Genetic Algorithm and Support Vector Regression for Software Effort Estimation

Abstract:

For software developers, accurately forecasting software effort is very important. In the field of software engineering, it is also a very challenging topic. Miscalculated software effort in the early phase might cause a serious consequence. It not only effects the schedule, but also increases the cost price. It might cause a huge deficit. Because all of the different software development team has it is own way to calculate the software effort, the factors affecting project development are also varies. In order to solve these problems, this paper proposes a model which combines genetic algorithm (GA) with support vector machines (SVM). We can find the best parameter of SVM regression by the proposed model, and make more accurate prediction. During the research, we test and verify our model by using the historical data in COCOMO. We will show the results by prediction level (PRED) and mean magnitude of relative error (MMRE).

• Periodical: Advanced Materials Research (Volumes 282-283)
• Pages: 748-752
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.282-283.748
• Online since: July 2011
• Authors: Jin Cherng Lin, Chu Ting Chang
• Keywords: COCOMO, Genetic Algorithm (GA), Software Effort, Support Vector Machine (SVM), Support Vector Regression (SVR)

References

[1] S.J. Huang and N.H. Chiu, Applying fuzzy neural network to estimate software development effort, Applied Intelligence, 2009, pp.73-83.

DOI: 10.1007/s10489-007-0097-4

[2] M Azzeh, D Neagu, PI Cowling, Fuzzy grey relational analysis for software effort estimation, Empir Softw Eng 15(1) : 60-90. DOI 10. 1007/s10664-009-9113-0.

DOI: 10.1007/s10664-009-9113-0

[3] Haykin, S. Neural Networks: A Comprehensive Foundation, Prentice Hall, 1999, ISBN 0-13-273350-1.

[4] Chipperfield, A. J., Fleming, P. J. and Pohlheim, H. P, A genetic algorithm toolbox for MATLAB, Proceedings of International Conference on Systems Engineering, Coventry, 6-8 September 1994, pp.200-207.

[5] Goldberg, D.E. Genetic Algorithm in Search, Optimization and Machine Learning, Addision-Wesley, New York, (1989).

[6] Davis, L. Handbook of Genetic Algorithm., Van Nostrand Reinhold, New York, (1991).

[7] V.N. Vapnik, The Nature of Statistical Learning Theory, New York: Springer, (1995).

[8] V.N. Vapnik, Statistical learning theory,. New York: Wiley, (1998).

[9] B. -W Liu and P. -S Yu Correction of QPESUMS Radar Rainfall Using Machine Learning Methods, (2009).

[10] Anna Corazza, Sergio Di Martino, Filomena Ferrucci, Carmine Gravino, and Emilia Mendes. Investigating the use of Support Vector Regression for web effort estimation, , Empir Softw Eng. IDO 10. 1007/s10664-010-9138-4.

DOI: 10.1007/s10664-010-9138-4

[11] C. -C. Chang and C. -J. Lin, LIBSVM: a library for support vector machines, 2001. Software available at http: /www. csie. ntu. edu. tw/~cjlin/libsvm/ , visited in 2010. 12.

[12] G. Boetticher, T. Menzies and T. Ostrand, PROMISE Repository of empirical software engineering data http: /promisedata. org/ repository, West Virginia University, Department of Computer Science, (2007).

[13] Boehm, B. W., software Engineering Economics, IEEE Transcactions on Software Engineering, Vo1. 10, No. 1, 1984, pp.4-21.