Segmentation of electrocardiograms using a hidden Markov model

The purpose of this study is to segment electrocardiograms (ECG) and detect accurately the P-wave onset and offset in order to be able to discriminate some cardiac arrhythmias. A hidden Markov model is used to perform this segmentation. The model includes the amplitude and the slope of the samples. It segments the beats of the ECGs in twelve parts. The results are good and can be applied to most of the ECGs encountered.

[1]  O. Fokapu,et al.  Evolution temporelle et fréquentielle de l'ECG: analyse battement par battement , 1993 .

[2]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[3]  G.G. Cano,et al.  An approach to cardiac arrhythmia analysis using hidden Markov models , 1990, IEEE Transactions on Biomedical Engineering.