The application of wavelet and feature vectors to ECG signals

Aya Matsuyama; Mirjam Jonkman

doi:10.1109/TENCON.2005.300875

The application of wavelet and feature vectors to ECG signals

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

Abstract

The Electrocardiogram (ECG) is one of the most commonly known biological signals, which are traditionally analyzed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis transforms signals into frequency domain, but has the disadvantage that time characteristics will become unobvious. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. In this paper, Arrhythmia ECG signals were examined. There were two stages in analyzing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalized energy and entropy were constructed. Vector quantisation technique was applied to these feature vectors to classify signals. The results showed that Normal Sinus Rhythm ECGs and Arrhythmia ECGs composed different clusters.

Original language	English
Title of host publication	TENCON 2005 - 2005 IEEE Region 10 Conference
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	4
Volume	2007
ISBN (Print)	0780393112, 9780780393110
DOIs	https://doi.org/10.1109/TENCON.2005.300875
Publication status	Published - 31 May 2007
Event	TENCON 2005 - 2005 IEEE Region 10 Conference - Melbourne, Australia Duration: 21 Nov 2005 → 24 Nov 2005

Conference

Conference	TENCON 2005 - 2005 IEEE Region 10 Conference
Country/Territory	Australia
City	Melbourne
Period	21/11/05 → 24/11/05

Access to Document

10.1109/TENCON.2005.300875

Cite this

@inproceedings{0da1d618e2994b158b8825aca321a5cf,

title = "The application of wavelet and feature vectors to ECG signals",

abstract = "The Electrocardiogram (ECG) is one of the most commonly known biological signals, which are traditionally analyzed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis transforms signals into frequency domain, but has the disadvantage that time characteristics will become unobvious. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. In this paper, Arrhythmia ECG signals were examined. There were two stages in analyzing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalized energy and entropy were constructed. Vector quantisation technique was applied to these feature vectors to classify signals. The results showed that Normal Sinus Rhythm ECGs and Arrhythmia ECGs composed different clusters.",

keywords = "ECG, Feature vector, Normalized energy, Vector quantisation, Wavelet",

author = "Aya Matsuyama and Mirjam Jonkman",

note = "Later published in Australasian Physical and Engineering Sciences in Medicine.; TENCON 2005 - 2005 IEEE Region 10 Conference ; Conference date: 21-11-2005 Through 24-11-2005",

year = "2007",

month = may,

day = "31",

doi = "10.1109/TENCON.2005.300875",

language = "English",

isbn = "0780393112",

volume = "2007",

booktitle = "TENCON 2005 - 2005 IEEE Region 10 Conference",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - The application of wavelet and feature vectors to ECG signals

AU - Matsuyama, Aya

AU - Jonkman, Mirjam

N1 - Later published in Australasian Physical and Engineering Sciences in Medicine.

PY - 2007/5/31

Y1 - 2007/5/31

N2 - The Electrocardiogram (ECG) is one of the most commonly known biological signals, which are traditionally analyzed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis transforms signals into frequency domain, but has the disadvantage that time characteristics will become unobvious. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. In this paper, Arrhythmia ECG signals were examined. There were two stages in analyzing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalized energy and entropy were constructed. Vector quantisation technique was applied to these feature vectors to classify signals. The results showed that Normal Sinus Rhythm ECGs and Arrhythmia ECGs composed different clusters.

AB - The Electrocardiogram (ECG) is one of the most commonly known biological signals, which are traditionally analyzed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis transforms signals into frequency domain, but has the disadvantage that time characteristics will become unobvious. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. In this paper, Arrhythmia ECG signals were examined. There were two stages in analyzing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalized energy and entropy were constructed. Vector quantisation technique was applied to these feature vectors to classify signals. The results showed that Normal Sinus Rhythm ECGs and Arrhythmia ECGs composed different clusters.

KW - ECG

KW - Feature vector

KW - Normalized energy

KW - Vector quantisation

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=34249321933&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2005.300875

DO - 10.1109/TENCON.2005.300875

M3 - Conference Paper published in Proceedings

SN - 0780393112

SN - 9780780393110

VL - 2007

BT - TENCON 2005 - 2005 IEEE Region 10 Conference

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - TENCON 2005 - 2005 IEEE Region 10 Conference

Y2 - 21 November 2005 through 24 November 2005

ER -

The application of wavelet and feature vectors to ECG signals

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this