DocumentCode
2360116
Title
Classifying electrocardiogram peaks using newwavelet domain features
Author
Vansteenkiste, E. ; Houben, R. ; Pizurica, A. ; Philips, W.
Author_Institution
Ghent Univ., Ghent
fYear
2008
fDate
14-17 Sept. 2008
Firstpage
853
Lastpage
856
Abstract
We study distinctive properties of normal and malfunction electrocardiogram (ECG) peaks in the wavelet domain and based on this study we propose novel classification features for ECG signals. We analyze different combinations of the proposed wavelet domain and time domain features using multidimensional clustering and dimensionality reduction techniques. The results indicate encouraging accuracy rates.
Keywords
data reduction; electrocardiography; feature extraction; medical signal processing; pattern classification; pattern clustering; statistical analysis; waveform analysis; ECG peak classification; ECG signal classification features; dimensionality reduction techniques; electrocardiogram; malfunction ECG peak; multidimensional clustering techniques; normal ECG peak; time domain features; wavelet domain features; Atrial fibrillation; Electrocardiography; Heart beat; Instruments; Multidimensional systems; Shape; Time domain analysis; Wavelet analysis; Wavelet coefficients; Wavelet domain;
fLanguage
English
Publisher
ieee
Conference_Titel
Computers in Cardiology, 2008
Conference_Location
Bologna
ISSN
0276-6547
Print_ISBN
978-1-4244-3706-1
Type
conf
DOI
10.1109/CIC.2008.4749176
Filename
4749176
Link To Document