二维主元分析法在心肌梗死心电信号检测中的应用  

The Application of Two Dimensional in the Detection of Myocardial Principal Component Analysis Infarction ECG Signals

作　　者：葛丁飞[1] 徐爱群[2] 

机构地区：[1]浙江科技学院信息与电子工程学院,浙江杭州310012 [2]浙江科技学院机械与汽车工程学院,浙江杭州310012

出　　处：《计量学报》2014年第3期252-257,共6页Acta Metrologica Sinica

基　　金：基金项目：国家自然科学基金（61074143）;浙江省自然科学基金（Y1100219）;浙江科技学院学科交叉预研专项重点项目（2012JCOIZ）

摘　　要：利用基于联合能量百分比搜索的二维主元分析法对12导高分辨率心电信号（ECG）进行全局特征提取和分类检测研究。所用数据取自PTB诊断数据库，包括健康状态ECG，早期心肌梗死（MI）ECG，急性期MIECG，恢复期MIECG。结果表明，所用的方法能有效地融合12导ECG信号及其高频分量中的细微结构信息，与常规主元分析法相比，其平均分类检测精度可提高10．43％，与常规二维主元分析法相比，能得到维数更低的特征表示，并可获得99．46％的平均分类检测精度。The joint energy percentage（EP） search method based on two dimensional principal component analysis is introduced to extract global features from 12-lead high resolution electrocardiogram（ECG） for the purpose of classification. Four types of classes are collected from PTB clinical diagnostic database, which corresponding patient＇ s statuses are health control, myocardial infarction （MI） in early stage, MI in acute stage and MI in recover stage, respectively. The experimental results show that the information can be fused efficiently using the proposed method, which are from 12-lead ECG and the details contained in high frequency components of ECG. The average classification accuracy can be increased by 10. 43% compared with that of conventional principal component analysis. The ECG signal can be represented with lower dimensions compared with that of independent EP criterion, and an average classification accuracy of 99.46% can be achieved.

关 键 词：计量学 心电信号 主元分析 心肌梗死 特征提取 

分 类 号：TB97[一般工业技术—计量学]