Format

Send to

Choose Destination
Sensors (Basel). 2015 Oct 30;15(11):27738-59. doi: 10.3390/s151127738.

A Neural Network-Based Gait Phase Classification Method Using Sensors Equipped on Lower Limb Exoskeleton Robots.

Jung JY1, Heo W2,3, Yang H4,5, Park H6,7.

Author information

1
Robot Group, Korea Institute of Industrial Technology, 143 Hanggaul-ro, Sanrok-gu, Ansan-si, Gyeonggi-do 15588, Korea. paran1@kitech.re.kr.
2
Robot Group, Korea Institute of Industrial Technology, 143 Hanggaul-ro, Sanrok-gu, Ansan-si, Gyeonggi-do 15588, Korea. eiever@kitech.re.kr.
3
School of Electrical and Electronic Engineering, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Korea. eiever@kitech.re.kr.
4
Robot Group, Korea Institute of Industrial Technology, 143 Hanggaul-ro, Sanrok-gu, Ansan-si, Gyeonggi-do 15588, Korea. hd0301@kitech.re.kr.
5
School of Intelligent Robots, University of Science and Technology, 217 Gajeong-ro, Yuseong-gu, Daejeon 34113, Korea. hd0301@kitech.re.kr.
6
Robot Group, Korea Institute of Industrial Technology, 143 Hanggaul-ro, Sanrok-gu, Ansan-si, Gyeonggi-do 15588, Korea. hsubpark@kitech.re.kr.
7
System Industry PD Group, Korea Evaluation Institute of Industrial Technology, 32 Cheomdan-ro 8-gil, Dong-gu, Daegu 41069, Korea. hsubpark@kitech.re.kr.

Abstract

An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases.

KEYWORDS:

MLP; NARX; exoskeleton robots; gait phase classification; neural network

PMID:
26528986
PMCID:
PMC4701252
DOI:
10.3390/s151127738
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center