Heart Signal Recognition by Hidden Markov Models: The ECG Case

Abstract:

Wave recognition in ECG signals by Hidden Markov Models (HMMs) relies on the stationary assumption for the set of parameters used to describe ECG waves. This approach seems unnatural and consequently generates severe errors in practice. A new class of HMMs called Modified Continuous Variable Duration HMMs is proposed to account for the specific properties of the ECG signal. An application of the latter, coupled with a multiresolution front-end analysis of the ECG is presented. Results show these methods can increase the perfomance of ECG recognition compared to classical HMMs.

Keywords

ECG Recognition - Hidden Markov Modeling - Wavelet Analysis

• REFERENCES

• 1 Coast AD, Stern RM, Cano GG, Briller SA. An approach to cardiac arrhythmia analysis using HMMs. IEEE Trans Biomed Eng 1990; 37: 826-35.
• 2 Thoraval L. Continuously variable duration HMMs for ECG segmentation. In: Carrault G, Mora F. Proceedings IEEE-EMBS . Paris: 1992: 529-30.
• 3 Levinson SE. Continuous speech recognition by means of acoustic/phonetic classification obtained from a HMM. In: Proceedings IEEE-ICASSP 1987; 93-6.
• 4 Bahl LR, Jelinek F, Mercer RL. A maximum likelihood approach to continuous speech recognition. IEEE Trans Pattern Anal Machine Intell 1983; 05: 179-90.
• 5 Thoraval L, Passariello G, Mora F, Coatrieux JL, Carrault G. A non-linear transformation of the ECG based on local signal symmetry properties. In: Proceedings IEEE-EMBS . Orlando: 1991: 582-3.
• 6 Senhadji L. Approche multiresolution pour l’analyse des signaux non stationnaires. These de L’Universite de Rennes I. Rennes, France, Febr: 1993