Advertisement

Soft-Margin SVM Incorporating Feature Selection Using Improved Elitist GA for Arrhythmia Classification

  • Vinod J. KadamEmail author
  • Samir S. Yadav
  • Shivajirao M. Jadhav
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 941)

Abstract

Cardiac arrhythmia is one of the serious heart disorders. In many cases; it may lead to stroke and heart failure. Therefore timely and accurate diagnosis is very necessary. In this paper, we proposed a novel ECG Arrhythmia classification approach which includes an Elitist-population based Genetic Algorithm to optimally select the important features and the Soft-Margin SVM as a base classifier to diagnose arrhythmia by classifying it into normal and abnormal classes. Our improved GA employs the classification error obtained by 10 fold cross-validated SVM classification model as a fitness value. The aim of the Genetic Algorithm is therefore to minimize this value. To show the effectiveness of the proposed method, the UCI ECG arrhythmia dataset was used. Performance of base classifier soft-margin SVM was analyzed with different values of the penalty parameter C. Proposed feature selection method significantly enhances the accuracy and generates fewer and relevant input features for the classifier. With the introduced model, we obtained a promising classification accuracy value. The result of the study proves that the model is also comparable with the existing methods available in the literature. The simulation results and statistical analyses are also showing that the proposed model is truly beneficial and efficient model for cardiac ECG Arrhythmia classification.

Keywords

Soft-Margin SVM Feature Selection Elitist Genetic Algorithm Arrhythmia classification ECG 

