基于表面肌电信号双谱分析的动作分类-北京工业大学学报.pdfVIP

第43卷 第7期 北 京 工 业 大 学 学 报 Vol.43 No.7 2017年 7月 JOURNAL OF BEIJING UNIVERSITY OFTECHNOLOGY Jul. 2017 基于表面肌电信号双谱分析的动作分类 孙光民,闫正祥,张俊杰,马北川,李摇 俊,姜摇 明,刘天伦,张摇 翼 (北京工业大学信息学部,北京摇 100124) 摘摇 要:为了提高人体上肢动作识别正确率,提出了一种基于表面肌电信号双谱分析的动作分类方法,以信息增益 作为表面肌电信号起止点分割效果衡量标准,结合TKE算子提取出肌肉运动起止区间的表面肌电信号,对提取到 的表面肌电信号进行双谱变换,提取双谱的正反对角切片作为表面肌电信号特征,以概率神经网络作为分类器,以 100次10折交叉验证为一次动作分类实验,计算10次分类实验的平均正确率,最终得到正对角切片、反对角切片 和正反对角切片的分类正确率分别为94郾56%、90郾93%和95郾48%. 关键词:表面肌电信号;TKE算子;信息增益;双谱分析;动作分类 中图分类号:TP391 文献标志码:A 文章编号:0254-0037(2017)07-1045-06 doi:10.11936/ bjutxb2016120011 Motion Classification Based on Bispectrum Analysis of Surface EMG Signal SUNGuangmin,YANZhengxiang,ZHANGJunjie,MA Beichuan,LIJun,JIANGMing,LIUTianlun,ZHANGYi (Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China) Abstract:In order to improve the accuracy of upper limb movement recognition,an action classification method based on bispectrum analysis of surface EMG signals was presented in this paper. Information gain was used as the measure criterion of the surface EMG start and end signal segmentation. The segmented signal was extracted by the TKE operator, then the extracted signals were bispectrum鄄 transformed,and bispectrum sliceswere extracted as the surface EMGfeatures. The probabilistic neural network was used as the classifier,with 100 times 10鄄fold cross validation as an action classification experiment,andtheaveragecorrectrateof 10 timeswascalculated. Thecorrectratesof classificationfor diagonal slices,secondary diagonal slices and bi鄄diagonal slices were 94郾56%,90郾83% and 95郾48% respectively. Key words:surface electromyography;Teager鄄Kaiser energy operation