FANet: Frequency-based Attention Networks for sEMG Hand Gesture Classification

(Will be updated soon)

Created by

This repository contains PyTorch implementation for Frequency-based attention network for sEMG Hand Gesture Classification (IEEE SPL & IEEE RA-L (under-review)).

Dataset

1. NinaPro DB5 Dataset

NinaPro is a publicly available multimodal database aimed at fostering machine learning research on human, robotic & prosthetic hands. You can download the NinaPro DB5 at https://ninapro.hevs.ch.

2. Custom ASR Gesture Dataset

The data is collected using Mindrove Armband on 6 distinct subjects. It can be downloaded at here.

Citation

If you find our work useful in your research, please consider citing:

• P. T. -T. Nguyen and C. -H. Kuo, "A Novel Surface Electromyographic Gesture Recognition Using Discrete Cosine Transform-Based Attention Network," in IEEE Signal Processing Letters, vol. 31, pp. 266-270, 2024, doi: 10.1109/LSP.2023.3348298.