References

  1. 1.
    Kadam, V.J., Jadhav, S.M.: Feature ensemble learning based on sparse autoencoders for diagnosis of Parkinson’s Disease. In: Iyer, B., Nalbalwar, S., Pathak, N. (eds.) Computing, Communication and Signal Processing. Advances in Intelligent Systems and Computing, vol. 810. Springer, Singapore (2019)Google Scholar
  2. 2.
  3. 3.
    Leng, S., San Tan, R., Chai, K.T.C., Wang, C., Ghista, D., Zhong, L.: The electronic stethoscope. Biomed. Eng. OnLine 14(1), 66 (2015).  https://doi.org/10.1186/s12938-015-0056-y
  4. 4.
    Guvenir, H.A., Acar, B., Demiroz, G., Cekin, A.: A supervised machine learning algorithm for arrhythmia analysis. In: Computers in Cardiology 1997, Lund, Sweden, pp. 433–436 (1997)Google Scholar
  5. 5.
    Dua, D., Taniskidou, E.K.: UCI Machine Learning Repository. School of Information and Computer Science, University of California, Irvine, CA (2017). http://archive.ics.uci.edu/ml
  6. 6.
    Gao, D., Madden, M., Schukat, M., Chambers, D., Lyons, G.: Arrhythmia identification from ECG signals with a neural network classifier based on a Bayesian framework. In: 24th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, December 2004Google Scholar
  7. 7.
    Polat, K., Sahan, S., Günes, S.: A new method to medical diagnosis: artificial immune recognition system (AIRS) with fuzzy weighted pre-processing and application to ECG arrhythmia. Expert Syst. Appl. 31, 264–269 (2006)Google Scholar
  8. 8.
    Lee, S.-H., Uhm, J.-K., Lim, J.S.: Extracting input features and fuzzy rules for detecting ECG arrhythmia based on NEWFM. In: 2007 International Conference on Intelligent and Advanced Systems, Kuala Lumpur, pp. 22–25 (2007).  https://doi.org/10.1109/ICIAS.2007.4658341
  9. 9.
    Uyar, A., Gurgen, F.: Arrhythmia classification using serial fusion of support vector machines and logistic regression. In: 2007 4th IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Dortmund (2007)Google Scholar
  10. 10.
    Elsayad, A.M.: Classification of ECG arrhythmia using learning vector quantization neural networks. In: 2009 International Conference on Computer Engineering & Systems, Cairo (2009)Google Scholar
  11. 11.
    Oveisi, F., Oveisi, S., Erfanian, A., Patras, I.: Tree-structured feature extraction using mutual information. IEEE Trans. Neural Netw. Learn. Syst. 23(1), 127–137 (2012).  https://doi.org/10.1109/TNNLS.2011.2178447CrossRefGoogle Scholar
  12. 12.
    Jadhav, S.M., Nalbalwar, S.L., Ghatol, A.A.: Artificial neural network models based cardiac arrhythmia disease diagnosis from ECG signal data. Int. J. Comput. Appl. 44, 8–13 (2012)Google Scholar
  13. 13.
    Khare, S., Bhandari, A., Singh, S., Arora, A.: ECG arrhythmia classification using spearman rank correlation and support vector machine. In: Deep, K., Nagar, A., Pant, M., Bansal, J. (eds.) Proceedings of the International Conference on Soft Computing for Problem Solving (SocProS 2011), 20–22 December 2011. Advances in Intelligent and Soft Computing, vol. 131. Springer, India (2012)Google Scholar
  14. 14.
    Yılmaz, E.: An expert system based on fisher score and LS-SVM for cardiac arrhythmia diagnosis. Comput. Math. Methods Med. 2013, Article ID 849674, 6 p. (2013)Google Scholar
  15. 15.
    Jadhav, S., Nalbalwar, S., Ghatol, A.: Feature elimination based random subspace ensembles learning for ECG arrhythmia diagnosis. Soft Comput. 18(3), 579–587 (2014).  https://doi.org/10.1007/s00500-013-1079-6CrossRefGoogle Scholar
  16. 16.
    shensheng Xu, S., Mak, M.W., Cheung, C.C.: Deep neural networks versus support vector machines for ECG arrhythmia classification. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), Hong Kong, pp. 127–132 (2017)Google Scholar
  17. 17.
    Han, C.-W.: Detecting an ECG arrhythmia using cascade architectures of fuzzy neural networks. In: Advanced Science and Technology Letters, (ASP 2017), vol. 143, pp. 272–275 (2017)Google Scholar
  18. 18.
    Ayar, M., Sabamoniri, S.: An ECG-based feature selection and heartbeat classification model using a hybrid heuristic algorithm. Inf. Med. Unlocked 13, 167–175 (2018)CrossRefGoogle Scholar
  19. 19.
    Majumdar, J., Bhunia, A.K.: Elitist genetic algorithm for assignment problem with imprecise goal. Eur. J. Oper. Res. 177(2), 684–692 (2007)CrossRefGoogle Scholar
  20. 20.
    Mishra, J., Bagga, J., Choubey, S., Gupta, I.K.: Energy optimized routing for wireless sensor network using elitist genetic algorithm. In: 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1–5. IEEE, July 2017Google Scholar
  21. 21.
    Tjandrasa, H., Djanali, S.: Classification of P300 event-related potentials using wavelet transform, MLP, and soft margin SVM. In: 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI), pp. 343–347. IEEE, March 2018Google Scholar
  22. 22.
    Nguyen, H.D., Jones, A.T., McLachlan, G.J.: Jpn. J. Stat. Data Sci. 1, 81 (2018).  https://doi.org/10.1007/s42081-018-0001-y
  23. 23.
    Norton, M., Mafusalov, A., Uryasev, S.: Soft margin support vector classification as buffered probability minimization. J. Mach. Learn. Res. 18, 1–43 (2017)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Merker, J.: On sparsity of soft margin support vector machines. J. Adv. Appl. Math. 2(3) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Vinod J. Kadam
    • 1
    Email author
  • Samir S. Yadav
    • 1
  • Shivajirao M. Jadhav
    • 1
  1. 1.Department of Information TechnologyDr. Babasaheb Ambedkar Technological UniversityLonereIndia

Personalised recommendations