More versatile, user-independent tools for recognizing and predicting locomotion modes (LMs) and LM transitions (LMTs) in natural gaits are still needed. This study tackles these challenges by proposing an automatic, user-independent recognition and prediction tool using easily wearable kinematic motion sensors for innovatively classifying several LMs (walking direction, level-ground walking, ascend and descend stairs, and ascend and descend ramps) and respective LMTs. We compared diverse state-of-the-art feature processing and dimensionality reduction methods and machine-learning classifiers to find an effective tool for recognition and prediction of LMs and LMTs. The comparison included kinematic patterns from 10 able-bodied subjects. The more accurate tools were achieved using min-max scaling [-1; 1] interval and 'mRMR plus forward selection' algorithm for feature normalization and dimensionality reduction, respectively, and Gaussian support vector machine classifier. The developed tool was accurate in the recognition (accuracy >99% and >96%) and prediction (accuracy >99% and >93%) of daily LMs and LMTs, respectively, using exclusively kinematic data. The use of kinematic data yielded an effective recognition and prediction tool, predicting the LMs and LMTs one-step-ahead. This timely prediction is relevant for assistive devices providing personalized assistance in daily scenarios. The kinematic data-based machine learning tool innovatively addresses several LMs and LMTs while allowing the user to self-select the leading limb to perform LMTs, ensuring a natural gait. ; This work was supported in part by the Fundação para a Ciência e Tecnologia (FCT) with the Reference Scholarship under Grant SFRH/BD/108309/2015 and SFRH/BD/147878/2019, by the FEDER Funds through the Programa Operacional Regional do Norte and national funds from FCT with the project SmartOs under Grant NORTE-01-0145-FEDER-030386, and through the COMPETE 2020—Programa Operacional Competitividade e Internacionalização (POCI)—with the Reference Project under Grant POCI-01-0145-FEDER-006941.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Daily locomotion recognition and prediction: A kinematic data-based machine learning approach


    Beteiligte:

    Erscheinungsdatum :

    2020-01-01


    Anmerkungen:

    doi:10.1109/ACCESS.2020.2971552



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach

    Figueiredo, Joana / Carvalho, Simão P. / Goncalve, D. et al. | BASE | 2020

    Freier Zugriff

    Kinematic Differences Between Motorized and Nonmotorized Treadmill Locomotion

    DeWitt, John K. / Bentley, Jason R. / Lee, Stuart M. C. et al. | NTRS | 2006




    Design and Kinematic Aspects of a Hybrid Locomotion Robot

    Conduraru Slatineanu, Alina ;Doroftei, Ioan ;Conduraru, Ionel | Trans Tech Publications | 2014