Multiscale Entropy Curve Analysis for ECG Signal

摘要：

Multiscale entropy (MSE) was proposed to measure the complexity of the physiological system. In general, distinguishing between the different complexities represented by MSE curves relies on human experience, but this practice is often confusing when curves have similar areas under the curve (AUC) or overlap. This study proposes to use clustering and control chart techniques to obtain the optimal features for recognizing the MSE curve. A real ECG signal data is used to present the proposed procedure. The results can be summarized in two points. The first is that the AUC is not the only important feature. Secondly, the methodology can effectively recognize the different physical conditions of the MSE curves.

关键词： multiscale entropy feature selection moving range ECG signal

作者: Cheng-Ding Chang Chien-Chih Wang Bernard C. Jiang

作者单位: Department of Industrial Engineering and Management, Yuan Ze University, Chung-Li,Taiwan, China Department of Industrial Engineering and Management, Ming Chi University of Technology,New Taipei Ci

会议类型: 国际会议

会议名称: The Institute Industrial Engineera Asian Conference 2011(2011年国际工业工程师协会亚洲会议)

会议地点: 上海

会议语种:英文

页码: 192-198

在线出版日期: 2011-06-10（万方平台首次上网日期，不代表论文的发表时间）