A Novel Hybrid Algorithm for Software Cost Estimation Based on Cuckoo Optimization and K-Nearest Neighbors Algorithms

E. E. Miandoab, F. S. Gharehchopogh

Abstract


The inherent uncertainty to factors such as technology and creativity in evolving software development is a major challenge for the management of software projects. To address these challenges the project manager, in addition to examining the project progress, may cope with problems such as increased operating costs, lack of resources, and lack of implementation of key activities to better plan the project. Software Cost Estimation (SCE) models do not fully cover new approaches. And this lack of coverage is causing problems in the consumer and producer ends. In order to avoid these problems, many methods have already been proposed. Model-based methods are the most familiar solving technique. But it should be noted that model-based methods use a single formula and constant values, and these methods are not responsive to the increasing developments in the field of software engineering. Accordingly, researchers have tried to solve the problem of SCE using machine learning algorithms, data mining algorithms, and artificial neural networks. In this paper, a hybrid algorithm that combines COA-Cuckoo optimization and K-Nearest Neighbors (KNN) algorithms is used. The so-called composition algorithm runs on six different data sets and is evaluated based on eight evaluation criteria. The results show an improved accuracy of estimated cost.


Keywords


Software Cost Estimation; COCOMO model; COA-Cuckoo optimization algorithm; KNN algorithm

Full Text:

PDF

References


F. S. Gharehchopogh, “Neural networks application in software cost estimation: a case study”, 2011 IEEE International Symposium on Innovations in Intelligent Systems and Applications, pp. 69-73, Istanbul, Turkey, June 15-18, 2011

B. Boehm, B. Clark, E. Horowitz, R. Shelby, C. Westland, “An overview of the COCOMO 2.0 software cost model”, Software Technology Conference, 1995

K. Parkash, H. Mittal, “Software cost estimation using fuzzy logic”, ACM SIGSOFT Software Engineering, Vol. 35, No. 1, pp. 1-7, 2010

Z. A. Dizaji, F. S. Gharehchopogh, “A hybrid of ant colony optimization and chaos optimization algorithms approach for software cost estimation”, Indian Journal of Science and Technology, Vol 8, No. 2, pp. 128–133, 2015

C. S. Reddy, P. S. Rao, K. Raju, V. V. Kumari, “A new approach for estimating software effort using RBFN network”, International Journal of Computer Science and Network Security, Vol. 8, No. 7, pp. 237-241, 2008

A. B. Krishna, T. K. R. Krishna, “Fuzzy and swarm intelligence for software effort estimation”, Advances in Information Technology and Management, Vol. 2, No. 1, pp. 246-250, 2012

I. Maleki, L. Ebrahimi, F. S. Gharehchopogh, “A hybrid approach of firefly and genetic algorithms in software cost estimation”, MAGNT Research Report, Vol. 2, No. 6, pp. 372-388, 2014

S. Sarwar, “Proposing effort estimation of cocomo ii through perceptron learning rule”, Int. J. Comput. Appl., Vol. 7, No. 1, pp. 22–32, 2013

T. M. Cover, P. E. Hart, “Nearest neighbor pattern classification”, IEEE Trans. Inform. Theory, Vol. IT-13, pp 21-27, 1967

T. Bailey, A. K. Jain, “A note on distance weighted k-nearest neighbor rules”, IEEE Trans. Systems, Man Cybernatics, Vol. 8, pp. 311-313, 1978

X. S. Yang, S. Deb, "Cuckoo search via levy flights", World Congress on Nature &Biologically Inspired Computing (NaBIC2009). IEEE Publications, pp. 210–214, 2009

R Rajabioun, “Cuckoo optimization algorithm”, Applied Soft Computing, Vol. 11, pp. 5508–5518 , 2011

L. F. Capretz, V. Marza, “Improving effort estimation by voting software estimation models”, Advances in Software Engineering, Article ID 829725, pp. 1-8, 2009

S. Kumari, S. Pushkar, “Performance analysis of the software cost estimation methods: a review”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 3, No. 7, pp. 229-238, 2013




eISSN: 1792-8036     pISSN: 2241-4487