Light-weighted CNN-Attention based architecture for Hand Gesture Recognition via ElectroMyography

TL;DR

This paper introduces a lightweight CNN-attention hybrid model for hand gesture recognition using sEMG signals, achieving state-of-the-art accuracy with significantly fewer parameters suitable for wearable devices.

Contribution

A novel hybrid CNN-attention architecture (HDCAM) that is lightweight and efficient, outperforming previous models in hand gesture recognition accuracy.

Findings

Achieved 82.91% and 81.28% accuracy on two window sizes.

Model has 18.87 times fewer parameters than previous SOTA.

Effective local and global feature extraction for gesture classification.

Abstract

Advancements in Biological Signal Processing (BSP) and Machine-Learning (ML) models have paved the path for development of novel immersive Human-Machine Interfaces (HMI). In this context, there has been a surge of significant interest in Hand Gesture Recognition (HGR) utilizing Surface-Electromyogram (sEMG) signals. This is due to its unique potential for decoding wearable data to interpret human intent for immersion in Mixed Reality (MR) environments. To achieve the highest possible accuracy, complicated and heavy-weighted Deep Neural Networks (DNNs) are typically developed, which restricts their practical application in low-power and resource-constrained wearable systems. In this work, we propose a light-weighted hybrid architecture (HDCAM) based on Convolutional Neural Network (CNN) and attention mechanism to effectively extract local and global representations of the input. The proposed HDCAM model with 58,441 parameters reached a new state-of-the-art (SOTA) performance with 82.91% and 81.28% accuracy on window sizes of 300 ms and 200 ms for classifying 17 hand gestures. The number of parameters to train the proposed HDCAM architecture is 18.87 times less than its previous SOTA counterpart.