Title of article
A Novel ICA-based Estimator for Software Cost Estimation
Author/Authors
Sadeghi, Behrouz Tayabad Unit - Payam Nour University of Khorasan Razavi , Khatibi Bardsiri, Vahid Kerman Branch - Islamic Azad University , Esfandiari, Monireh Tayabad Unit - Payam Nour University of Khorasan Razavi , Hoseinzadeh, Farzad Lengeh Branch - Islamic Azad University
Pages
10
From page
15
To page
24
Abstract
One of the most important and valuable goal of software development life cycle is software cost estimation or SCE. There have been proposed so many models using heuristic and meta-heuristic algorithms to do machine learning process for SCE. COCOMO81 is one of the most popular models for SCE proposed by Barry Boehm in 1981. However COCOMO81 is an old estimation model, it has been widely used for the purpose of cost estimation in its new forms. In this paper, the Imperialism Competition Algorithm (ICA) has been employed to tune the COCOMO81 parameters. Experimental results show that in the separated COCOMO81 dataset, ICA can estimate the COCOMO81 model parameters such that the performance parameters are significantly improved. The proposed hybrid model is flexible enough to tune the parameters for any data sets in form of COCOMO81.
Keywords
DCOCOMO81 , software cost estimation , accuracy , meta-heuristic , imperialism competition algorithm
Journal title
Astroparticle Physics
Serial Year
2015
Record number
2422741
Link To Document