Adaptive Online Decomposition of Surface EMG Using Progressive FastICA Peel-Off
Haowen Zhao, Xu Zhang, Maoqi Chen, Ping Zhou
Abstract
This study presents a method for adaptive online decomposition of high-density surface electromyogram (SEMG) signals to overcome the performance degradation during long-term recordings. The proposed method utilized the progressive FastICA peel-off (PFP) method and integrated a practical double-thread-parallel algorithm into the conventional two-stage calculation approach. During the offline initialization stage, a set of separation vectors was computed. In the subsequent online decomposition stage, a backend thread was implemented to periodically update the separation vectors using the constrained FastICA algorithm and the automatic PFP method. Concurrently, the frontend thread employed the newly updated separation vectors to accurately extract motor unit (MU) spike trains in real time. To assess the effectiveness of the proposed method, simulated and experimental SEMG signals from abductor pollicis brevis muscles of ten subjects were used for evaluation. The results demonstrated that the proposed method outperformed the conventional method, which relies on fixed separation vectors. Specifically, the proposed method showed an improved matching rate by 3.63% in simulated data and 1.98% in experimental data, along with an increased motor unit number by 2.39 in simulated data and 1.30 in experimental data. These findings illustrated the feasibility of the proposed method to enhance the performance of online SEMG decomposition. As a result, this work holds promise for various applications that require accurate MU firing activities in decoding neural commands and building neural-machine interfaces.