@article{de_jesus_oliveira_auditory_2023, title = {Auditory feedback in tele-rehabilitation based on automated gait classification}, copyright = {CC-BY}, issn = {1617-4917}, url = {https://doi.org/10.1007/s00779-023-01723-2}, doi = {10.1007/s00779-023-01723-2}, abstract = {In this paper, we describe a proof-of-concept for the implementation of a wearable auditory biofeedback system based on a sensor-instrumented insole. Such a system aims to assist everyday users with static and dynamic exercises for gait rehabilitation interventions by providing auditory feedback based on plantar pressure distribution and automated classification of functional gait disorders. As ground reaction force (GRF) data are frequently used in clinical practice to quantitatively describe human motion and have been successfully used for the classification of gait patterns into clinically relevant classes, a feed-forward neural network was implemented on the firmware of the insoles to estimate the GRFs using pressure and acceleration data. The estimated GRFs approximated well the GRF measurements obtained from force plates. To distinguish between physiological gait and gait disorders, we trained and evaluated a support vector machine with labeled data from a publicly accessible dataset. The automated gait classification was then sonified for auditory feedback. The potential of the implemented auditory feedback for preventive and supportive applications in physical therapy was finally assessed with both expert and non-expert participants. A focus group revealed experts’ expectations for the proposed system, while a usability study assessed the clarity of the auditory feedback to everyday users. The evaluation shows promising results regarding the usefulness of our system in this application area.}, language = {en}, urldate = {2023-05-16}, journal = {Personal and Ubiquitous Computing}, author = {de Jesus Oliveira, Victor Adriel and Slijepčević, Djordje and Dumphart, Bernhard and Ferstl, Stefan and Reis, Joschua and Raberger, Anna-Maria and Heller, Mario and Horsak, Brian and Iber, Michael}, month = may, year = {2023}, keywords = {Biofeedback, Biomechanics, Center for Digital Health and Social Innovation, Departement Gesundheit, Departement Medien und Digitale Technologien, Department Gesundheit, FH SP Data Analytics \& Visual Computing, Forschungsgruppe Media Computing, Gait Analysis, Gait Classification, Institut für Creative Media Technologies, Institut für Gesundheitswissenschaften, Machine Learning, Phaidra, SP CDHSI Motor Rehabilitation, Wiss. Beitrag, best, best-bhorsak, best-lbiber, peer-reviewed}, }