Abstract—Imprecise estimation of software development cost is one of the major factors that contributes in the failure of software projects. Several algorithmic models have been
devised for cost estimation; but they lack the ability to handle
imprecision and uncertainties associated with the software project attributes. Embedding a fuzzy component in the algorithmic model enables it to deal with the imprecision and
uncertainty problem; consequently improves its accuracy.
However, the performance of any fuzzy system depends on the settings of its parameters. This paper proposes a genetic fuzzy
model for effort estimation. Genetic algorithm is used in tuning
the fuzzy sets of the model to optimize the estimation accuracy.
MATLAB 2012 was used in implementing the proposed model.
The model was evaluated using artificial datasets derived from COCOMONASA2 dataset. The experimental results showed
that the accuracy and sensitivity of the proposed model is
superior to COCOMO. It’s note worthy to mention that the
idea of the paper is not restricted to COCOMO; it could be applied to other algorithmic models.
Index Terms—COCOMO81, genetic algorithms, fuzzy systems, genetic fuzzy, effort estimation.
Abeer Hamdy is with the Electronics Research Institute and British
University, Egypt (e-mail: Abeer.hamdy@bue.edu.eg)
[PDF]
Cite: Abeer Hamdy, "Abeer Hamdy," International Journal of Modeling and Optimization vol. 4, no. 3, pp. 227-232, 2014.