PROJECT TITLE :

A Novel Adaptive, Real-Time Algorithm to Detect Gait Events From Wearable Sensors

ABSTRACT:

A true-time, adaptive algorithm based on two inertial and magnetic sensors placed on the shanks was developed for gait-event detection. For every leg, the algorithm detected the Initial Contact (IC), because the minimum of the flexion/extension angle, and the tip Contact (EC) and therefore the Mid-Swing (MS), as minimum and most of the angular velocity, respectively. The algorithm consisted of calibration, real-time detection, and step-by-step update. Data collected from 22 healthy subjects (21 to eighty five years) walking at 3 self-selected speeds were used to validate the algorithm against the GaitRite system. Comparable levels of accuracy and significantly lower detection delays were achieved with respect to different revealed methods. The algorithm robustness was tested on ten healthy subjects performing sudden speed changes and on ten stroke subjects (forty three to 89 years). For healthy subjects, F1-countless one and mean detection delays below fourteen ms were obtained. For stroke subjects, F1-millions of 0.998 and zero.944 were obtained for IC and EC, respectively, with mean detection delays perpetually below 31 ms. The algorithm accurately detected gait events in real time from a heterogeneous dataset of gait patterns and paves the way for the look of closed-loop controllers for customized gait trainings and/or assistive devices.