Charles Darwin University

CDU eSpace
Institutional Repository

 
CDU Staff and Student only
 

Improved ECG signal analysis using wavelet and feature extraction

Matsuyama, Aya, Jonkman, Mirjam E. and De Boer, Friso G. (2005). Improved ECG signal analysis using wavelet and feature extraction. In: Yana, K., Yamamoto, Y., Akay, S., Cerutti, S., He, B., Saranumi, N., Sato, S., Tamura, T. and van Bemmel, J. 5th International Workshop on Biosignal Interpretation, Tokyo, Japan, 6-8 September 2005.

Document type: Conference Paper
Citation counts: Google Scholar Search Google Scholar

Author Matsuyama, Aya
Jonkman, Mirjam E.
De Boer, Friso G.
Title Improved ECG signal analysis using wavelet and feature extraction
Conference Name 5th International Workshop on Biosignal Interpretation
Conference Location Tokyo, Japan
Conference Dates 6-8 September 2005
Conference Publication Title Proceedings of the 5th International Workshop on Biosignal Interpretation
Editor Yana, K.
Yamamoto, Y.
Akay, S.
Cerutti, S.
He, B.
Saranumi, N.
Sato, S.
Tamura, T.
van Bemmel, J.
Place of Publication Tokyo, Japan
Publisher BIS2005
Publication Year 2005
ISBN 4-9902682-9-6   (check CDU catalogue  open catalogue search in new window)
Start Page 235
End Page 238
Total Pages 4
HERDC Category E1 - Conference Publication (DEST)
Abstract Automatic detection of arrhythmias is important for diagnosis of heart problems. Wavelet analysis is suitable to extract information from non-stationary signals like the ECG because of its ability to decompose the signal at various resolutions. In this paper we present an improved version of novel method to separate abnormal beats and normal beats within the ECG signals, using wavelet analysis and feature extraction. Two feature extraction methods were analysed, one based on the normalised energy and one based on the entropy of the beat to beat signal. Results indicate that eliminating normal beats which occur before and after the abnormal beats, improved the separation between normal and abnormal.
Keyword Electrocardiography
Signal Processing
Cardiovascular diseases
Additional Notes Published in: Methods of Information in Medicine, 46 (2):227-230. ISSN: 0026-1270
 
Versions
Version Filter Type
Access Statistics: 43 Abstract Views  -  Detailed Statistics
Created: Fri, 12 Sep 2008, 08:35:25 CST by Administrator