Software effort estimation based on the optimal Bayesian belief network

• Published in: Applied soft computing 2016-12, Vol.49, p.968-980
• Main Authors: Zare, Fatemeh, Khademi Zare, Hasan, Fallahnezhad, Mohammad Saber
• Format: Article
• Language: English
• Subjects: Bayesian belief network; Optimal control; Software effort estimation; Software quality
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2016.08.004

[Display omitted] •Presenting an updatable Bayesian belief network for software effort estimation.•Considering all intervals of nodes of network as fuzzy numbers.•Applying optimal control by genetic algorithm for obtaining an accurate estimation.•Considering the effective components and steps of software development in software effort estimation.•Considering software quality in terms of the number of detected and removed defects in steps of software development. In this paper, we present a model for software effort (person-month) estimation based on three levels Bayesian network and 15 components of COCOMO and software size. The Bayesian network works with discrete intervals for nodes. However, we consider the intervals of all nodes of network as fuzzy numbers. Also, we obtain the optimal updating coefficient of effort estimation based on the concept of optimal control using Genetic algorithm and Particle swarm optimization for the COCOMO NASA database. In the other words, estimated value of effort is modified by determining the optimal coefficient. Also, we estimate the software effort with considering software quality in terms of the number of defects which is detected and removed in three steps of requirements specification, design and coding. If the number of defects is more than the specified threshold then the model is returned to the current step and an additional effort is added to the estimated effort. The results of model indicate that optimal updating coefficient obtained by genetic algorithm increases the accuracy of estimation significantly. Also, results of comparing the proposed model with the other ones indicate that the accuracy of the model is more than the other models.