Multiple ECG Beats Recognition in the Frequency Domain Using Grey Relational Analysis

Author

Lin, Chia Hung ; Du, Yi Chun ; Chen, Yung Fu ; Chen, Tain Song

Author_Institution

Dept. of Electr. Eng., Kao-Yuan Univ., Kaohsiung

fYear

2006

fDate

Aug. 30 2006-Sept. 3 2006

Firstpage

2154

Lastpage

2158

Abstract

This paper proposes a method for multiple ECG beats recognition using novel grey relational analysis (GRA). Converts each QRS complex to a Fourier spectrum from ECG signals, the spectrum varies with the rhythm origin and conduction path. The variations of power spectra are observed in the range of 0 Hz-20 Hz in the frequency domain. According to the frequency-domain parameters, GRA performs to recognize the cardiac arrhythmias including the supraventricular ectopic beat, bundle branch ectopic beat, ventricular ectopic beat, and fusion beat. The method was tested on MIT-BIH arrhythmia database. The results demonstrate the efficiency of the proposed non-invasive method, and also show high accuracy for detecting electrocardiogram (ECG) signals

Keywords

Fourier analysis; cardiovascular system; electrocardiography; frequency-domain analysis; medical signal detection; medical signal processing; pattern recognition; relational databases; 0 to 20 Hz; Fourier spectrum; MIT-BIH arrhythmia database; QRS complex; bundle branch ectopic beat; cardiac arrhythmias; cardiac rhythm origin; conduction path; electrocardiogram signal detection; frequency domain analysis; fusion beat; grey relational analysis; multiple ECG beats recognition; supraventricular ectopic beat; ventricular ectopic beat; Artificial neural networks; Electrocardiography; Electrodes; Frequency domain analysis; Heart rate variability; Rhythm; Robustness; Signal analysis; Signal processing; Time frequency analysis; Cardiac Arrhythmia; Frequency Domain; Grey Relational Analysis (GRA);

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2006. EMBS '06. 28th Annual International Conference of the IEEE

Conference_Location

New York, NY

ISSN

1557-170X

Print_ISBN

1-4244-0032-5

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2006.260019

Filename

4462215