Improving the transition modelling in hidden Markov models for ECG segmentation

Frénay, Benoît;de Lannoy, Gaël;Verleysen, Michel
(2009) 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning (ESANN 2009) — Location: Bruges (Belgium) (22.April.2009)

Files

159-ImprovingthetransitionmodellinginhiddenMarkovmodelsforECGsegmentation.pdf
  • Restricted Access
  • Adobe PDF
  • 711.93 KB
Request a copy

Details

Authors
  • Frénay, BenoîtUCLouvain
    Author
  • de Lannoy, GaëlUCLouvain
    Author
  • Verleysen, MichelUCLouvain
    Author
Abstract
The segmentation of ECG signal is a useful tool for the diagnosis of cardiac diseases. However, the state-of-the-art methods use hidden Markov models which do not adequately model the transitions between successive waves. This paper uses two methods which attempt to overcome this limitation: a HMM state scission scheme which prevents ingoing and outgoing transitions in the middle of the waves and a Bayesian network where the transitions are emission-dependent. Experiments show that both methods improve the results on pathological ECG signals.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Frénay, B., de Lannoy, G., & Verleysen, M. (2009). Improving the transition modelling in hidden Markov models for ECG segmentation. Proceedings of the 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning (ESANN 2009), p. 141-146. https://hdl.handle.net/2078.5/254119