Title :
Software quality prediction using median-adjusted class labels
Author :
Pizzi, Nicolino J. ; Summers, Arthur R. ; Pedrycz, Witold
Author_Institution :
Inst. for Biodiagnostics, Nat. Res. Council of Canada, Winnipeg, Man., Canada
fDate :
6/24/1905 12:00:00 AM
Abstract :
Software metrics aid project managers in predicting the quality of software systems. A method is proposed using a neural network classifier with metric inputs and subjective quality assessments as class labels. The labels are adjusted using fuzzy measures of the distances from each class center computed using robust multivariate medians
Keywords :
learning (artificial intelligence); multilayer perceptrons; pattern classification; software development management; software engineering; software metrics; software quality; fuzzy set theory; learning; median-adjusted class labels; multilayer perceptron; pattern classification; quality assessments; software development; software metrics; software quality prediction; training set; Multilayer perceptrons; Neural networks; Project management; Quality assessment; Quality management; Robustness; Software measurement; Software metrics; Software quality; Testing;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007518
