欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为提高肢体运动模式识别率,基于肌电信号的产生机理提出了选用信号的形态特征实现肌电信号模式识别的新方案。方案以分形理论中关联维及分维数的概念分别表征肌电信号的复杂度及自相似性,其中关联维的计算采用了一种改进的G-P算法、即G-P关联维逼近法;在手部动作模式识别中,以关联维和分维数作为表面肌电信号的特征向量,分类器采用由对支持向量机构造的二叉树结构多类分类器。针对手部张开、合拢及腕伸、腕屈4种运动模式的识别实验,该方法的正确识别率达到了91.0%,已具备一定的实用性。
英文摘要：
This paper is aimed at raising the pattern recognition rate of physical movement based on electromyography（ EMG ）signal generation mechanism by presenting a new method of pattern recognition in accordance with EMG morphological characteristics. The complexity and self-similarity of the EMG are represented by the concepts of correlation dimension and fractal dimension in the fractal theory respectively. The calculation of the correlation dimension adopts an improved G-P algorithm, named G-P correlation dimension approximation method. In hand gestures pattern recognition, the combination of correlation dimension and fractal dimension is used as an input eigenvector of multi-pattern recognition classifier and the binary-tree architecture classifier is constructed with twin support vector machines （TSVM）. The experiment, designed to classify four hand gestures including hand open, hand grasp, wrist extension and wrist flexion, shows that by using this method, the recognition rate has reached 91.0% ,which demonstrates the practicality of this approach.
同期刊论文项目
同项目期刊论文
期刊信息
位置：