Multiple Classification of Gait Using Time-Frequency Representations and Deep Convolutional Neural Networks
- 28 February 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 28 (4) , 997-1005
Abstract
Human gait has served as a useful barometer of health. Existing studies for automatic categorization of gait have been limited to a binary classification of pathological and non-pathological gait and provided low accuracy in multi-classification. This study aimed to propose a novel approach that can multi-classify gait with no visually discernible difference in characteristics. Sixty-nine participants without gait disturbance were recruited. Twenty-nine of the participants were semi-professional athletes, and 19 were ordinary people. The remaining 21 participants were people with subtle foot deformities. The 3-axis acceleration and the 3-axis angular velocity signals were measured using the inertial measurement units attached to the foot, shank, thigh, and posterior pelvis while walking. The gait spectrograms were acquired by applying time-frequency analyses to the lower body movement signals measured in one stride and used to train the deep convolutional neural network-based classifiers. Four-fold cross-validation was applied to 80% of the total samples and the remaining 20% were used as test data. The foot, shank, and thigh spectrograms enabled complete classification of the three groups even without requiring a sophisticated process for feature engineering. This is the first study that employed the spectrographic approach in gait classification and achieved reliable multi-classification of gait without observable differences in characteristics using the deep convolutional neural networks.Keywords
Funding Information
- High-Tech Based National Athletic Performance Improvement (Winter) Project from the Korea Sports Promotion Foundation
- Korea Institute of Science and Technology (KIST) Institutional Program (2E30270)
This publication has 27 references indexed in Scilit:
- Classification of Parkinson's Disease Gait Using Spatial-Temporal Gait FeaturesIEEE Journal of Biomedical and Health Informatics, 2015
- Convolutional Neural Networks for Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Convolutional Neural Networks for Distant Speech RecognitionIEEE Signal Processing Letters, 2014
- High-level gait and balance disorders in the elderly: a midbrain disease?Journal of Neurology, 2013
- Gait ataxia—specific cerebellar influences and their rehabilitationMovement Disorders, 2013
- Normative spatiotemporal gait parameters in older adultsGait & Posture, 2011
- Loss of white matter integrity is associated with gait disorders in cerebral small vessel diseaseBrain, 2010
- Gait classification in post-stroke patients using artificial neural networksGait & Posture, 2009
- Toward the Design of a Wearable System for Fall-Risk Detection in TelerehabilitationTelemedicine and e-Health, 2009
- Gait disorders: search for multiple causes.Cleveland Clinic Journal of Medicine, 2005