EMG subspace alignment and visualization for cross-subject hand gesture classification
This work addresses calibration inefficiencies in human/machine interfaces for users of EMG-based systems, though it is incremental in nature.
The paper tackled the problem of long calibration times for new users in EMG-based hand gesture recognition by proposing a method to improve cross-subject generalization through subspace alignment, achieving improved estimation results as demonstrated on a dataset of 14 subjects.
Electromyograms (EMG)-based hand gesture recognition systems are a promising technology for human/machine interfaces. However, one of their main limitations is the long calibration time that is typically required to handle new users. The paper discusses and analyses the challenge of cross-subject generalization thanks to an original dataset containing the EMG signals of 14 human subjects during hand gestures. The experimental results show that, though an accurate generalization based on pooling multiple subjects is hardly achievable, it is possible to improve the cross-subject estimation by identifying a robust low-dimensional subspace for multiple subjects and aligning it to a target subject. A visualization of the subspace enables us to provide insights for the improvement of cross-subject generalization with EMG signals.