An enhanced neural network technique for software risk analysis.

An enhanced technique for risk categorization is presented. This technique, PCA-ANN, provides an improved capability to discriminate high-risk software. The approach draws on the combined strengths of pattern recognition, multivariate statistics and neural networks. Principal component analysis is u...

Full description

Bibliographic Details

Published in:	IEEE Transactions on software engineering 28, 9 (2002).
Main Author:	Neumann, D.E
Format:	Article
Language:	English
Subjects:	Cross-normalization. Enhanced neural network technique. High-risk software modules. Input data normalization. Multicollinearity. Multivariate statistics. Pattern recognition. Principal component analysis. Risk categorization. Software risk analysis.