计量学报Issue(6)：534-539,6.DOI:10.3969/j.issn.1000-1158.2014.06.03
基于经验模态分解样本熵的肌电信号识别
EMG SignaI Recognition Based on EMD SampIe Entropy
摘要
Abstract
AccOrding tO the chaOtic and nOnIinear characteristics Of surface eIectrOmyOgraphy( sEMG ),a fast and efficient hands mOvement sEMG pattern recOgnitiOn methOd fOr reaI-time cOntrOI Of myOeIectric prOsthetic hand is designed. A muIti-mOdeIing pattern recOgnitiOn methOd Of sEMG features based On the empiricaI mOde decOmpOsitiOn( EMD ) sampIe entrOpy and cIustering anaIysis is prOpOsed. First,it decOmpOses the sEMG signaI intO a set Of intrinsic mOde functiOns ( IMF),then cOmbines sOme Of the IMF which cOntains the usefuI infOrmatiOn accOrding tO frequency effectiveness,and caIcuIates the sampIe entrOpy Of the cOmbinatiOn. The sampIe entrOpy Of twO sEMG Of the extensOr carpi uInaris and fIexOr carpi uInaris cOnstitute the feature vectOr,the cIustering cIassifier which based On principaI axis cIustering arithmetic is appIied tO cIassify the fOur hand mOvements. The resuIt shOws that fOur mOvements( hand extensiOn,hand grasps,wrist spreads and wrist bends ) are successfuIIy identified. The average recOgnitiOn rate is 93%. The methOd achieved high recOgnitiOn rate,anti-interference abiIity and Iess cOmputatiOn,that is suitabIe fOr the cOntrOI Of the myOeIectric prOsthetic hand.关键词
计量学/表面肌电信号/经验模式分解/样本熵/聚类分析/模式识别Key words
MetrOIOgy/Surface eIectrOmyOgraphy/EmpiricaI mOde decOmpOsitiOn/SampIe entrOpy/CIustering anaIysis/Pattern recOgnitiOn分类
通用工业技术引用本文复制引用
席旭刚,朱海港,罗志增,张启忠..基于经验模态分解样本熵的肌电信号识别[J].计量学报,2014,(6):534-539,6.基金项目
国家自然科学基金（60903084，61172134，61201300）；浙江省自然科学基金（LY13F030017）；浙江省科技计划项目 （）
