当前位置:文库下载 > 所有分类 > 工程科技 > 信息与通信 > Characteristic wave detection in ECG signal using morphological transform
免费下载此文档侵权投诉

Characteristic wave detection in ECG signal using morphological transform

数学形态学方法对心电信号进行滤波与识别

BMC Cardiovascular Disorders

Research article

BioMed Central

Open Access

Characteristic wave detection in ECG signal using morphological

transform

YanSun*1, KapLukChan2 and ShankarMuthuKrishnan

Address: 1Bioinformatics Institute, Singapore 138671 and 2Biomedical Engineering Research Center, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798

Email: YanSun*-sunyan@bii.a-star.edu.sg; KapLukChan-eklchan@ntu.edu.sg; ShankarMuthuKrishnan-eklchan@ntu.edu.sg* Corresponding author

Published: 20 September 2005BMC Cardiovascular Disorders 2005, 5:28

doi:10.1186/1471-2261-5-28

This article is available from: http://www.wenkuxiazai.com/1471-2261/5/28

Received: 24 January 2005Accepted: 20 September 2005

© 2005 Sun et al; licensee BioMed Central Ltd.

which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Background: Detection of characteristic waves, such as QRS complex, P wave and T wave, is oneof the essential tasks in the cardiovascular arrhythmia recognition from Electrocardiogram (ECG).Methods: A multiscale morphological derivative (MMD) transform-based singularity detector, isdeveloped for the detection of fiducial points in ECG signal, where these points are related to thecharacteristic waves such as the QRS complex, P wave and T wave. The MMD detector isconstructed by substituting the conventional derivative with a multiscale morphological derivative.Results: We demonstrated through experiments that the Q wave, R peak, S wave, the onsets andoffsets of the P wave and T wave could be reliably detected in the multiscale space by the MMDdetector. Compared with the results obtained via with wavelet transform-based and adaptivethresholding-based techniques, an overall better performance by the MMD method was observed.Conclusion: The developed MMD method exhibits good potentials for automated ECG signalanalysis and cardiovascular arrhythmia recognition.

Background

The detection of the major characteristic waves in ECG,namely the QRS complexes, P and T waves, is one of theessential tasks in ECG analysis. The performance of anautomated ECG analysis system depends heavily on thereliable detection of these fiducial waves. The difficultiesof characteristic waves detection lie in oscillations in thebaseline, irregular morphology of the waveforms, and fre-quency overlapping among the wide-band distribution ofthe characteristic waves [1], etc.

A significant amount of research effort has been devotedto the automated detection of the fiducial (reference)points of the ECG characteristic waves [2-12]. Most ofthese methods are filtering or adaptive thresholdingbased, which exhibit limitation in real application. Veryfew algorithms work well for the detection of all fiducialpoints such as the onsets and offsets of the P wave, T waveand the QRS complex (also known as the ECG waveboundaries). The main drawback of filtering-basedapproach is that frequency variations in the characteristicwaves often adversely affect its performance. The fre-quency distribution of QRS complexes generally overlapswith that of the noise, resulting in both false positive andfalse negative detections. The main problems of thethresholding techniques are their high noise sensitivityand their low efficiency when dealing with odd morphol-ogies. Therefore, more sophisticated signal processing

第1页

免费下载Word文档免费下载:Characteristic wave detection in ECG signal using morphological transform

(下载1-7页,共7页)

我要评论

返回顶部