Software Defect Classification with a Variant of NSGA-II and Simple Voting Strategies

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9275)


Software Defect Prediction is based on datasets that are imbalanced and therefore limit the use of machine learning based classification. Ensembles of genetic classifiers indicate good performance and provide a promising solution to this problem. To further examine this solution, we performed additional experiments in that direction. In this paper we report preliminary results obtained by using a Matlab variant of NSGA-II in combination with four simple voting strategies on three subsequent releases of the Eclipse Plug-in Development Environment (PDE) project. Preliminary results indicate that the voting procedure might influence software defect prediction performances.


SDP SBSE Multi-objective optimisation NSGA-II 



The work presented in this paper is supported by the University of Rijeka Research Grant


  1. 1.
    Abraham, A., Goldberg, R.: Evolutionary Multiobjective Optimization: Theoretical Advances and Applications. Springer, Heidelberg (2006). Science & Business MediaGoogle Scholar
  2. 2.
    Afzal, W., Torkar, R.: A comparative evaluation of using genetic programming for predicting fault count data. In: ICSEA 2008, pp. 407–414 (2008)Google Scholar
  3. 3.
    Bhowan, U., Johnston, M., Zhang, M., Yao, X.: Evolving diverse ensembles using genetic programming for classification with unbalanced data. IEEE TEC 17(3), 368–386 (2013)Google Scholar
  4. 4.
    Coello Coello, C., Lamont, G.: Evolutionary Algorithms for Solving Multi-Objective Problems. Genetic and Evolutionary Computation Series. Springer, Berlin (2007)zbMATHGoogle Scholar
  5. 5.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE TEC 6(2), 182–197 (2002)Google Scholar
  6. 6.
    Ferrucci, F., Gravino, C., Oliveto, R., Sarro, F.: Genetic programming for effort estimation: an analysis of the impact of different fitness functions. In: SSBSE 2010, pp. 89–98 (2010)Google Scholar
  7. 7.
    Galinac Grbac, T., Mauša, G., Dalbelo Bašić, B.: Stability of software defect prediction in relation to levels of data imbalance. In: SQAMIA (2013)Google Scholar
  8. 8.
    Harman, M., McMinn, P.: A theoretical and empirical study of search based testing: local. global and hybrid search. IEEE TSE 36(2), 226–247 (2010)Google Scholar
  9. 9.
    Mauša, G., Galinac Grbac, T., Dalbelo Bašić, B.: Software defect prediction with bug-code analyzer - a data collection tool demo. In: SoftCOM 2014 (2014)Google Scholar
  10. 10.
    Sarro, F., Di Martino, S., Ferrucci, F., Gravino, C.: A further analysis on the use of genetic algorithm to configure support vector machines for inter-release fault prediction. In: SAC 2012, pp. 1215–1220Google Scholar
  11. 11.
    Sarro, F., Ferrucci, F., Gravino, C.: Single and multi objective genetic programming for software development effort estimation. In: ACM SAC 2012, pp. 1221–1559 (2012)Google Scholar
  12. 12.
    Shin, Y., Harman, M.: Pareto efficient multiobjective test case selection. In: ISSTA 2007, pp. 140–150 (2007)Google Scholar
  13. 13.
    Wang, S., Yao, X.: Using class imbalance learning for software defect prediction. IEEE Trans. Reliab. 62(2), 434–443 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Faculty of EngineeringUniversity of RijekaRijekaCroatia

Personalised recommendations