New Approach with Hybrid of Artificial Neural Networkand Ant Colony Optimization in Software CostEstimation

Nowadays, software cost estimation (SCE) with machine learning techniquesare more performance than other traditional techniques which were based onalgorithmic techniques. In this paper, we present a new hybrid model of multi-layerperceptron (MLP) artificial neural network (ANN) and ant colony optimization(ACO) algorithm for high accuracy in SCE called Multilayer Perceptron Ant ColonyOptimization (MLPACO). Current research uses some of features for increasingaccuracy of estimation among of the existing parameters has been considered foreffort estimation in software projects, and then these selected features will befiltered by ACO algorithm in order to reach highest accuracy in estimation andoptimization of MLP ANN method. The results show that this novel approach withhigh accuracy for more than 80% cases is better than algorithmic constructive costmodel (COCOMO) in the majority cases. Also, the results of proposed algorithmshow that mean magnitude of relative error (MMRE) in the proposed algorithm islower than COCOMO model.

Keywords:

Software Cost Estimation , Artificial Neural Network , Ant Colony Optimization , Effort , Optimization