Gait Phase Identification and Damping Control for Knee Orthosis Using Time Series Forest Classifier

Knee orthosis plays a vital role in enhancing the wellbeing and quality of life of individuals suffering from knee arthritis. This study explores a machine-learning-based methodology for predicting a user's gait subphase using inertial measurement units (IMUs) for a semiactive orthosis. A musculoskeletal simulation is employed with the help of existing experimental motion-capture data to obtain essential metrics related to the gait cycle, which are then normalized and scaled. A meticulous data capture methodology using foot switches is used for precise synchronization with IMU data, resulting in comprehensive labeled subphase datasets. The integration of simulation results and labeled datasets provides activation data for effective knee flexion damping following which multiple supervised machine learning algorithms are trained and evaluated for performances. The time series forest classifier emerged as the most suitable algorithm, with an accuracy of 86 percent, against randomized convolutional kernel transform, K-neighbor time series classifier, and long short-term memory-fully convolutional network, with accuracies of 68, 76, and 78, respectively, showcasing exceptional performance scores, thereby rendering it an optimal choice for identifying gait subphases and achieving the desired level of damping for magnetorheological brake-mounted knee orthosis based on simulated results.