Exploring the behaviour of neural network software quality models

Author

Khoshgoftaar, Taghi M. ; Szabo, Robert M. ; Guasti, Peter J.

Author_Institution

Dept. of Comput. Sci., Florida Atlantic Univ., Boca Raton, FL, USA

Volume

10

Issue

3

fYear

1995

fDate

5/1/1995 12:00:00 AM

Firstpage

89

Lastpage

96

Abstract

We explore the behaviour of neural network software quality models. We select a multiple regression quality model from the principal components of software complexity metrics collected from a large commercial software system. We train two neural networks; one with the complete set of principal components and one with the set of components selected by multiple regression model selection. Comparisons of the three models, for two quality measures gathered from five related software systems, lead to a better understanding of neural network software quality models, and the relationship between software complexity metrics and software quality metrics

Keywords

neural nets; software metrics; software quality; statistical analysis; large commercial software system; multiple regression model selection; multiple regression quality model; neural network training; principal components; software complexity metrics; software quality metrics; software quality models;

fLanguage

English

Journal_Title

Software Engineering Journal

Publisher

iet

ISSN

0268-6961

Type

jour

Filename

391466