Online Decomposition of Surface Electromyogram Into Individual Motor Unit Activities Using Progressive FastICA Peel-Off.

Surface electromyogram (SEMG) decomposition provides a promising tool for decoding and understanding neural drive information non-invasively. In contrast to previous SEMG decomposition methods mainly developed in offline conditions, there are few studies on online SEMG decomposition. A novel method for online decomposition of SEMG data is presented using the progressive FastICA peel-off (PFP) method. The proposed online method utilized a two-stage approach, consisting of an offline prework stage for initializing high-quality separation vectors through the offline PFP algorithm, and an online decomposition stage for estimating source signals of different motor units by applying these vectors to the input SEMG data stream. Specifically, a new successive multi-threshold Otsu algorithm was developed in the online stage for determining each motor unit spike train (MUST) precisely with fast and simple computations (to replace a time-consuming iterative threshold setting in the original PFP method). The performance of the proposed online SEMG decomposition method was evaluated by both simulation and experimental approaches. When processing simulated SEMG data, the online PFP method achieved a decomposition accuracy of 97.37%, superior to that (95.1%) of an online method with a traditional k-means clustering algorithm for MUST extraction. Our method was also found to achieve superior performance at higher noise levels. For decomposing experimental SEMG data, the online PFP method was able to extract an average of 12.00 ± 3.46 MUs per trial, with a matching rate of 90.38%, with respect to the expert-guided offline decomposition results. Our study provides a valuable way of online decomposition of SEMG data with advanced applications in movement control and health.