AUTHOR=Zhao Dazheng , Ma Yehao , Meng Jingyan , Hu Yang , Hong Mengqi , Zhang Jiaji , Zuo Guokun , Lv Xiao , Liu Yunfeng , Shi Changcheng 

TITLE=MCR-ALS-based muscle synergy extraction method combined with LSTM neural network for motion intention detection

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2023.1174710

DOI=10.3389/fnbot.2023.1174710

ISSN=1662-5218

ABSTRACT=The time-varying and individual variability of surface electromyographic signals (sEMG) can lead to poorer motor intention detection results from different subjects and longer temporal intervals between training and testing datasets. The consistency of using muscle synergy between the same tasks may be beneficial to improve the detection accuracy over long time ranges. However, the initialization randomness of the conventional non-negative matrix decomposition (NMF) in muscle synergy analysis affects its application in the field of motor intention detection, especially in the continuous estimation of upper limb joint angles. In this study, we proposed a reliable multivariate curve-resolved-alternating least squares (MCR-ALS) muscle synergy extraction method combined with long-short term memory neural network (LSTM) to estimate continuous elbow joint motion by using the sEMG datasets from different subjects and different days. The sEMG signals of three muscles in the upper arm were recorded. Meanwhile, the acceleration signals of the upper arm motion were also acquired to calculate the elbow joint angular movements. The pre-processed sEMG signals were then decomposed into muscle synergies by MCR-ALS and NMF methods, and the decomposed muscle activation matrices were used as sEMG features. The sEMG features and elbow joint angular signals were input to LSTM to establish a neural network model. Finally, the established neural network models were tested by using sEMG dataset from different subjects and different days, and the detection accuracy was measured by correlation coefficient. The results showed that this method can improve the accuracy of motor intention detection results from different subjects and different acquisition timepoints.