In the view of different motion state corresponding to different step length in PDR of indoor and outdoor pedestrian navigation, a method is proposed to classify the lower limb motion state: walking, running, upstairs and downstairs. First use three-axis accelerometer to collect acceleration signal of waist in four conditions, then extract the inter-quartile range (IQR) and difference of peak and trough (DPT) of every step; finally build three kind of classifier include linear discriminant analysis(LDA), support vector machine(SVM) and BP neural network to classify motion states. The results show that BP neural network can be better than LDA and SVM model in classification when space between the classes is small and the average classification accuracy reached 94.5%.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    The classification of human lower limb motion based on acceleration sensor


    Beteiligte:
    Min Li, (Autor:in) / Long Zhao, (Autor:in)


    Erscheinungsdatum :

    2016-08-01


    Format / Umfang :

    267207 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SEMG BASED HUMAN LOWER LIMB CONTIMUOUS MOTION OF ESTIMATION METHOD

    Tao, Y. / Huang, Y. / Zheng, J. et al. | TIBKAT | 2021


    Energy Efficient Autonomous Lower Limb Exoskeleton for Human Motion Enhancement

    Nazim Mir-Nasiri / Hudyjaya Siswoyo Jo | BASE | 2016

    Freier Zugriff

    Energy Efficient Autonomous Lower Limb Exoskeleton for Human Motion Enhancement

    Nazim Mir-Nasiri / Hudyjaya Siswoyo Jo | BASE | 2016

    Freier Zugriff

    Development of an improved lower limb orthosis for a motion-assist robot for the lower limb

    Yabunaka, Toshihito / Kawaguchi, Naoki / Shinoda, Nobuyuki et al. | IEEE | 2013


    Walking Classification of Hip Joint Lower Limb Exoskeleton

    Analia, Riska / M, Joshua Ferdinand. / Susanto et al. | IEEE | 2019