Journal of Medical Systems

, Volume 36, Issue 2, pp 549–556

A Biomedical Decision Support System Using LS-SVM Classifier with an Efficient and New Parameter Regularization Procedure for Diagnosis of Heart Valve Diseases

Original Paper


Classification success of Support Vector Machine (SVM) depends on the characteristic of given data set and some training parameters (C and σ). In literature, a few studies have been presented for regularization of these parameters which affects classification performance directly. This study proposes a new approach based on Renyi’s entropy and Logistic regression methods for parameter regularization. Our regularization procedure runs at two steps. In the first step, optimal value of kernel parameter interval is found via Renyi’s entropy method and optimal C value is found via logistic regression using exponential function in the next step. In addition to, this new decision support system is applied to biomedical research area via an application related to Doppler Heart Sounds (DHS). Experimental results show the efficiency of developed regularization procedure.


Doppler heart sounds Feature extraction Support vector machines Decision support systems Parameter regularization 


  1. 1.
    Akay, M., Akay, Y. M., and Welkowitz, W. Neural networks for the diagnosis of coronary artery disease. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN. Vol. 2, pp. 419–424, 1992.Google Scholar
  2. 2.
    Nanda, N. C., Doppler echocardiography, 2nd edition. Lea & Febiger, London, 1993.Google Scholar
  3. 3.
    Keeton, P. I. J., and Schlindwein, F. S., Application of wavelets in Doppler Ultrasound. Sens. Rev. 17(Issue 1):38–45, 1997. doi:10.1108/02602289710163355.CrossRefGoogle Scholar
  4. 4.
    Wright, I. A., Gough, N. A. J., Rakebrandt, F., Wahab, M., and Woodcock, J. P., Neural network analysis of Doppler ultrasound blood flow signals: A pilot study. Ultrasound Med. Biol. 23(5):683–690, 1997.CrossRefGoogle Scholar
  5. 5.
    Jing, F., Xuemin, W., Mingshi, W., and Wie, L. Noninvasive acoustical analysis system of coronary heart disease. In: Proceedings of the Sixteenth Southern Biomedical Engineering Conference, pp. 239–241, 1997.Google Scholar
  6. 6.
    Turkoglu, I., Arslan, A., and Ilkay, E., An expert system for diagnosis of the heart valve diseases. Expert Syst. Appl. 23(3):229–236, 2002.CrossRefGoogle Scholar
  7. 7.
    Uğuz, H., Arslan, A., and Türkoğlu, İ., A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases. Pattern Recognit. Lett. 28(4):395–404, 2007.CrossRefGoogle Scholar
  8. 8.
    Çomak, E., Arslan, A., and Türkoğlu, İ., A decision support system based on support vector machines for diagnosis of the heart valve diseases. Comput. Biol. Med. 37(1):21–27, 2007.CrossRefGoogle Scholar
  9. 9.
    Chan, B. C. B., Chan, F. H. Y., Lam, F. K., Lui, P. W., and Poon, P. W. F., Fast detection of venous air embolism is Doppler heart soundusing the wavelet transform. IEEE Trans. Biomed. Eng. 44(Issue \4):237–245, 1997.CrossRefGoogle Scholar
  10. 10.
    Guler, I., Kiymik, M. K., Kara, S., and Yuksel, M. E., Application of autoregressive analysis to 20 MHz pulsed Doppler data in real time. Biomedical Computing 31(3–4):247–256, 1992.CrossRefGoogle Scholar
  11. 11.
    Gold, C., Holub, A., and Sollich, P., Bayesian approach to feature selection and parameter tuning for support vector machine classifiers. Neural Netw. 18:693–701, 2005.MATHCrossRefGoogle Scholar
  12. 12.
    UCI Repository of Machine Learning Databases.
  13. 13.
    Huang, C. L., and Wang, C. J., A GA-based feature selection and parameters optimization for support vector machines. Expert Syst. Appl. 31:231–240, 2006.CrossRefGoogle Scholar
  14. 14.
    Min, S. H., Lee, J., and Han, I., Hybrid genetic algorithms and support vector machines for bankruptcy prediction. Expert Syst. Appl. 31:652–660, 2006.CrossRefGoogle Scholar
  15. 15.
    Kulkarni, A., Jayaraman, V. K., and Kulkarni, B. D., Support vector classification with parameter tuning assisted by agent-based technique. Comput. Chem. Eng. 28:311–318, 2004.CrossRefGoogle Scholar
  16. 16.
    Eitrich, T., and Lang, B., Efficient optimization of support vector machine learning parameters for unbalanced datasets. J. Comput. Appl. Math. 196:425–436, 2006.MathSciNetMATHCrossRefGoogle Scholar
  17. 17.
    Coussement, K., and Van den Poel, D., Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques. Expert Syst. Appl. 34:313–327, 2008.CrossRefGoogle Scholar
  18. 18.
    Lin, S. W., Ying, K. C., Chen, S. C., and Lee, Z. J., Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst. Appl. 35(4):1817–1824, 2008.CrossRefGoogle Scholar
