2026-05-01T02:33:59Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4589 2021-12-13T02:12:49Z 1582963302567:1597824175385 user-ucsy

Application of neural networks for software quality prediction using object-oriented metrics Thwin, Mie Mie Thet Quah, Tong Seng This paper presents the application of neural networks in software quality estimation using object-oriented metrics. In this paper,two kinds of investigation are performed. The first on predicting the number of defects in a class and the second on predicting thenumber of lines changed per class. Two neural network models are used, they are Ward neural network and General Regressionneural network (GRNN). Object-oriented design metrics concerning inheritance related measures, complexity measures, cohesionmeasures, coupling measures and memory allocation measures are used as the independent variables. GRNN network model isfound to predict more accurately than Ward network model. 2005-05 http://hdl.handle.net/20.500.12678/0000004589 https://meral.edu.mm/records/4589