Incremental HMM training applied to ECG signal analysis

Rodrigo Andreao (1, 2) , Sandra Muller (1) , Jérôme Boudy (3) , Bernadette Dorizzi (3) , Teodanio Bastos-Filho (1) , Mario Sarcinelli-Filho (1)

1 UFES - Departamento de Engenharia Elétrica [Vitoria] (Universidade Federal do Espirito Santo)
2 CEFETES - Centro Federal de Educação Tecnológica do Espírito Santo (Universidade Federal do Espirito Santo)
3 TSP - EPH - Département Electronique et Physique

This work discusses the implementation of incremental hidden Markov model (HMM) training methods for electrocardiogram (ECG) analysis. The HMMs are used to model the ECG signal as a sequence of connected elementary waveforms. Moreover, an adaptation process is implemented to adapt the HMMs to the ECG signal of a particular individual. The adaptation training strategy is based on incremental versions of the expectation-maximization, segmental k-means and Bayesian approaches. Performance of the training methods was assessed through experiments considering the QT and ST-T databases. The results obtained show that the incremental training improves beat segmentation and ischemia detection performance with the advantage of low computational effort

Mots clés: HMM adptation; ECG segmentation; ECG analysis; Incremental training

Domaines: Traitement du signal et de l'image [eess.SP]

Rodrigo Andreao, Sandra Muller, Jérôme Boudy, Bernadette Dorizzi, Teodanio Bastos-Filho, et al.. Incremental HMM training applied to ECG signal analysis. Computers in Biology and Medicine, 2008, 38 (6), pp.659 - 667. ⟨10.1016/j.compbiomed.2008.03.006⟩. ⟨hal-01326204⟩