Gait Phase Detection for Lower-Limb Exoskeletons using Foot Motion Data from a Single Inertial Measurement Unit in Hemiparetic Individuals.

Miguel D Sánchez Sánchez Manchola,María J Pinto Pinto Bernal,Marcela Munera,Carlos A Cifuentes

doi:10.3390/s19132988

Miguel D Sánchez Sánchez Manchola, María J Pinto Pinto Bernal + Show 2 more

Open Access

https://doi.org/10.3390/s19132988

Copy DOI

Abstract

Due to the recent rise in the use of lower-limb exoskeletons as an alternative for gait rehabilitation, gait phase detection has become an increasingly important feature in the control of these devices. In addition, highly functional, low-cost recovery devices are needed in developing countries, since limited budgets are allocated specifically for biomedical advances. To achieve this goal, this paper presents two gait phase partitioning algorithms that use motion data from a single inertial measurement unit (IMU) placed on the foot instep. For these data, sagittal angular velocity and linear acceleration signals were extracted from nine healthy subjects and nine pathological subjects. Pressure patterns from force sensitive resistors (FSR) instrumented on a custom insole were used as reference values. The performance of a threshold-based (TB) algorithm and a hidden Markov model (HMM) based algorithm, trained by means of subject-specific and standardized parameters approaches, were compared during treadmill walking tasks in terms of timing errors and the goodness index. The findings indicate that HMM outperforms TB for this hardware configuration. In addition, the HMM-based classifier trained by an intra-subject approach showed excellent reliability for the evaluation of mean time, i.e., its intra-class correlation coefficient (ICC) was greater than . In conclusion, the HMM-based method proposed here can be implemented for gait phase recognition, such as to evaluate gait variability in patients and to control robotic orthoses for lower-limb rehabilitation.

Highlights

Human gait refers to the physiological way of locomotion which can be altered by several pathologies [1]
Taking into account the premises found in literature, this study proposes the validation of two algorithms for a gait phase detection system (GPDS) that only uses the uni-axial gyro and accelerometer signals drawn from an embedded inertial measurement unit (IMU) placed on the foot instep to accurately detect four gait events
This paper features the validation of two gait phase detection algorithms in a system which only involves the inertial sensing from a foot-mounted IMU: a TB and an hidden Markov model (HMM)-based algorithm; the latter is trained by means of two modalities, namely an intra-subject approach and an inter-subject procedure based on standardized data from healthy subjects

Summary

Introduction

Human gait refers to the physiological way of locomotion which can be altered by several pathologies [1]. Gait analysis is of great help to therapists who wish to monitor the recovery of patients going through rehabilitation processes [2]. Gait classification can be implemented as part of the control parameters for functional electrical stimulation (FES) [3,4], the detection of abnormal gait pattern in patients with paretic limbs and their classification based on known pathologies [5], and an estimation of the risk that elderly people fall [6]. An atypical gait pattern can be an indicator of the progression of neurological disorders. Atypical gait patterns have been proven to predict if seniors will develop dementia or cognitive decline [7]. Researchers have managed to program humanoid robots to use human-based

Methods

Results

Discussion

Conclusion