A Framework for Empirical Fourier Decomposition-Based Gesture Classification for Stroke Rehabilitation

The demand for surface electromyography (sEMG)-based exoskeletons is rapidly increasing due to their noninvasive nature and ease of use. With increase in use of Internet of Things (IoT)-based devices in daily life, there is a greater acceptance of exoskeleton-based rehab. As a result, there is a need for highly accurate and generalizable gesture classification mechanisms based on sEMG data. In this work, we present a framework which preprocesses raw sEMG signals with empirical Fourier decomposition (EFD)-based approach followed by dimension reduction. This resulted in improved performance of the hand gesture classification. EFD decomposition’s efficacy of handling mode mixing problem on nonstationary signals, resulted in less number of decomposed components. In the next step, a thorough analysis of decomposed components as well as interchannel analysis is performed to identify the key components and channels that contribute toward the improved gesture classification accuracy. As a third step, we conducted ablation studies on time-domain features to observe the variations in accuracy on different models. Finally, we present a case study of comparison of automated feature extraction-based gesture classification versus manual feature extraction-based methods. Experimental results show that manual feature-based gesture classification method thoroughly outperformed automated feature extraction-based methods, thus emphasizing a need for rigorous fine tuning of automated models.