A Neuro-Evolutionary Approach to Electrocardiographic Signal Classification



This chapter presents an evolutionary Artificial Neural Networks (ANN) classifier system as a heartbeat classification algorithm designed according to the rules of the PhysioNet/Computing in Cardiology Challenge 2011 (Moody, Comput Cardiol Challenge 38:273–276, 2011), whose aim is to develop an efficient algorithm able to run within a mobile phone that can provide useful feedback when acquiring a diagnostically useful 12-lead Electrocardiography (ECG) recording. The method used to solve this problem is a very powerful natural computing analysis tool, namely evolutionary neural networks, based on the joint evolution of the topology and the connection weights relying on a novel similarity-based crossover. The chapter focuses on discerning between usable and unusable electrocardiograms tele-medically acquired from mobile embedded devices. A preprocessing algorithm based on the Discrete Fourier Transform has been applied before the evolutionary approach in order to extract an ECG feature dataset in the frequency domain. Finally, a series of tests has been carried out in order to evaluate the performance and the accuracy of the classifier system for such a challenge.


Mobile Phone Crossover Operator Scaled Conjugate Gradient Entire Evolutionary Process Heart State Evaluation 
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. 1.
    Data Driven Approach to ECG Signal Quality Assessment using Multistep SVM Classification. Contribution sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  2. 2.
    Jokic, S., Krco, S., Delic, V., Sakac, D., Jokic, I., Lukic, Z.: An efficient ECG modeling for heartbeat classification. IEEE 10th Symposium on Neural Network Applications on Electrical Engineering, NEUREL 2010, Belgrade, Serbia, 23–25 Sept 2010Google Scholar
  3. 3.
    Moody, G.B.: Improving the quality of ECGs collected using mobile phones: the 12th annual physionet/computing in cardiology challenge. Comput. Cardiol. Challenge 38, 273–276 (2011)MathSciNetGoogle Scholar
  4. 4.
    Silva, K., Moody, G.B., Celi, L.: Improving the quality of ECGs collected using mobile phones: the physionet/computing in cardiology challenge 2011. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  5. 5.
    Tat, T.H.C., Chen Xiang, C., Thiam, L.E.: Physionet challenge 2011: improving the quality of electrocardiography data collected using real time QRS-complex and T-wave detection. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  6. 6.
    Jiang, W., Kong, S.G.: Block-based neural networks for personalized ECG signal classification. IEEE T. Neural Networks 18(6), 1750–1761 (2007)CrossRefGoogle Scholar
  7. 7.
    Azzini, A., Tettamanzi, A.G.B.: A new genetic approach for neural network design. In: Abraham, A., Grosan, C., Pedrycz W. (eds.) Engineering Evolutionary Intelligent Systems. Studies in Computational Intelligence, vol. 82. Springer, Berlin (2008)Google Scholar
  8. 8.
    Azzini, A., Tettamanzi, A.G.B., Dragoni, M.: SimBa-2: improving a novel similarity-based crossover for the evolution of artificial neural networks. 11th international conference on intelligent systems design and applications (ISDA 2011), pp. 374–379. IEEE (2011)Google Scholar
  9. 9.
    PhysioNet: Research Resource for Complex Physiologic Signals,
  10. 10.
    Camargo, F.: Learning algorithms in neural networks. Technical Report, Computer Science Department, Columbia University (1990)Google Scholar
  11. 11.
    Gurney, K.: An Introduction to Neural Networks. Taylor & Francis, Bristol (1997)CrossRefGoogle Scholar
  12. 12.
    Kröse, B., Van der Smagt, P.: An Introduction to Neural Networks. The University of Amsterdam, Amsterdam (1996)
  13. 13.
    Yao, X.: Evolving artificial neural networks. In: Proceedings of the IEEE, pp. 1423–1447 (1999)Google Scholar
  14. 14.
    Zhang, G.: Neural networks for classification: a survey. IEEE T. Syst. Man Cy. C: Appl. Rev. 30, 451–462 (2000)CrossRefGoogle Scholar
  15. 15.
    Bahrammirzaee, A.: A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems. Neural Comput. Appl. 19, 1165–1195 (2010)CrossRefGoogle Scholar
  16. 16.
    Castellani, M., Rowlands, H.: Evolutionary artificial neural network design and training for wood veneer classification. Eng. Appl. Artif. Intel. 22, 1165–1195 (2009)CrossRefGoogle Scholar
  17. 17.
    Fernández, J., Hervás, C., Martínez-Estudillo, F., Gutiérrez, P.: Memetic pareto evolutionary artificial neural networks to determine growth/no-growth in predictive microbiology. Appl. Soft Comput. 11, 534–550 (2011)CrossRefGoogle Scholar
  18. 18.
