Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Authors : Xini HU, Jiangming KAN, Wenbin LI

Pages : 732-742

View : 23 | Download : 12

Publication Date : 0000-00-00

Article Type : Research Paper

Abstract :This paper presents a novel classification approach for surface electromyogram insert ignore into journalissuearticles values(sEMG); signals. The proposed classification approach involves two steps: insert ignore into journalissuearticles values(1); feature extraction from an sEMG, in which a 7-dimensional feature vector is extracted from 27 types of features of the sEMG by linear discriminant analysis insert ignore into journalissuearticles values(LDA);, and insert ignore into journalissuearticles values(2); a novel classifier, DAGSVMerr, based on a directed acyclic graph insert ignore into journalissuearticles values(DAG); and support vector machine insert ignore into journalissuearticles values(SVM);, in which a separability measure function based on erroneous recognition rates insert ignore into journalissuearticles values(ERRs); is defined to determine the initial operation list. The proposed approach takes advantage of the feedback idea to improve the performance of the classification. The experimental results show that the proposed approach has a better performance than traditional methods, and it achieves an average classification accuracy rate of 99.4%$\, {\pm \, }$1.3% with an error rate of 0.6%. Correct classification rates of the proposed approach are very high, and the approach can be utilized to recognize gesture instructions by analyzing sEMG signals in gesture equipment control studies.
Keywords : Surface electromyogram, classification, directed acyclic graph, support vector machine