期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：8
页码：15660
DOI：10.15680/IJIRSET.2017.0608019
出版社：S&S Publications
摘要：Nowadays, the rate of disabled and the people who find difficulties in using their limbs due to age areincreasing. Recent literature in pattern recognition-based myoelectriccontrol has highlighted a disparity betweenclassificationaccuracy and the usability of upper limb prostheses. This paper suggests that the conventionally definedclassification accuracy may be idealistic and may not reflect true clinical performance. An accurate andcomputationally efficient means of classifying electromyographic(EMG) signal patterns has been the subject ofconsiderable research effort in recent years.Herein, a novel myoelectric control system based on SVM and ANNclassification scheme, capable of rejecting unknown data patterns, is introduced. This scheme is shown to outperformother popular classifiers when compared using conventional classification accuracy analysis that may be morerepresentative of real prosthetic use. Additionally, the classification scheme allows for real-time, independentadjustment of individual class-pair boundaries making it flexible and intuitive for clinical use.
