Yamin, Mohammad

    PY - 2015

    Y1 - 2015

    N2 - Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. In this paper, we present a novel data analytic scheme for intelligent Human Activity Recognition (AR) using wireless body sensors and smartphone inertial sensors which use information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Further, we propose a novel multimodal scheme based on combining multimodal three dimensional (x, y, z) accelerometer and gyro data from smart phone inertial sensors. Extensive experiments using different publicly available database of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.

    AB - Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. In this paper, we present a novel data analytic scheme for intelligent Human Activity Recognition (AR) using wireless body sensors and smartphone inertial sensors which use information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Further, we propose a novel multimodal scheme based on combining multimodal three dimensional (x, y, z) accelerometer and gyro data from smart phone inertial sensors. Extensive experiments using different publicly available database of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.

    KW - Activity recognition

    KW - Assisted living

    KW - Body sensor

    KW - Machine learning

    KW - Smart phone

    UR - http://www.scopus.com/inward/record.url?scp=84929905498&partnerID=8YFLogxK

    M3 - Article

    VL - 28

    SP - 59

    EP - 69

    JO - Malaysian Journal of Computer Science

    JF - Malaysian Journal of Computer Science

    SN - 0127-9084

    IS - 1

    ER -