Surface Electromyogram Feature Set Optimization for Lower Limb Activity Classification

Abstract

Surface electromyogram (SEMG) shows the vital information of human motor activity. This information can identify the motor activity and controlling assistive and rehabilitative devices. However, its efficient extraction and interpretation plays a very critical role. The present study is focused on lower limb activity classification by selecting the efficient feature vector of the lower limb SEMG signal. Here, the SEMG signal-dependent continuous locomotion mode classification method has been proposed along with a dual-stage Feature Selection Algorithm (FSA). To evaluate the proposed method, SEMG signals of fifteen subjects were recorded from two lower limb muscles (Fibularis longus and Biceps Femoris) for five lower limb activities. The performance of six different classifiers was compared for intuitive feature vectors and FSA. The study analysed the performance of the proposed model for a single muscle approach and a dual muscle approach of activity classification. The time domain features were found more effective over other features, whereas Biceps Femoris muscle came out as a dominant muscle. The FSA enhanced the performance of classification model with fewer features as compared to intuitive feature subsets. Moreover, the dual muscle approach outperformed (p-value<0.05) over the single muscle approach. The best performance, for the dual muscle approach, was achieved 97.73 ± 2.47%, 98.99 ± 1.26% and 96.33 ± 2.70% for Neural Network, Linear Discriminant Analysis and Support Vector Machine classifiers, respectively (p-value > 0.05).

Keywords:

• Activity classification
• Feature set optimization
• Lower limb
• Surface electromyogram

Acknowledgements

The authors would like to extend his sincere gratitude to the Ministry of Electronics and Information Technology (MeitY), New Delhi for granting the Visvesvaraya Fellowship and Director, Thapar Institute of Engineering and Technology, Patiala for providing the required facilities to carry out current research work.

Additional information

Funding

This work was supported by Ministry of Electronics and Information technology.

Notes on contributors

Rohit Gupta

Rohit Gupta obtained PhD from Thapar Institute of Engineering and Technology, Patiala. Currently, he is a post-doctoral fellow at Indian Institute of Technology Delhi.

Inderjeet Singh Dhindsa

Inderjeet Singh Dhindsa obtained PhD from Thapar Institute of Engineering and Technology, Patiala. Currently, he is a lecturer at Government Polytechnic, Ambala City, India. E-mail: [email protected]

Ravinder Agarwal

Ravinder Agarwal is currently a professor in Electrical and Instrumentation Engineering Department at Thapar University, Patiala. He published more than 75 research papers in reviewed international journals of repute and more than 150 research publications in national and international conferences. E-mail: [email protected]