论文部分内容阅读
动作表面肌电(SEMG)信号是一种从皮肤表面采集的复杂电信号,它的模式识别在人体假肢和人—计算机交互系统等实际应用中非常重要。为了提高识别率,提出一种将模糊熵(FuzzyEn)和多尺度分析相结合的方法。该方法从动作SEMG信号非线性和非平稳特性的角度出发,引入了多尺度模糊熵(MSFuzzyEn)特征,并应用到人体前臂六类动作SEMG信号的模式识别中。首先利用小波分解对原始信号进行多尺度分解。然后计算MSFuzzyEn并将其作为特征向量输入支持向量机(SVM)进行识别,平均识别率达到97%,比利用原始信号的FuzzyEn进行识别时提高3%。结果表明,利用MSFuzzyEn对动作SEMG信号进行模式识别效果良好。
The Surface Electromyography (SEMG) signal is a complex electrical signal acquired from the skin surface and its pattern recognition is very important in practical applications such as human prostheses and human-computer interaction systems. In order to improve the recognition rate, a method combining fuzzy entropy and multi-scale analysis is proposed. The method introduces the multi-scale fuzzy entropy (MSFuzzyEn) feature from the viewpoint of the nonlinear and non-stationary characteristics of the moving SEMG signal and applies it to the pattern recognition of the six types of human forearm SEMG signals. First, the original signal is decomposed by multi-scale using wavelet decomposition. The MSFuzzyEn is then calculated and input as Support Vector Machine (SVM) as the feature vector. The average recognition rate is 97%, which is 3% higher than that of the original signal FuzzyEn. The results show that the use of MSFuzzyEn on the action SEMG signal pattern recognition is good.