Cardiac Arrhythmia Diagnosis on ECG Signals using Weighted Principal Component Analysis

摘要：

　　This study proposes a simple and reliable method for diagnosing cardiac arrhythmias by analyzing ECG signals.The proposed method consists of three major processing stages:(i)QRS extraction stage for detecting QRS waveform;(ii)qualitative features stage for qualitative feature selection; and(iii)classification stage for determining patients heartbeat cases using the Weighted Principal Component Analysis(WPCA).This study introduces a new weight computation procedure for the WPCA training and decision.Both mean and variance of the qualitative features are used to calculate the principal eigenvectors of this WPCA.Records of MIT-BIH database are used for performance evaluation.Simulation results show that the total classification accuracy is approximately 93.19%.The proposed WPCA method has advantages of good detection results,no complicated mathematic computations,high speed and low memory space,and high reliability.

关键词： Weighted Principal Component Analysis (WPCA) Eigen-decomposition MIT-BIH arrhythmia database Electrocardiogram (ECG)

作者: Yun-Chi Yeh Yi Chu Wan-Teseng Chang

作者单位: Department of Electronic Engineering Chien Hsin University of Science and Technology,Zhongli,Taiwan 320

会议类型: 国际会议

会议名称: The 2014 ICME International Conference on Complex Medical Engineering (CME2014)ICME复合医学工程国际会议

会议地点: 台北

会议语种:英文

页码: 357-362,164

在线出版日期: 2014-06-26（万方平台首次上网日期，不代表论文的发表时间）