Towards physical activity recognition using smartphone sensors

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    130 Citations (Scopus)
    831 Downloads (Pure)

    Abstract

    In recent years, the use of a smartphone accelerometer in physical activity recognition has been well studied. However, the role of a gyroscope and a magnetometer is yet to be explored, both when used alone as well as in combination with an accelerometer. For this purpose, we investigate the role of these three smartphone sensors in activity recognition. We evaluate their roles on four body positions using seven classifiers while recognizing six physical activities. We show that in general an accelerometer and a gyroscope complement each other, thereby making the recognition process more reliable. Moreover, in most cases, a gyroscope does not only improve the recognition accuracy in combination with an accelerometer, but it also achieves a reasonable performance when used alone. The results for a magnetometer are not encouraging because it causes over-fitting in training classifiers due to its dependence on directions. Based on our evaluations, we show that it is difficult to make an exact general statement about which sensor performs better than the others in all situations because their recognition performance depends on the smartphone’s position, the selected classifier, and the activity being recognized. However, statements about their roles in specific situations can be made. We report our observations and results in detail in this paper, while our data-set and data-collection app is publicly available, thereby making our experiments reproducible.
    Original languageUndefined
    Title of host publication10th IEEE International Conference on Ubiquitous Intelligence and Computing, UIC 2013
    Place of PublicationCalifornia
    PublisherIEEE Computer Society
    Pages80-87
    Number of pages8
    ISBN (Print)978-1-4799-2481-3
    DOIs
    Publication statusPublished - 3 Dec 2013
    EventIEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013 - Vietri sul Mare, Italy
    Duration: 18 Dec 201320 Dec 2013
    Conference number: 10

    Publication series

    Name
    PublisherIEEE Computer Society

    Conference

    ConferenceIEEE 10th International Conference on Ubiquitous Intelligence and Computing, UIC 2013
    Abbreviated titleUIC
    CountryItaly
    CityVietri sul Mare
    Period18/12/1320/12/13

    Keywords

    • EWI-23843
    • assisted living
    • smartphone sensors
    • well-being applications
    • Gyroscope
    • IR-88302
    • Sensor fusion
    • Accelermeter
    • Activity Recognition
    • Magnetometer
    • METIS-300091
    • Health Monitoring

    Cite this

    Shoaib, M., Scholten, J., & Havinga, P. J. M. (2013). Towards physical activity recognition using smartphone sensors. In 10th IEEE International Conference on Ubiquitous Intelligence and Computing, UIC 2013 (pp. 80-87). California: IEEE Computer Society. https://doi.org/10.1109/UIC-ATC.2013.43