Title :
A new approach to the P-wave detection and classification based upon application of wavelet neural network
Author :
Domider, T. ; Tkacz, E.J. ; Kostka, P. ; Wrzesniowski, A.
Author_Institution :
Inst. of Electron., Tech. Univ. Silesia, Gliwice, Poland
Abstract :
Presents a new approach to the P wave classification problem which is based upon the application of a new recently developed and widely described tool such as the wavelet neural network. The novel idea of classification is based on the creation of our own non-standard wavelet exactly as a P wave morphology template and then calculation of the wavelet transform as a first layer of a classical multi-layer perceptron. This first layer works as a feature selector and extractor.
Keywords :
electrocardiography; feature extraction; mathematical morphology; medical signal processing; multilayer perceptrons; pattern classification; wavelet transforms; ECG processing; P wave morphology template; P-wave classification; P-wave detection; classical multi-layer perceptron; feature extractor; feature selector; first layer; nonstandard wavelet; wavelet neural network; wavelet transform; Biomedical electronics; Biomedical signal processing; Continuous wavelet transforms; Electrocardiography; Feature extraction; Morphology; Neural networks; Shape; Signal processing algorithms; Wavelet transforms;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020559
