An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals
This work addresses data scarcity in sEMG-based applications like prosthetics control, but it is incremental as it builds on existing deep learning methods with a hybrid approach.
The paper tackled the problem of hand movement recognition from sEMG signals by proposing a feature-imitating network (FIN) to reduce the need for large labeled datasets, achieving 80% accuracy in recognition and 99% R2 accuracy in feature reconstruction.
Surface Electromyography (sEMG) is a non-invasive signal that is used in the recognition of hand movement patterns, the diagnosis of diseases, and the robust control of prostheses. Despite the remarkable success of recent end-to-end Deep Learning approaches, they are still limited by the need for large amounts of labeled data. To alleviate the requirement for big data, we propose utilizing a feature-imitating network (FIN) for closed-form temporal feature learning over a 300ms signal window on Ninapro DB2, and applying it to the task of 17 hand movement recognition. We implement a lightweight LSTM-FIN network to imitate four standard temporal features (entropy, root mean square, variance, simple square integral). We observed that the LSTM-FIN network can achieve up to 99\% R2 accuracy in feature reconstruction and 80\% accuracy in hand movement recognition. Our results also showed that the model can be robustly applied for both within- and cross-subject movement recognition, as well as simulated low-latency environments. Overall, our work demonstrates the potential of the FIN modeling paradigm in data-scarce scenarios for sEMG signal processing.