2011 | OriginalPaper | Chapter
EMG Classification for Application in Hierarchical FES System for Lower Limb Movement Control
Authors : Dingguo Zhang, Ying Wang, Xinpu Chen, Fei Xu
Published in: Intelligent Robotics and Applications
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
This paper proposes a functional electrical stimulation (FES) system based on electromyogram (EMG) classification, which aims to serve for the hemiplegia or incomplete paralyzed patients. This is a hierarchical system and the controller contains three levels. This work focuses on EMG signal processing in order to get the motion intention. Autoregressive (AR) feature, time domain statistics (TDS), and discriminant fourier feature (FC) are adopted as the EMG features. Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) are used as the classifier. The performances of motion recognition are compared on three subjects. We find the FC feature generally has the best performance. Preliminary FES experiment is conducted on a healthy subject.