User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Feature selection for supervised inter-patient heart beat classification

Primary tabs

Doquire, Gauthier [UCL] de Lannoy, Gaël [UCL] François, Damien [UCL] Verleysen, Michel [UCL]

Supervised and interpatient classification of heart beats is primordial in many applications requiring long-term monitoring of the cardiac function. Several classification models able to cope with the strong class unbalance and a large variety of feature sets have been proposed for this task. In practice, over 200 features are often considered, and the features retained in the final model are either chosen using domain knowledge or an exhaustive search in the feature sets without evaluating the relevance of each individual feature included in the classifier. As a consequence, the results obtained by these models can be suboptimal and difficult to interpret. In this work, feature selection techniques are considered to extract optimal feature subsets for state-of-the-art ECG classification models. The performances are evaluated on real ambulatory recordings and compared to previously reported feature choices using the same models. Results indicate that a small number of individual features actually serve the classification and that better performances can be achieved by removing useless features.

Document type Article de périodique (Journal article) – Article de recherche
Access type Accès restreint
Publication date 2011
Language Anglais
Journal information "Computational Intelligence and Neuroscience" - Vol. 2011, no. 643816, p. 1-9 (2011)
Peer reviewed yes
Publisher Hindawi Publishing Corporation ((United States) New York)
issn 1687-5265
Publication status Publié
Affiliations UCL - SST/ICTM/ELEN - Pôle en ingénierie électrique
UCL - SST/ICTM/INMA - Pôle en ingénierie mathématique
Links
  1. deChazal P., O'Dwyer M., Reilly R.B., Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features, 10.1109/tbme.2004.827359
  2. Christov Ivaylo, Gómez-Herrero Gèrman, Krasteva Vessela, Jekova Irena, Gotchev Atanas, Egiazarian Karen, Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification, 10.1016/j.medengphy.2005.12.010
  3. de Lannoy Gael, François Damien, Delbeke Jean, Verleysen Michel, Weighted SVMs and Feature Relevance Assessment in Supervised Heart Beat Classification, Biomedical Engineering Systems and Technologies (2011) ISBN:9783642184710 p.212-223, 10.1007/978-3-642-18472-7_17
  4. Journal of Machine Learning Research, 5, 1531 (2004)
  5. Goldberger A. L., Amaral L. A. N., Glass L., Hausdorff J. M., Ivanov P. Ch., Mark R. G., Mietus J. E., Moody G. B., Peng C.-K., Stanley H. E., PhysioBank, PhysioToolkit, and PhysioNet : Components of a New Research Resource for Complex Physiologic Signals, 10.1161/01.cir.101.23.e215
  6. Gómez-Verdejo Vanessa, Verleysen Michel, Fleury Jérôme, Information-theoretic feature selection for functional data classification, 10.1016/j.neucom.2008.12.035
  7. Journal of Machine Learning Research, 3, 1157 (2003)
  8. (2006)
  9. Guyon Isabelle, Weston Jason, Barnhill Stephen, Vapnik Vladimir, 10.1023/a:1012487302797
  10. Kohavi Ron, John George H., Wrappers for feature subset selection, 10.1016/s0004-3702(97)00043-x
  11. Lagerholm M., Peterson C., Braccini G., Edenbrandt L., Sornmo L., Clustering ECG complexes using Hermite functions and self-organizing maps, 10.1109/10.846677
  12. Computers in Cardiology, 34, 105 (2007)
  13. Llamedo Mariano, Martínez Juan Pablo, Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria, 10.1109/tbme.2010.2068048
  14. Melgani F., Bazi Y., Classification of Electrocardiogram Signals With Support Vector Machines and Particle Swarm Optimization, 10.1109/titb.2008.923147
  15. Meyer Patrick Emmanuel, Schretter Colas, Bontempi Gianluca, Information-Theoretic Feature Selection in Microarray Data Using Variable Complementarity, 10.1109/jstsp.2008.923858
  16. Moddemeijer R., On estimation of entropy and mutual information of continuous distributions, 10.1016/0165-1684(89)90132-1
  17. Learning pattern classification tasks with imbalanced data sets (2009)
  18. Osowski S., Tran Hoai Linh, ECG beat recognition using fuzzy hybrid neural network, 10.1109/10.959322
  19. Osowski S., Hoai L.T., Markiewicz T., Support Vector Machine-Based Expert System for Reliable Heartbeat Recognition, 10.1109/tbme.2004.824138
  20. Computers in Cardiology, 35, 229 (2008)
  21. Hanchuan Peng, Fuhui Long, Ding C., Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy, 10.1109/tpami.2005.159
  22. Fast training of support vector machines using sequential minimal optimization (1999)
  23. Rossi F., Lendasse A., François D., Wertz V., Verleysen M., Mutual information for the selection of relevant variables in spectrometric nonlinear modelling, 10.1016/j.chemolab.2005.06.010
  24. Shimbel Alfonso, Rapoport Anatol, A statistical approach to the theory of the central nervous system, 10.1007/bf02478329
  25. Steuer R., Kurths J., Daub C. O., Weise J., Selbig J., The mutual information: Detecting and evaluating dependencies between variables, 10.1093/bioinformatics/18.suppl_2.s231
  26. (1999)
Bibliographic reference Doquire, Gauthier ; de Lannoy, Gaël ; François, Damien ; Verleysen, Michel. Feature selection for supervised inter-patient heart beat classification. In: Computational Intelligence and Neuroscience, Vol. 2011, no. 643816, p. 1-9 (2011)
Permanent URL http://hdl.handle.net/2078.1/82235