  19. 19.
    Saini, V. D., Nanda, N. C., and Maulik, D., Basic principles of ultrasound and Doppler effect, Doppler echocardiography. Lea & Febiger, Philadelphia, 1993.Google Scholar
  20. 20.
    Madeira, M. M., Tokhi, M. O., and Ruano, M. G., Real-time implementation of a Doppler signal spectral estimator using sequential and parallel processing techniques. Microprocess. Microsyst. 24(3):153–167, 2000.CrossRefGoogle Scholar
  21. 21.
    Karabetsos, E., Papaodysseus, C., and Koutsouris, D., Design and development of a new ultrasonic doppler technique for estimation of the aggregation of red blood cells. Journal of the International Measurement Confederation, Elsevier 24(Issue 4):207–215, 1998. doi:10.1016/S0263-2241(98)00053-0.Google Scholar
  22. 22.
    Akay, M., Wavelet applications in medicine. IEEE Spectrum 34:50–56, 1997.CrossRefGoogle Scholar
  23. 23.
    Liang, H., and Nartimo, I. A feature extraction algorithm based on wavelet packet decomposition for heart sound signals. Proceedings of the IEEE-SP International Symposium, pp. 93–96, 1998.Google Scholar
  24. 24.
    Quiroga, R. Q. Quantitative analysis of EEG signals: Time-frequency methods and Chaos theory, Ph.D. Thesis; Lübeck: Intitute of Physiology, Medical University, 1998.Google Scholar
  25. 25.
    Devasahayam, S. R., Signals and systems in biomedical engineering. Kluwer, Dordoecht, 2000.CrossRefGoogle Scholar
  26. 26.
    Burrus, C. S., Gopinath, R. A., and Guo, H., Introduction to wavelet and wavelet transforms. Prentice Hall, USA, 1998.Google Scholar
  27. 27.
    Coifman, R. R., and Wickerhauser, M. V., Entropy-based algorithms for best basis selection. IEEE Trans. Inf. Theory 38(2):713–718, 1992.MATHCrossRefGoogle Scholar
  28. 28.
    Quiroga, R. Q., Roso, O. A., and Basar, E., Wavelet entropy: A measure of order in evoked potentials, Evoked potentials and magnetic fields, vol. 49. Elsevier, Amsterdam, pp. 298–302, 1999.Google Scholar
  29. 29.
    Daisuke, T., and Shigeo, A., Fuzzy least squares support vector machines for multiclass problems. Neural Netw. Fields, Elsevier 16:785–792, 2003.Google Scholar
  30. 30.
    Gunn, S. R. Support vector machines for classification and regression, ISIS, Technical Report, University of Southampton, Department of Electrical and Computer Science, 1998.Google Scholar
  31. 31.
    Burbidge, R., and Buxton, B. An introduction to support vector machines for data mining, Young OR 12, University of Nottingham, pp. 3–15, 2001.Google Scholar
  32. 32.
    Kim, H. C., Pang, S., Je, H. M., Kim, D., and Bang, S. Y., Constructing support vector machine ensemble. Pattern Recogn., Elsevier 36:2757–2767, 2003.MATHCrossRefGoogle Scholar
  33. 33.
    Goh, K. S., Chang, E., and Cheng, K. T. SVM binary classifier ensembles for image classification, CIKM’01. Atlanta, Georgia, USA, pp. 395–402, 2001.Google Scholar
  34. 34.
    Gokcay, E., and Principe, I., Information theoretic clustering. IEEE Trans. Pattern Anal. Mach. Intell. 24(Issue 2):158–170, 2002.CrossRefGoogle Scholar
  35. 35.
    Jenssen, R., Hild, K. E., II, Erdogmus, D., Principe, J. C., and Eltoft, T., Clustering using Renyi’s entropy. Proc. Int. Jt. Conf. Neural Netw. 1:523–528, 2003.CrossRefGoogle Scholar
  36. 36.
    McQueen, J. Some methods for classification and analysis of multivariate observations. In: Fifth Berkley Symposium on Mathematical Statistics and Probability, pp. 281–297, 1967.Google Scholar
  37. 37.
    Eltoft, T., and Defigueiredo, R. J. P., A new neural network for cluster-detection-and-labeling. IEEE Trans. Neural Netw. 9(5):1021–1035, 1998.CrossRefGoogle Scholar
  38. 38.
    Ben-Hur, A., Hom, D., Siegelmann, H. T., and Vapnik, V., Support vector clustering. J. Mach. Learn. Res. 2:125–137, 2001.Google Scholar
  39. 39.
    Bakhtazad, A., Palazoglu, A., and Romagnoli, J. A., Process data de-noising using wavelet transform. Intell. Data Anal. 3:267–285, 1999.MATHCrossRefGoogle Scholar
  40. 40.
    Osareh, A., Mirmehdi, M., Thomas, B., and Markham, R. Comparative exudate classification using support vector machines and neural networks. In: Dohi, T., and Kikinis, R. (Eds.), 5th International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer LNCS 2489, pp. 413–420, 2002.Google Scholar
  41. 41.
    Centor, R. M., Signal detectability: The use of ROC curves and their analysis. Med. Decis. Mak. 11:102–106, 1991.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Department of Computer EngineeringPamukkale UniversityDenizliTurkey
  2. 2.Department of Computer EngineeringSelcuk UniversityKonyaTurkey

Personalised recommendations