TY - JOUR
T1 - Real-Time Gait Phase Detection on Wearable Devices for Real-World Free-Living Gait
AU - Wu, Jiaen
AU - Becsek, Barna
AU - Schaer, Alessandro
AU - Maurenbrecher, Henrik
AU - Chatzipirpiridis, George
AU - Ergeneman, Olgac
AU - Pane, Salvador
AU - Torun, Hamdi
AU - Nelson, Bradley J.
N1 - Funding information: This project has received funding from the European Union’s Horizon Research and Innovation program under the Marie Sklodowska-Curie grant agreement No. 764977.
PY - 2023/3/1
Y1 - 2023/3/1
N2 - Detecting gait phases with wearables unobtrusively and reliably in real-time is important for clinical gait rehabilitation and early diagnosis of neurological diseases. Due to hardware limitations of microcontrollers in wearable devices (e.g., memory and computation power), reliable real-time gait phase detection on the microcontrollers remains a challenge, especially for long-term real-world free-living gait. In this work, a novel algorithm based on a reduced support vector machine (RSVM) and a finite state machine (FSM) is developed to address this. The RSVM is developed by exploiting the cascaded K-means clustering to reduce the model size and computation time of a standard SVM by 88% and a factor of 36, with only minor degradation in gait phase prediction accuracy of around 4%. For each gait phase prediction from the RSVM, the FSM is designed to validate the prediction and correct misclassifications. The developed algorithm is implemented on a microcontroller of a wearable device and its real-time (on the fly) classification performance is evaluated by twenty healthy subjects walking along a predefined real-world route with uncontrolled free-living gait. It shows a promising real-time performance with an accuracy of 91.51%, a sensitivity of 91.70%, and a specificity of 95.77%. The algorithm also demonstrates its robustness with varying walking conditions.
AB - Detecting gait phases with wearables unobtrusively and reliably in real-time is important for clinical gait rehabilitation and early diagnosis of neurological diseases. Due to hardware limitations of microcontrollers in wearable devices (e.g., memory and computation power), reliable real-time gait phase detection on the microcontrollers remains a challenge, especially for long-term real-world free-living gait. In this work, a novel algorithm based on a reduced support vector machine (RSVM) and a finite state machine (FSM) is developed to address this. The RSVM is developed by exploiting the cascaded K-means clustering to reduce the model size and computation time of a standard SVM by 88% and a factor of 36, with only minor degradation in gait phase prediction accuracy of around 4%. For each gait phase prediction from the RSVM, the FSM is designed to validate the prediction and correct misclassifications. The developed algorithm is implemented on a microcontroller of a wearable device and its real-time (on the fly) classification performance is evaluated by twenty healthy subjects walking along a predefined real-world route with uncontrolled free-living gait. It shows a promising real-time performance with an accuracy of 91.51%, a sensitivity of 91.70%, and a specificity of 95.77%. The algorithm also demonstrates its robustness with varying walking conditions.
KW - Footwear
KW - Legged locomotion
KW - Microcontrollers
KW - Phase detection
KW - Real-time gait phase detection
KW - Real-time systems
KW - Support vector machines
KW - Wearable computers
KW - embedded system algorithms
KW - gait rehabilitation
KW - real-world free-living walking
KW - wearable sensors
UR - http://www.scopus.com/inward/record.url?scp=85144806214&partnerID=8YFLogxK
U2 - 10.1109/jbhi.2022.3228329
DO - 10.1109/jbhi.2022.3228329
M3 - Article
SN - 2168-2194
VL - 27
SP - 1295
EP - 1306
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 3
ER -