Genetically Modified Logistic Regression with Radial Basis Function for Robust Software Effort Prediction

  • Manas Gaur
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 390)


Existing logistic regression technique applies log-based function on the dataset and provides the necessary result for analysis. It has been for years for prediction analytics. This project develops a genetically modified evolutionary logistic regression technique using radial basis functions (GLR-RBF). This methodology employs three crucial stages. First stage is an evolutionary stage employing two fitness functions. Initially, the dataset obtained from the repository is modified using Genetic Algorithm (GA), followed by creation and simulation of radial basis neural network (RBFNN). The RBFNN is iteratively trained and simulated. The weight matrix generated in each stage is tested with a fitness function, which define the rule for selection of the best individual that will be appended to the dataset. The process of appending the weight matric to the dataset marks the second stage. In the third stage, the new set of covariates is fed into logistic regression operator which classifies the attributes based on effort response variable. This method has been tested in field of remote sensing image classification and other large dataset. This project also tests this technique for software effort prediction, which is regarded as the crucial activity before the commencement of the software development cycle. The model GLR-RBF was found be competitive when compared with similar standard models. The measure obtained from AUC indicates that GLR-RBF has reached the state-of-the-art.


Artificial neural network Radial basis functions Range-based classification Logistic regression Genetic algorithm Decision tree and Bayesian classifier Attribute reduction 


  1. 1.
    Hervas-Martinez, C., Martinez-Estudillo, F.J., Carbonero-Ruz, M.: Multilogistic regression by means of evolutionary product-unit neural networks. Neural Netw. 14, 201–208 (2004)Google Scholar
  2. 2.
    Krishnapuram, B., Carin, L., Figueiredo, M.A., Hartemink, A.J.: Sparse multinomial logistic regression: fast algorithm and generalization bounds. IEEE Trans. Pattern Anal. Mach. Intell. 27, 957–968 (2005)CrossRefGoogle Scholar
  3. 3.
    Nabney, I.T.: Efficient training of RBF networks for classification. Int. J. Neural Syst. 14, 201–208 (2004)CrossRefGoogle Scholar
  4. 4.
    Whitehead, B.A., Choate, T.D.: Cooperative-competitive genetic evolution of radial basis function centres and widths for time series prediction. In: IEEE Trans. Neural Netw. 7, 869–880 (1996)Google Scholar
  5. 5.
    Sentas P., Angelis L., Stamelos, I.: Multinomial logistic regression applied on software productivity prediction. In: Proceedings of the 9th PanHellenic Conference in informatics (2003)Google Scholar
  6. 6.
    Salem, A.M., Rekab, K., Whittaker, J.A.: Prediction of software failures through logistic regression. Inf. Softw. Technol. Elsevier 46, 781–789 (2004)CrossRefGoogle Scholar
  7. 7.
    Sentas, P., Angelis, L., Stamelos, I.: Software productivity and effort prediction with ordinal regression. Inf. Softw. Technol. Elsevier 45, 17–29 (2005)CrossRefGoogle Scholar
  8. 8.
    Krishnamurthy, S., Fisher, D.: Machine learning approaches to estimating software development effort. IEEE Trans. Softw. Eng. 126–137 (1995)Google Scholar
  9. 9.
    Papatheocharous, E.: Software cost modelling and estimation using artificial neural network enhanced input sensitivity analysis. J. Univ. Comput. Sci. 1–30 (2012)Google Scholar
  10. 10.
    Orr, M.J.: Optimising the widths of radial basis functions. In: Proceedings of the 5th Bazillian Symposium on Neural Network, pp. 26–29 (1998)Google Scholar
  11. 11.
    Chen, S., et al.: Orthogonal least square learning algorithm for radial basis function. In: IEEE Trans. Neural Netw. 2, 302–309 (1991)Google Scholar
  12. 12.
    Hunt K.J. et al.: Neural network for control system-A survey. In: Automatica 28, 1083–1112 (1992)Google Scholar
  13. 13.
    Buchtala, O., Klimek M., Sick, B.: Evolutionary optimization of radial basis function classifier for data mining application. In: IEEE Trans. Syst. Man, Cybern., B; Cybern. 35, 928–947 (2005)Google Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  1. 1.M. Tech, Software EngineeringDelhi Technological UniversityDelhiIndia

Personalised recommendations