A Wearable Gait Phase Detection System Based on Force Myography Techniques.

Xianta Jiang,Carlo Menon,Kelvin H T Chu,Mahta Khoshnam

doi:10.3390/s18041279

Abstract

(1) Background: Quantitative evaluation of gait parameters can provide useful information for constructing individuals’ gait profile, diagnosing gait abnormalities, and better planning of rehabilitation schemes to restore normal gait pattern. Objective determination of gait phases in a gait cycle is a key requirement in gait analysis applications; (2) Methods: In this study, the feasibility of using a force myography-based technique for a wearable gait phase detection system is explored. In this regard, a force myography band is developed and tested with nine participants walking on a treadmill. The collected force myography data are first examined sample-by-sample and classified into four phases using Linear Discriminant Analysis. The gait phase events are then detected from these classified samples using a set of supervisory rules; (3) Results: The results show that the force myography band can correctly detect more than 99.9% of gait phases with zero insertions and only four deletions over 12,965 gait phase segments. The average temporal error of gait phase detection is 55.2 ms, which translates into 2.1% error with respect to the corresponding labelled stride duration; (4) Conclusions: This proof-of-concept study demonstrates the feasibility of force myography techniques as viable solutions in developing wearable gait phase detection systems.

Highlights

Walking is one of the basic activities of humans in everyday life and gait analysis provides a systematic and quantitative means to assess human locomotion [1,2]
The work builds upon lower walking speeds, we focus on slow-paced walking and collect the data at three low speeds our previous work that demonstrated that Force myography (FMG) can be effectively used to count steps in a controlled
The Tukey HSD on the effect of the gait phase showed that the temporal error of phase 4 (Swing) is significantly lower than that of other phases (p < 0.0005), but there was no significant difference between the other three phases (Phases 1–3)

Summary

Introduction

Walking is one of the basic activities of humans in everyday life and gait analysis provides a systematic and quantitative means to assess human locomotion [1,2]. Automatic detection of gait phases can be used in distinguishing walking styles [10], detecting foot-drop [11,12], and improving the gait through nerve stimulation using functional electrical stimulation (FES) [12,13]. The methods using inertial sensors can typically achieve a high accuracy at moderate to high walking speeds or in self-paced walking. Their performance noticeably degrades at lower walking speeds, which is usually the pace for individuals with difficulty in walking [15,16]

Results

Discussion

Conclusion