The Application of Genetic Algorithm for Unsupervised Classification of ECG

  • Roshan Joy Martis
  • Hari Prasad
  • Chandan Chakraborty
  • Ajoy Kumar Ray
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 56)

Abstract

In this chapter,we have proposed an integrated methodology for electrocardiogram (ECG) based differentiation of arrhythmia and normal sinus rhythm using genetic algorithm optimized k-means clustering. Open source databases consisting of the MIT BIH arrhythmia and MIT BIH normal sinus rhythm data are used. The methodology consists of QRS-complex detection using the Pan-Tompkins algorithm, principal component analysis (PCA), and subsequent pattern classification using the k-means classifier, error back propagation neural network (EBPNN) classifier, and genetic algorithm optimized k-means clustering. The m-fold cross-validation scheme is used in choosing the training and testing sets for classification. The k-means classifier provides an average accuracy of 91.21 % over all folds, whereas EBPNN provides a greater average accuracy of 95.79 %. In the proposed method, the k-means classifier is optimized using the genetic algorithm (GA), and the accuracy of this classifier is 95.79 %, which is equal to that of EBPNN. In conclusion, the classification accuracy of simple unsupervised classifiers can be increased to near that of supervised classifiers by optimization using GA. The application of GA to other unsupervised algorithms to yield higher accuracy as a future direction is also observed.

Keywords

Electrocardiogram Principal component analysis Neural network Genetic algorithm MIT-BIH database 

References

  1. 1.
    Cardiovascular Disease: Prevention and Control (2010) WHO report on global strategy on diet, physical activity and health. World Health Organization, Geneva. http://www.who.int/dietphysicalactivity/publications/facts/cvd/en/. Accessed 5 Sept 2010
  2. 2.
    Park K (2005) Park’s textbook of preventive and social medicine, 18th edn. Banarsidas Bhanot publishers, JabalpurGoogle Scholar
  3. 3.
    Fauci AS, Braunwald E, Kesper DL, Hauser SL, Longo DL, Jamesonn JL, Loscalzo J (2008) Harrison’s principles of internal medicine, 17th edn. Mc-Graw Hill, New YorkGoogle Scholar
  4. 4.
    Gaziano TA, Bitton A, Anand S, Abrahams-Gessel S, Murphy A (2010) Growing epidemic of coronary heart disease in low-and middle-income countries. Curr Probl Cardiol 35(2):72–115CrossRefGoogle Scholar
  5. 5.
    Guyton AC, Hall JE (2006) Textbook of medical physiology, 11th edn. W. B Saunders Co, PhiladelphiaGoogle Scholar
  6. 6.
    Duda R, Hart P, Stork D (2001) Pattern classification, 2nd edn. Wiley, New YorkGoogle Scholar
  7. 7.
    Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice Hall, Eagle-wood CliffsMATHGoogle Scholar
  8. 8.
    Jain AK, Murthy MN, Flynn PJ (1999) Data Clustering: a review. ACM Comput Surv 31:264–323CrossRefGoogle Scholar
  9. 9.
    Xu R, Wunsch D (2005) Survey of clustering algorithms. IEEE Trans Neural Networks 16(3):645–678CrossRefGoogle Scholar
  10. 10.
    MacQueen JB (1967) Some methods for classification and analysis of multivariate observations. Paper presented at the proceedings of 5th Berkeley symposium on mathematical statistics and probability, University of California Press, Berkeley, vol 1, pp 281–297Google Scholar
  11. 11.
    Naldi MC, de Carvalho ACPLF, Campell RJGB, Hruschka ER (2007) Genetic Clustering for data Mining. In: Maimon O, Rokach L (eds) Soft Computing for Knowledge Discovery and Data Mining. Springer, New York, pp 113–132Google Scholar
  12. 12.
    Deb K (2001) Multi-objective optimization using evolutionary algorithms. Wiley, New YorkGoogle Scholar
  13. 13.
    Martis RJ, Chakraborty C, Ray AK (2009) A two stage mechanism for registration and classification of ECG using Gaussian mixture model. Pattern Recogn 42(11):2979–2988CrossRefMATHGoogle Scholar
  14. 14.
    Martis RJ, Krishnan MM, Chakraborty C, Pal S, Sarkar D, Mandana KM, Ray AK (2012) Automated screening of arrhythmia using wavelet based machine learning techniques. J Med Syst 36(2):677–688Google Scholar
  15. 15.
    Martis RJ, Chakraborty C (2011) Arrhythmia disease diagnosis using genetic algorithm optimized k-means clustering. J Mech Med Biol 11(4):897–915Google Scholar
  16. 16.
    Vaidyanathan PP (2003) Multirate systems and filter banks. Pearson education (Asia) Pte, TaiwanGoogle Scholar
  17. 17.
    Oppenheim AO, Schaffer RA (2003) Discrete time signal processing, Mc-Graw Hill edition, New YorkGoogle Scholar
  18. 18.
    Murthy IS, Niranjan UC (1992) Component wave delineation of ECG by filtering in the fourier domain. Med Biol Eng Comput 30(2):169–176CrossRefGoogle Scholar
  19. 19.
    Li C, Zheng C, Tai C (1995) Detection of ECG characteristic points using wavelet transforms. IEEE Trans Biomed Eng 42(1):21–29CrossRefGoogle Scholar
  20. 20.
    Martinez JP, Almeida R, Olmos S, Rocha AP, Laguna P (2004) A wavelet based ECG delineator: Evaluation on standard databases. IEEE Trans Biomed Eng 51(4):570–581CrossRefGoogle Scholar
  21. 21.
    Benitez D, Gaydecki PA, Zaidi A, Fitzpatrick AP (2001) The use of the Hilbert transform in ECG signal analysis. Comput Biol Med 31(5):399–406CrossRefGoogle Scholar
  22. 22.
    Bishop C (1995) Neural Networks for pattern recognition, Oxford University press, OxfordGoogle Scholar
  23. 23.
    Schneider J (1997) Cross validation. http://www.cs.cmu.edu/~schneide/tu5/node42.html. Accessed on 5 Sept 2010

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Roshan Joy Martis
    • 1
  • Hari Prasad
    • 1
  • Chandan Chakraborty
    • 1
  • Ajoy Kumar Ray
    • 2
  1. 1.School of Medical Science and TechnologyIITKharagpurIndia
  2. 2.Department of Electronics and Electrical Communication EngineeringIITKharagpurIndia

Personalised recommendations