Title: Evolutionary neural network classifiers for software effort estimation

Authors: Noor Khalaf L. Alhammad; Esra Alzaghoul; Fawaz A. Alzaghoul; Mohammed Akour

Addresses: Department of Computer Information Systems, The University of Jordan, Amman, Jordan ' Department of Computer Information Systems, The University of Jordan, Amman, Jordan ' Department of Computer Information Systems, The University of Jordan, Amman, Jordan ' Software Engineering Department, Yarmouk University, Irbid, Jordan

Abstract: The estimation of software development efforts has become a crucial activity in software project management. Due to this importance, many researchers focused their efforts on proposing models for relationship construction between efforts and software size and requirements. However, there are still gaps and problems in software effort's estimation process; due to the lack of enough data available in the initial stage of project life cycle. The need for an enhanced and an accurate method for software effort estimation is an urgent issue that challenged software project-management researchers around the world. This work proposes a model based on artificial neural network (ANN) and dragonfly algorithm (DA), in order to provide more accurate model for software effort estimation. The applicability of the model was evaluated using several experiments and the results were in favour of the enhancement with more accurate effort estimation.

Keywords: COCOMO 81; artificial neural network; ANN; dragonfly algorithm; effort estimation.

DOI: 10.1504/IJCAET.2020.10027779

International Journal of Computer Aided Engineering and Technology, 2020 Vol.12 No.4, pp.495 - 512

Received: 16 May 2017
Accepted: 04 Jan 2018

Published online: 29 May 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article