Feature extraction of ECG signal

Author

Peshave, Juie D. ; Shastri, Rajveer

Author_Institution

Electron. & Telecommun. Dept., Univ. of Pune, Pune, India

fYear

2014

fDate

3-5 April 2014

Firstpage

1864

Lastpage

1868

Abstract

Electrocardiogram (ECG) is one the important biomedical signal. One heartbeat of ECG consists of different segments such as QRS complex, ST segment and PR segment. Features of an ECG signal are nothing but these segments and intervals between fiducial points such as RR interval, amplitude of P, R and T wave. Several techniques are discovered and are still developing for analyzing ECG signal. Some of them are Continuous Wavelet Transform, Discrete Wavelet Transform and Pan Tompkin´s Algorithm. In this paper, with the help of extracted dynamic feature 3 different types of arrhythmia have been detected using discrete wavelet transform and thresholding method. This system is validated on standard MIT-BIH arrhythmia database and it yields about 85% of sensitivity.

Keywords

discrete wavelet transforms; electrocardiography; feature extraction; medical disorders; medical signal processing; ECG heartbeat; ECG signal; MIT-BIH arrhythmia database; P wave amplitude; PR segment; Pan Tompkin´s algorithm; QRS complex; R wave amplitude; RR interval; ST segment; T wave amplitude; biomedical signal; continuous wavelet transform; discrete wavelet transform; electrocardiogram; extracted dynamic feature; feature extraction; thresholding method; Databases; Electrocardiography; Monitoring; Sensitivity; Wavelet analysis; Discrete Wavelet Transform(DWT); Electrocardiograph; Feature extraction; Thresholding method;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing (ICCSP), 2014 International Conference on

Conference_Location

Melmaruvathur

Print_ISBN

978-1-4799-3357-0

Type

conf

DOI

10.1109/ICCSP.2014.6950168

Filename

6950168