Hyperellipsoidal Classifier for Beat Classification in ECG Signals

  • G. Bortolan
  • I. Christov
  • W. Pedrycz


In this chapter, we study an ECG signal processing and beat classification problem in particular, considering a technique coming with high interpretation capabilities, namely a family of hyperbox classifiers. Different techniques based on a combination of fuzzy clustering and genetic algorithms have been applied to support learning processes in the specific pattern recognition task. Hyperbox classifiers have been investigated for the detection and classification of different types of heartbeats in electrocardiograms (ECGs), which are of major importance in the diagnosis of cardiac dysfunctions. In particular, the learning capacity and the classification ability for normal beats (N) and premature ventricular contractions (PVC) have been tested, with focus on the interpretability aspect. The MIT-BIH arrhythmia database has been used for testing and validating of the proposed method. A total of 26 morphology features have been extracted from ECG and reconstructed VCG signals. Three learning procedures have been developed and analyzed. We have elaborated on several ways of combining fuzzy clustering and genetic algorithm in identifying the optimal hyperboxes and forming a family of hyperellipsoids. The results showed that even a limited number of hyperboxes can increase the geometrical interpretability without a significant reduction of the accuracy of such classifier.


Genetic Algorithm Feature Space Fuzzy Cluster Premature Ventricular Contraction Right Bundle Branch Block 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. AAMI.: Testing and reporting performance results of cardiac rhythm and ST-segment measurement algorithms. Ansi/AAMI EC57:1998/(R)2008. Association for the Advancement of Medical Instrumentation (2008)Google Scholar
  2. Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function. Plenum, New York (1981)MATHGoogle Scholar
  3. Bortolan, G. and Pedrycz, W.: Fuzzy descriptive models: an interactive framework of information granulation. IEEE Trans. Fuzzy Sets. 10, 743–755 (2002a)CrossRefGoogle Scholar
  4. Bortolan, G., Pedrycz, W.: An interactive framework for an analysis of ECG signals. Artif. Intell. Med. 24, 109–132 (2002b)CrossRefGoogle Scholar
  5. Bortolan, G., Pedrycz, W.: Hyperbox classifier for arrhythmia classification. Kybernetes. 36, 531–547 (2007)MATHGoogle Scholar
  6. Bortolan, G., Willems, J.L.: Diagnostic ECG classification based on neural networks. J. Electrocardiol. 26, 75–79 (1994)Google Scholar
  7. Bortolan, G., Brohet, C. Fusaro, S.: Possibilities of using neural networks for diagnostic ECG classification. J. Electrocardiol. 29, 10–16 (1996)CrossRefGoogle Scholar
  8. Bortolan, G., Jekova, I., Christov, I.: Comparison of four methods for premature Ventricular Contraction and normal beat clustering. IEEE Comp. Cardiol. 32, 921–924 (2005)CrossRefGoogle Scholar
  9. Bortolan, G., Christov, I., Pedrycz, W.: Hyperbox classifiers for ECG beat analysis. IEEE Comp. Cardiol. 34, 145–148 (2007)Google Scholar
  10. Christov, I., Bortolan, G.: Ranking of pattern recognition parameters for premature ventricular contractions classification by neural networks. Physiological Measurement, 24, 1281–1290 (2004)CrossRefGoogle Scholar
  11. Christov, I., Jekova, I., Bortolan, G.: Premature ventricular contraction classification by the Kth nearest-neighbours rule. Physiol. Meas. 26, 123–130 (2005)CrossRefGoogle Scholar
  12. Christov, I., Gómez-Herrero, G., Krasteva, V., Jekova, I., Gotchev, A., Egiazarian, K.: Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification. Med. Eng. Phys. 28, 876–887 (2006)CrossRefGoogle Scholar
  13. Conn, A.R., Gould, N.I.M., Toint, P.L.: A globally convergent augmented Lagrangian pattern search algorithm for optimization with general constraints and simple bounds. SIAM J. Numer. Anal. 28, 545–572 (1991)MathSciNetMATHCrossRefGoogle Scholar
  14. Daskalov, I.K., Christov, I.: Electrocardiogram signal preprocessing for automatic detection of QRS boundaries. Med. Eng. Phys. 21, 37–44 (1999)CrossRefGoogle Scholar
  15. Daskalov, I., Dotsinsky, I., Christov, I.: Developments in ECG acquisition, preprocessing, parameter measurement and recording. IEEE Eng. Med. Biol. 17, 50–58 (1998)CrossRefGoogle Scholar
  16. Gabrys, B., Bargiela, A.: General fuzzy min-max neural network for clustering and classification. IEEE Trans. Neural Netw. 11, 769–783 (2001)CrossRefGoogle Scholar
  17. Gómez-Herrero, G., Gotchev, A., Christov, I., Egiazarian, K.: Feature extraction for heartbeat classification using independent component analysis and matching pursuits. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP2005, pp. 725–728, Philadelphia (2005)Google Scholar
  18. Gómez-Herrero, G., Jekova, I., Krasteva, V., Christov, I., Gotchev, A., Egiazarian, K.: Relative estimation of the Karhunen-Loève transform basis functions for detection of ventricular ectopic beats. IEEE Comp. Cardiol. 33, 569–572 (2006)Google Scholar
  19. Jaklic, A., Leonardis, A., Solina, F.: Segmentation and Recovery of Superquadrics. Kluwer Academic, London (2000)MATHGoogle Scholar
  20. Jekova, I., Bortolan, G., Christov, I.: Pattern recognition and optimal parameter selection in premature ventricular contraction classification. IEEE Comp. Cardiol. 31, 357–360 (2004)CrossRefGoogle Scholar
  21. Jekova, I., Bortolan, G., Christov, I.: Assessment and comparison of different classification methods for heart beat clustering. Med. Eng. Phys. 30, 248–257 (2008)CrossRefGoogle Scholar
  22. Mark, R., Moody, G.: MIT-BIH Arrhythmia Data Base Directory. Massachusetts Institute of Technology, Cambridge (1988)Google Scholar
  23. Silipo, R., Bortolan, G., Marchesi, C.: Design of hybrid architectures based on neural classifier and RBF pre-processing for ECG analysis. Int. J. Approx Reason. 21, 177–196 (1999)MATHCrossRefGoogle Scholar
  24. Simpson, P.K.: Fuzzy min-max neural networks: 1. Classification. IEEE Trans. Neural Netw. 3, 776–586 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  1. 1.Institute of Biomedical EngineeringISIB-CNRPadovaItaly
  2. 2.Institute of Biophysics and Biomedical EngineeringBASSofiaBulgaria
  3. 3.Department of Electrical & Computer EngineeringUniversity of AlbertaEdmontonCanada
  4. 4.Systems Research Institute Polish Academy of SciencesWarsawPoland

Personalised recommendations