Volume 5, Issue 1, January 2014, Pages 72–81
Isa Maleki1, Ali Ghaffari2, and Mohammad Masdari3
1 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, West Azerbaijan, Iran
2 Department of Computer Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
3 Department of Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
Original language: English
Copyright © 2014 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
One of the most important effective factors the software companies face is the Software Cost Estimation (SCE) in software development process time. SCE is one of the subjects which have been considered in late decades in many researches. The real estimation in software development needs effort and cost factors which are done by use of the algorithmic and Artificial Intelligence (AI) models. Boehm used the COCOMO model which is an algorithmic model in 1981 for SCE. The low accuracy and non-reliable structures of the algorithmic models led to high risks of software projects. So, it is needed to estimate the cost of the project annually and compare it to the other techniques. The Meta-Heuristic algorithms have been developed well lately in software fields and SCE. Meta-heuristic and Genetic Algorithms (GA) and Ant Colony Optimization (ACO) solve the problems according to the optimization of the problems and are very efficient in optimizing the algorithmic models and the effective factors in cost estimation. In this paper we have proposed a hybrid model based on GA and ACO for optimization of the effective factors' weight in NASA dataset software projects. The results of the experiments show that the proposed model is more efficient than COCOMO model in software projects cost estimation and holds less Magnitude of Relative Error (MRE) in comparison to COCOMO model.
Author Keywords: Software Cost Estimation, COCOMO, Artificial Intelligence, Meta-Heuristic Algorithms, Genetic Algorithm, Ant Colony Optimization.
Isa Maleki1, Ali Ghaffari2, and Mohammad Masdari3
1 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, West Azerbaijan, Iran
2 Department of Computer Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
3 Department of Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
Original language: English
Copyright © 2014 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
One of the most important effective factors the software companies face is the Software Cost Estimation (SCE) in software development process time. SCE is one of the subjects which have been considered in late decades in many researches. The real estimation in software development needs effort and cost factors which are done by use of the algorithmic and Artificial Intelligence (AI) models. Boehm used the COCOMO model which is an algorithmic model in 1981 for SCE. The low accuracy and non-reliable structures of the algorithmic models led to high risks of software projects. So, it is needed to estimate the cost of the project annually and compare it to the other techniques. The Meta-Heuristic algorithms have been developed well lately in software fields and SCE. Meta-heuristic and Genetic Algorithms (GA) and Ant Colony Optimization (ACO) solve the problems according to the optimization of the problems and are very efficient in optimizing the algorithmic models and the effective factors in cost estimation. In this paper we have proposed a hybrid model based on GA and ACO for optimization of the effective factors' weight in NASA dataset software projects. The results of the experiments show that the proposed model is more efficient than COCOMO model in software projects cost estimation and holds less Magnitude of Relative Error (MRE) in comparison to COCOMO model.
Author Keywords: Software Cost Estimation, COCOMO, Artificial Intelligence, Meta-Heuristic Algorithms, Genetic Algorithm, Ant Colony Optimization.
How to Cite this Article
Isa Maleki, Ali Ghaffari, and Mohammad Masdari, “A New Approach for Software Cost Estimation with Hybrid Genetic Algorithm and Ant Colony Optimization,” International Journal of Innovation and Applied Studies, vol. 5, no. 1, pp. 72–81, January 2014.