    Wang, P., Weise, T., Chiong, R.: Novel evolutionary algorithms for supervised classification problems: an experimental study. Evol. Intel. 4(Special Issue), 1–14 (2011)Google Scholar
  19. 19.
    Azzini, A., Tettamanzi, A.G.B.: Evolving neural networks for static single-position automated trading. J. Artif. Evol. Appl. 2008, 1–17 (2008) (Article ID 184286)Google Scholar
  20. 20.
    Azzini, A., da Costa Pereira, C., Tettamanzi, A.G.B.: Modeling turning points in financial markets with soft computing techniques. In: Brabazon, A., O’Neill, M., Maringer D. (eds.) Natural Computing in Computational Finance, Studies in Computational Intelligence, vol. 293, pp. 147–167. Springer, Berlin (2010)CrossRefGoogle Scholar
  21. 21.
    Azzini, A., Lazzaroni, M., Tettamanzi, A.G.B.: Incipient fault diagnosis in electrical drives by tuned neural networks. Instrumentation and measurement technology conference, IMTC’06, pp. 1284–1289 (2006)Google Scholar
  22. 22.
    Azzini, A., Marrara, S.: Dermatology disease classification via novel evolutionary artificial neural network. In: Proceedings of the 18th International Conference on Database and Expert Systems Applications, DEXA’07, pp. 148–152 (2007)Google Scholar
  23. 23.
    Azzini, A., Tettamanzi, A.G.B.: Evolutionary ANNs: a state of the art survey. Intelligenza Artificiale 5, 19–35 (2011)Google Scholar
  24. 24.
    Yao, X., Xu, Y.: Recent advances in evolutionary computation. Int. J. Comput. Sci. Technol. 21, 1–18 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  25. 25.
    Floreano, D., Durr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intel. 10, 47–62 (2008)CrossRefGoogle Scholar
  26. 26.
    Hestenes, M., Stiefel, E.: Methods of conjugate gradients for solving linear systems. J. Res. Natl. Bur. Stand. 49(6), 409–436 (1952)CrossRefzbMATHMathSciNetGoogle Scholar
  27. 27.
    Stanley K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10, 99–127 (2002)CrossRefGoogle Scholar
  28. 28.
    Muhlenbein, H., Schlierkamp-Voosen, D.: The science of breeding and its application to the breeder genetic algorithm (bga). Evol. Comput. 1, 335–360 (1993)CrossRefGoogle Scholar
  29. 29.
    Goldberg, D.: Genetic Algorithms in Search, Optimization and Machine Learning. Kluwer Academic, Boston (1989)zbMATHGoogle Scholar
  30. 30.
    Schwefel, H.: Numerical Optimization for Computer Models. Wiley, Chichester (1981)Google Scholar
  31. 31.
    Azzini, A., Dragoni, M., Tettamanzi, A.G.B.: A novel similarity-based crossover for artificial neural network evolution. In: Schaefer, R., Cotta, C., Kolodziej, J., Rudolph, G. (eds.) Parallel Problem Solving from Nature PPSN XI. Lecture Notes in Computer Science, vol. 6238, pp. 344–353. Springer, Berlin (2010)Google Scholar
  32. 32.
    Garcia-Pedrajas, N., Ortiz-Boyer, D., Hervas-Martinez, C.: An alternative approach for neural network evolution with a genetic algorithm: crossover by combinatorial optimization. Neural Networks 19, 514–528 (2006)CrossRefzbMATHGoogle Scholar
  33. 33.
    Hancock, P.J.B.: Genetic algorithms and permutation problems: a comparison of recombination operators for neural net structure specification. Proceedings of IEEE International Workshop on Combinations of Genetic Algorithms and Neural Networks, COGANN’92, pp. 108–122. IEEE, Baltimore (1992)Google Scholar
  34. 34.
    Xia, H., McBride, J., Sullivan, A., De Bock, T., Bains, J., Wortham, D., Zhao, X.: A multistage computer test algorithm for improving the quality of ECGs. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  35. 35.
    Moody, B.E.: A rule-based method for ECG quality control. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  36. 36.
    Johannesen, L.: Assessment of ECG quality on an android platform. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  37. 37.
    Langley, P., Di Marco, L., King, S., Di Maria, C., Duan, W., Bojarnejad, M., Wang, K., Zheng, D., Allen, J., Murray, A.: An algorithm for assessment of ECG quality acquired via mobile telephone. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  38. 38.
    Hayn, D., Jammerbund, B., Schreier, G.: Real-time visualization of signal quality during mobile ECG recording. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar
  39. 39.
    Chudcek, V., Zach, L., Kulek, J., Spilka, J., Lhotsk, L.: Simple scoring system for ECG signal quality assessment on android platform. Contribution Sent to the 38th Physionet Cardiology Challenge (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Dipartimento di Tecnologie dell’InformazioneUniversità degli Studi di MilanoCrema (CR)Italy
  2. 2.Fondazione Bruno Kessler (FBK-IRST)TrentoItaly
  3. 3.I3S Laboratory UMR 7271 - UNS/CNRS/INRIA, Ple GLC, WIMMICS Research TeamSophia Antipolis CEDEX, NiceFrance

Personalised recommendations