Self-organising networks in modelling experimental data in software engineering

Abstract

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modelling. A number of various modelling methodologies and detailed modelling designs have been proposed including neural networks and fuzzy models. The authors introduce self-organising networks (SON) that result from a synergy of fuzzy inference schemes and polynomial neural networks (PNNs). The latter has included an efficient scheme of selecting input variables of the model being realised on a basis of a group method of data handling (GMDH) algorithm. The authors discuss a detailed architecture of the SON and propose a comprehensive learning algorithm. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SON are not predetermined (as is the case in a popular topology of a multilayer perceptron). The experimental results include well-known software data such as the one describing software modules of the medical imaging system (MIS) and the NASA data set concerning software cost estimation. The experimental results reveal that the proposed model exhibits high accuracy.