Attention-Based Convolutional Neural Network Model for Human Lower Limb Activity Recognition using sEMG

TL;DR

This paper introduces a lightweight attention-based deep neural network for real-time classification of lower limb movements using sEMG signals, achieving high accuracy with minimal computational resources.

Contribution

The study presents a novel, efficient deep neural network model that does not require extensive preprocessing, suitable for real-time human movement recognition from sEMG data.

Findings

Achieved 86.74% validation accuracy and 85.38% test accuracy.

Model contains only 62,876 parameters, enabling real-time deployment.

Outperforms existing models in efficiency and effectiveness.

Abstract

Accurate classification of lower limb movements using surface electromyography (sEMG) signals plays a crucial role in assistive robotics and rehabilitation systems. In this study, we present a lightweight attention-based deep neural network (DNN) for real-time movement classification using multi-channel sEMG data from the publicly available BASAN dataset. The proposed model consists of only 62,876 parameters and is designed without the need for computationally expensive preprocessing, making it suitable for real-time deployment. We employed a leave-oneout validation strategy to ensure generalizability across subjects, and evaluated the model on three movement classes: walking, standing with knee flexion, and sitting with knee extension. The network achieved 86.74% accuracy on the validation set and 85.38% on the test set, demonstrating strong classification performance under realistic conditions. Comparative analysis with existing models in the literature highlights the efficiency and effectiveness of our approach, especially in scenarios where computational cost and real-time response are critical. The results indicate that the proposed model is a promising candidate for integration into upper-level controllers in human-robot interaction systems.