Heartbeat Case Determination Using Cluster Analysis Method on ECG Signals

• Main Authors: Tsui-Shiun Chu, 楚萃勛
• Other Authors: 葉雲奇
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/83867713853757549790

碩士 === 健行科技大學 === 電子工程所 === 101 === In this dissertation, some novel and efficient algorithms in three related research topics about ECG signals will be presented and discussed. In the first research topic, a simple and reliable method, called the finite-impulse-response (FIR), is proposed to detect the QRS complex of an electrocardiogram (ECG) signal. In the second research topic, qualitative feature selection from ECG signals using the Principal Component Analysis (PCA) method. In the third research topic, Cluster Analysis is applied for classifying the cardiac arrhythmia on ECG signals. The proposed methods can accurately classify the normal heartbeats and abnormal heartbeats. Abnormal heartbeats include Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Ventricular Premature Contractions (VPC) and Atrial Premature Contractions (APC). The proposed methods were evaluated using the MIT-BIH arrhythmia database and have the following advantages: (1) The average time required for processing 30-minute long records of ECG signals is less than 1 minute; (2) The maximum memory requirement is only about 10 MB; (3) Good detection results. In the experiments, the sensitivity is 95.59%, 91.32%, 90.50%, 94.51%, and 93.77% for heartbeat cases NORM, LBBB, RBBB, VPC, and APC, respectively. The total classification accuracy was approximately 94.30%.