ABSTRACT
BACKGROUND AND OBJECTIVES: Surface Electromyography (sEMG) is used mostly for neuromuscular diagnosis, assistive technology, physical rehabilitation, and human-computer interactions. Achieving a precise and lightweight method along with low latency for gesture recognition is still a real-life challenge, especially for rehabilitation and assistive robots. This work aims to introduce a highly accurate and lightweight deep learning method for gesture recognition. METHODS: High-density sEMG, unlike sparse sEMG, does not require accurate electrode placement and provides more physiological information. Then we apply high-density sEMG, which, according to previous studies, leads to sEMG images. In this study, we introduce the Sensor-Wise method, which has a higher capability to extract features compared to the sEMG image method due to its high compatibility with the nature of sEMG signals and the structure of convolutional networks. RESULTS: The proposed method, because of its optimal structure with only two hidden layers and its high compatibility, has shown no sign of overfitting and was able to reach an accuracy of almost 100% (99.99%) when it was evaluated by CapgMyo DB-a database through 96 electrodes. Using this method, even with 16 electrodes, we were able to reach an accuracy of 99.8%, which was higher than the accuracies reported in the previous studies. Additionally, the method was evaluated by the CSL-HDEMG database, where the accuracy reached 99.55%. Previous studies either introduced expensive computational methods with overfitting or reported lower accuracies compared to this study. CONCLUSIONS: The Sensor- Wise method has high compatibility with the nature of sEMG signals and the structure of convolutional networks. The high accuracy and lightweight structure of this method with only two hidden layers make it a proper option for hardware implementation.
