Two Stages Feature Selection Based on Filter Ranking Methods and SVMRFE on Medical Applications

  • Hayet DjellaliEmail author
  • Nacira Ghoualmi Zine
  • Nabiha Azizi
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 1)


This paper investigates feature selection stage applied to medical classification of disease on datasets from UCI repository. Feature selection methods based on minimum Redundancy Maximum Relevance (mRMR) filter and Ficher score were applied, each of them select a subset of features then the selection criteria is used to get the initial features subset. The second stage Support vector machine recursive feature elimination is performed to have the final subset. Experiments show that the proposed method provide an accuracy of 99.89 % on hepatitis dataset and 97.81 % on Wisconcin Breast cancer dataset and outperforms MRMR and Support vector machine recursive feature elimination SVM-RFE methods, as well as other popular methods on UCI database, and select features that are relevant in discriminating cancer class (malign/benign).


Support Vector Machine Feature Selection Support Vector Machine Classifier Feature Subset Feature Selection Method 
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.
    Saeys, Y., Inza, I., Larranaga, P.: A review of feature selection technique in bioinformatics. J. Bioinform. Oxford university press, 1–10 (2005)Google Scholar
  2. 2.
    Ding, C., Peng, H., Long, F., Ding, C.: Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8) (2005)Google Scholar
  3. 3.
    Yoon, S., Kim, S.: Mutual information-based SVM-RFE for diagnostic classification of digitized mammograms. J. Pattern Recognit. Lett. 30, 1489–1495 (2009)CrossRefGoogle Scholar
  4. 4.
    Mitra, S., Shankar, B.U.: Medical image analysis for cancer management in natural computing framework. Inf. Sci. 306, 111–131 (2015)CrossRefGoogle Scholar
  5. 5.
    Yang, F., Mao, K.Z.: Robust feature for microaccray data based on multicriterion fusion. IEEE/ACM trans. Comput. Biol. Bioinform. 8(4), 1080–1092 (2011).Google Scholar
  6. 6.
    Akay, M.F.: Support vector machines combined with feature selection for breast cancer diagnosis. J. Expert Syst. Appl. 36, 3240–3247 (2009)CrossRefGoogle Scholar
  7. 7.
    Yang, P., Bing B., Zhou, J.Y., Yang, A., Zomaya. Y.: Stability of feature selection algorithms and ensemble feature selection methods in bioinformatics, pp. 1–23 (2006).Google Scholar
  8. 8.
    Zhang, J., Hu, X., Li, P., He, W., Zhang H.Y.: A hybrid feature selection approach by correlation based filters and svm-rfe. In: International Conference on Pattern Recognition, 3684–3689 (2014).Google Scholar
  9. 9.
    Guyon, J., Weston, S., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46(1–3), 389–422 (2002)CrossRefzbMATHGoogle Scholar
  10. 10.
    Bolon Canedo, V., Sanchez Maono, N., Betanzos, A.: A review of feature selection methods on synthetic data. J. knowl. Inform. Syst. 34, 483–519 (2013).Google Scholar
  11. 11.
    Jirapech Umpai T., Aitken. S.: Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes. BMC Bioinform. 6(1), 148 (2005)Google Scholar
  12. 12.
    Li, L., Weinberg, C.R., Darden, T.A., Pedersen, L.G.: Gene selection for sample classification based on gene expression data: study of sensitivity to choice of parameters of the ga/knn method. Bioinform. 17(12), 1131–1142 (2001)CrossRefGoogle Scholar
  13. 13.
    Umbach, D.M., Li L., Terry, P., Taylor. J. A.: Application of the ga/knn method to seldi proteomics data. Bioinform. 20(10) (2004)Google Scholar
  14. 14.
    Yan, K., Zhang, D.: Feature selection and analysis on correlated gas sensor data with recursive feature elimination. J. Sens. actuators B chem. 353–363 (2015).Google Scholar
  15. 15.
    Piyushkumar A.M., Rajapakse, J.C.: SVM-RFE with mrmr filter for gene selection, IEEE Trans. Nanobioscience 9(1) (2010)Google Scholar
  16. 16.
    Heath, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, W.: The digital database for screening mammography. In: Yaffe, M. (ed.), Proceeding 5th IWDM. Medical Physics Publishing, pp. 212–218 (2001).Google Scholar
  17. 17.
    Maka, M.W., Kung, S.Y.: Fusion of feature selection methods for pairwise scoring SVM. Neurocomputing 71, 3104–3113 (2008)CrossRefGoogle Scholar
  18. 18.
    Kai-Bo D., Rajapakse, H., Wang H., Azuaje F.: Multiple SVM-RFE for gene selection in cancer classification with expression data. IEEE Trans. Nanobioscience 4(3), 228–234 (2005).Google Scholar
  19. 19.
    Tang, Y.C., Zhang Y.Q., Huang, Z.: Development of two stage SVMRFE Gene selection strategy for microarray expression data analysis. IEEE ACM. Trans. Comput. Biol. Bioinform. 4(3), 365–381 (2007).Google Scholar
  20. 20.
    Zhang, Y., Ding, C., Li, T.: Gene selection algorithm by combining relief and mRMR. BMC Genom. 9(2), S27 (2008)CrossRefGoogle Scholar
  21. 21.
    Peng, Y., Wu, Z., Jiang, J.: A novel feature selection approach for biomedical data classification. J. Biomed. Inform. 43, 15–23 (2010)CrossRefGoogle Scholar
  22. 22.
    Vapnick, V.: Statistical learning theory, Wiley (1998)Google Scholar
  23. 23.

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Hayet Djellali
    • 1
    • 2
    • 4
    Email author
  • Nacira Ghoualmi Zine
    • 1
    • 2
    • 4
  • Nabiha Azizi
    • 3
    • 4
  1. 1.Computer Science DepartmentAnnabaAlgeria
  2. 2.LRS LaboratoryAnnabaAlgeria
  3. 3.Labged LaboratoryAnnabaAlgeria
  4. 4.Badji Mokhtar UniversityAnnabaAlgeria

Personalised recommendations