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)

Benoît Frénay; Gaël de Lannoy; Michel Verleysen

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)

Benoît Frénay, Gaël de Lannoy, Michel Verleysen

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning
Pages	141-146
Number of pages	6
Publication status	Published - 2009
Externally published	Yes
Event	17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009 - Bruges, Belgium Duration: 22 Apr 2009 → 24 Apr 2009

Conference

Conference	17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009
Country/Territory	Belgium
City	Bruges
Period	22/04/09 → 24/04/09

Keywords

ECG segmentation Transition modelling Hidden Markov models ICTEAM:MLAI

Fingerprint

Dive into the research topics of '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)'. Together they form a unique fingerprint.

Cite this

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). In ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning (pp. 141-146)

Frénay, Benoît ; de Lannoy, Gaël ; Verleysen, Michel. / 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). ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning. 2009. pp. 141-146

@inproceedings{52a744ed063c42a68d3cb43aa2e01e29,

title = "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)",

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.",

keywords = "ECG segmentation Transition modelling Hidden Markov models ICTEAM:MLAI",

author = "Beno{\^i}t Fr{\'e}nay and {de Lannoy}, Ga{\"e}l and Michel Verleysen",

year = "2009",

language = "English",

isbn = "2930307099",

pages = "141--146",

booktitle = "ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning",

note = "17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009 ; Conference date: 22-04-2009 Through 24-04-2009",

}

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). in ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning. pp. 141-146, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009, Bruges, Belgium, 22/04/09.

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). / Frénay, Benoît; de Lannoy, Gaël; Verleysen, Michel.

ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning. 2009. p. 141-146.

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Improving the transition modelling in hidden Markov models for ECG segmentation

T2 - 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009

AU - Frénay, Benoît

AU - de Lannoy, Gaël

AU - Verleysen, Michel

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - ECG segmentation Transition modelling Hidden Markov models ICTEAM:MLAI

UR - http://www.scopus.com/inward/record.url?scp=84887000490&partnerID=8YFLogxK

M3 - Conference contribution

SN - 2930307099

SN - 9782930307091

SP - 141

EP - 146

BT - ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning

Y2 - 22 April 2009 through 24 April 2009

ER -

Frénay B, de Lannoy G, Verleysen M. 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). In ESANN 2009 Proceedings, 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning. 2009. p. 141-146

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)

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this