We have proposed a morphological approach based on an evolutionary learning for software development cost estimation (SDCE). The dilation–erosion perceptron (DEP) method which is a hybrid artificial neuron is built on mathematical morphology (MM) framework. This method has its roots in the complete lattice theory. The proposed work also presents an evolutionary learning procedure, i.e., a chaotic modified genetic algorithm (CMGA) to construct the DEP (CMGA) model overcoming the drawbacks arising in the morphological operator’s gradient estimation in the classical learning procedure of DEP. The experimental analysis was conducted on estimation of five different SDCE problems and then analyzed using three performance measurement metrics.
View more info for "Chaos-based Modified Morphological Genetic Algorithm for Software Development Cost Estimation"
|Journal||Data powered by TypesetAdvances in Intelligent Systems and Computing|
|Publisher||Data powered by TypesetSpringer Singapore|