Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device

Ryan M. Gibson, Abbes Amira, Naeem Ramzan, Pablo Casaseca-de-la-Higuera, Zeeshan Pervez

    Research output: Contribution to journalArticle

    55 Downloads (Pure)

    Abstract

    There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80% battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve battery usage performance. Various Matching pursuit-based compressive sensing techniques have been utilised to significantly reduce acceleration information required for transmission.
    Original languageEnglish
    Pages (from-to)96–108
    Number of pages13
    Journal Biomedical Signal Processing and Control
    Volume33
    Early online date1 Dec 2016
    DOIs
    Publication statusPublished - Mar 2017

    Fingerprint

    Accelerometers
    Principal component analysis
    Classifiers
    Activities of Daily Living
    Principal Component Analysis
    Equipment and Supplies
    Binary trees
    Discrete wavelet transforms
    Wavelet Analysis
    Databases
    Experiments
    Wounds and Injuries
    Population

    Keywords

    • biomedical accelerometer
    • falls diagnosis
    • sensing techniques

    Cite this

    Gibson, Ryan M. ; Amira, Abbes ; Ramzan, Naeem ; Casaseca-de-la-Higuera, Pablo ; Pervez, Zeeshan. / Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device. In: Biomedical Signal Processing and Control. 2017 ; Vol. 33. pp. 96–108.
    @article{55321ba18a3f415d92a50f9d21b65acb,
    title = "Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device",
    abstract = "There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80{\%} battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve battery usage performance. Various Matching pursuit-based compressive sensing techniques have been utilised to significantly reduce acceleration information required for transmission.",
    keywords = "biomedical accelerometer, falls diagnosis, sensing techniques",
    author = "Gibson, {Ryan M.} and Abbes Amira and Naeem Ramzan and Pablo Casaseca-de-la-Higuera and Zeeshan Pervez",
    note = "Author confirmed file is AAM (notes preprint on file) File uploaded 14-12-16; 12m embargo Funder: no funder mentioned",
    year = "2017",
    month = "3",
    doi = "10.1016/j.bspc.2016.10.016",
    language = "English",
    volume = "33",
    pages = "96–108",
    journal = "Biomedical Signal Processing and Control",
    issn = "1746-8094",
    publisher = "Elsevier B.V.",

    }

    Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device. / Gibson, Ryan M.; Amira, Abbes; Ramzan, Naeem; Casaseca-de-la-Higuera, Pablo; Pervez, Zeeshan.

    In: Biomedical Signal Processing and Control, Vol. 33, 03.2017, p. 96–108.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device

    AU - Gibson, Ryan M.

    AU - Amira, Abbes

    AU - Ramzan, Naeem

    AU - Casaseca-de-la-Higuera, Pablo

    AU - Pervez, Zeeshan

    N1 - Author confirmed file is AAM (notes preprint on file) File uploaded 14-12-16; 12m embargo Funder: no funder mentioned

    PY - 2017/3

    Y1 - 2017/3

    N2 - There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80% battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve battery usage performance. Various Matching pursuit-based compressive sensing techniques have been utilised to significantly reduce acceleration information required for transmission.

    AB - There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80% battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve battery usage performance. Various Matching pursuit-based compressive sensing techniques have been utilised to significantly reduce acceleration information required for transmission.

    KW - biomedical accelerometer

    KW - falls diagnosis

    KW - sensing techniques

    U2 - 10.1016/j.bspc.2016.10.016

    DO - 10.1016/j.bspc.2016.10.016

    M3 - Article

    VL - 33

    SP - 96

    EP - 108

    JO - Biomedical Signal Processing and Control

    JF - Biomedical Signal Processing and Control

    SN - 1746-8094

    ER -