Cuckoo search based hybrid models for improving the accuracy of software effort estimation

This research proposes a new approach which is based on Cuckoo Search algorithm for the prediction of software development effort. It uses Cuckoo Search for discovering the best possible parameters of COCOMO II model and then further hybridizes with ANN for increasing the accuracy to better predict the software development effort. The proposed hybrid models have been tested on two standard datasets. During experimentation, it has been seen that the proposed hybrid models provide more accurate and effective results than other existing models. The result has been analyzed with MMRE and three different types of PRED 25, 30 and 40% that shows the efficiency and capability of the proposed hybrid models. A comparative study of computational complexity with other existing approach has also been done which shows the superiority of the proposed model over existing approaches.

[1]  Barry W. Boehm,et al.  Software Engineering Economics , 1993, IEEE Transactions on Software Engineering.

[2]  Sweta Kumari,et al.  Performance Analysis of the Software Cost Estimation Methods: A Review , 2013 .

[3]  Xin-She Yang,et al.  Cuckoo Search via Lévy flights , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[4]  Nasser Tadayon.  Neural network approach for software cost estimation , 2005, International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II.

[5]  Iman Attarzadeh,et al.  Proposing an Enhanced Artificial Neural Network Prediction Model to Improve the Accuracy in Software Effort Estimation , 2012, 2012 Fourth International Conference on Computational Intelligence, Communication Systems and Networks.

[6]  Ioan Salomie,et al.  Optimizing the Semantic Web Service Composition Process Using Cuckoo Search , 2011, IDC.

[7]  Riyanarto Sarno,et al.  Optimizing effort and time parameters of COCOMO II estimation using fuzzy multi-objective PSO , 2017, 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI).

[8]  Sweta Kumari,et al.  A Genetic Algorithm Approach for Multi-criteria Project Selection for Analogy-Based Software Cost Estimation , 2015 .

[9]  A. R. Venkatachalam.  Software cost estimation using artificial neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[10]  Avinash Singh,et al.  Optimizing Basic COCOMO Model Using Simplified Genetic Algorithm , 2016 .

[11]  M. Madheswaran,et al.  Enhancement of prediction accuracy in COCOMO model for software project using neural network , 2014, Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT).

[12]  Sweta Kumari,et al.  Fuzzy Clustering and Optimization Model for Software Cost Estimation , 2015 .

[13]  Alaa F. Sheta,et al.  Estimation of the COCOMO Model Parameters Using Genetic Algorithms for NASA Software Projects , 2006 .

[14]  Gavin R. Finnie,et al.  Using Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort , 1994, Australas. J. Inf. Syst..

[15]  Barry W. Boehm,et al.  Software development cost estimation approaches — A survey , 2000, Ann. Softw. Eng..

[16]  H. Stanley,et al.  Optimizing the success of random searches , 1999, Nature.

[17]  Harish Mittal,et al.  Software cost estimation using fuzzy logic , 2010, ACM SIGSOFT Softw. Eng. Notes.

[18]  Amir Hossein Gandomi,et al.  Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems , 2011, Engineering with Computers.

[19]  Sweta Kumari,et al.  Comparison and Analysis of Different Software Cost Estimation Methods , 2013 .