AUTHOR=Wu Le , Chen Xun , Chen Xiang , Zhang Xu 

TITLE=Rejecting Novel Motions in High-Density Myoelectric Pattern Recognition Using Hybrid Neural Networks

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2022.862193

DOI=10.3389/fnbot.2022.862193

ISSN=1662-5218

ABSTRACT=The objective of this work is to develop a method for alleviating novel pattern interference toward achieving a robust myoelectric pattern-recognition control system. To this end, a framework was presented for surface electromyogram (sEMG) pattern classification and novelty detection using hybrid neural networks, i.e., a convolutional neural network (CNN) and auto-encoder networks. In the framework, the CNN was first used to extract spatio-temporal information convoyed in the sEMG data recorded via high-density (HD) 2-dimentional electrode arrays. Given the target motion patterns well characterized by the CNN, then, autoencoder networks were applied to learn variable correlation in the spatio-temporal information, where samples from any novel pattern appeared to be significantly different from those from target patterns. Therefore, it was straightforward to discriminate and then reject the novel motion interferences identified as untargeted and unlearnt patterns. The performance of the proposed method was evaluated with HD-sEMG data recorded by two 8×6 electrode arrays placed over the forearm extensors and flexors of 9 subjects performing 7 target motion tasks and 6 novel motion tasks. The proposed method achieved high accuracies over 95% for identifying and rejecting novel motion tasks, and it outperformed conventional methods, with statistical significance (p < 0.05). The proposed method is demonstrated to be a promising solution for rejecting novel motion interferences which is ubiquitous in myoelectric control. This work will enhance the robustness of myoelectric control system against novelty interference.