Combining Wavelet Transform and Hidden Markov Models for ECG Segmentation. (27th December 2006)

• Record Type: Journal Article
• Authors: Andreão Andreão, Rodrigo Varejão Rodrigo Varejão; Boudy Boudy, Jérôme Jérôme
• Other Names: Sandham Sandham William Allan William Allan Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2007(2007)
• Publication Date: 2006-12-27
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2007/56215
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : This work aims at providing new insights on the electrocardiogram (ECG) segmentation problem using wavelets. The wavelet transform has been originally combined with a hidden Markov models (HMMs) framework in order to carry out beat segmentation and classification. A group of five continuous wavelet functions commonly used in ECG analysis has been implemented and compared using the same framework. All experiments were realized on the QT database, which is composed of a representative number of ambulatory recordings of several individuals and is supplied with manual labels made by a physician. Our main contribution relies on the consistent set of experiments performed. Moreover, the results obtained in terms of beat segmentation and premature ventricular beat (PVC) detection are comparable to others works reported in the literature, independently of the type of the wavelet. Finally, through an original concept of combining two wavelet functions in the segmentation stage, we achieve our best performances.