Monitoring of gait performance using dynamic time warping on IMU-sensor data

In this paper, a novel method for monitoring the changes in gait joint angle trajectories recorded using the low-cost and wearable Inertial Measurement Units (IMU) is presented. The introduced method is based on Dynamic Time Warping (DTW), an algorithm commonly used for evaluating the similarity of two time series which may vary in time and speed. DTW is employed as the measure of distance between two gait trajectories taken in different time instances, which could be used as an intuitive and effective measure for the evaluation of gait performances. The experimental results presented in the paper demonstrate that the proposed method is applicable for clinically relevant applications and is consequently adaptable to patients with diseases characterized with gait disorders and to different walking scenarios. The proposed method was firstly validated by applying the DTW-based measure on gait trajectories of five healthy subjects recorded while simulating different levels of walking disabilities. Then proposed measure was applied to estimate the distance between the “healthy” gait trajectories and gait trajectories of three patients with Parkinson's disease (PD) while performing single-task and dual-task overground walking. Also, the proposed measure was demonstrated as an effective measure for monitoring the changes in gait patterns of a PD patient before and after medication-based treatment. This result indicates potential use of proposed method for effective pharmacological management of PD.