Recognition of Walking Activities Using Wireless Inertial and Orientation Sensors: A Performance Evaluation

Ç. Yalçin, Mihai Marin Perianu, Raluca Marin Perianu, Paul J.M. Havinga

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

    1 Downloads (Pure)


    In this paper, we evaluate experimentally several methods for recognizing walking activities using on-body wireless nodes equipped with inertial and orientation sensors. The walking activities (walking on flat surfaces, uphill and downhill, upstairs and downstairs) are selected by healthcare experts as being relevant for elderly patients suffering from Chronic Obstructive Pulmonary Disease (COPD). We target specifically recognition methods that operate with time-domain features only, due to the limitations of sensor nodes in terms of computational power, memory and energy. The results show that among all sensors the compass sensor performs best regardless of the classification method. Both the compass and gyroscope sensors outperform significantly the accelerometer sensor, which is typically used in previous related work. The best trade-off in performance vs. time complexity is obtained by fusing the gyroscope and compass information, with an overall accuracy of 91%.
    Original languageUndefined
    Title of host publicationWorkshop Proceedings of the 7th International Conference on Intelligent Environments
    EditorsJ.C. Augusto
    Place of PublicationNetherlands
    PublisherIOS Press
    Number of pages7
    ISBN (Print)978-1-60750-794-9
    Publication statusPublished - Jul 2011
    Event7th International Conference on Intelligent Environments, IE 2011 - Nottingham, UK
    Duration: 25 Jul 201128 Jul 2011

    Publication series

    NameAmbient Intelligence and Smart Environments
    PublisherIOS Press


    Workshop7th International Conference on Intelligent Environments, IE 2011
    Other25-28 July 2011


    • METIS-278739
    • EWI-20368
    • IR-77807

    Cite this