A Novel Approach to Software Maintainability Prediction
Software maintainability, one of the software quality attributes, is of great concern for the management of a software development project. A software maintainability prediction model would be very helpful since it can provide the management with useful information needed for decision-makings. In this paper, we adopt a novel approach which is based on a fuzzy neural network to develop a software quality/maintainability prediction model. The proposed model is a hybrid model of artificial neural network (ANN) and fuzzy logic (FL), which exploits the advantages of ANN and FL while eliminating their limitations. Using this model, early prediction of software quality/maintainability becomes feasible, which helps to identify design deficiencies and avoid expensive rework.
software quality software maintenance fuzzy neural network (FNN) fuzzy self-adaptation learning control network (FALCON) computational intelligence
YANG Bo YA Lano GUO Suchang HUANG Hongzhong
Department of Industrial Engineering, School of Mechatronics Engineering,University of Electronic Science and Technology of China, China
国际会议
The First International Conference on Maintenance Engineering(首届维修工程国际学术会议)
成都
英文
887-894
2006-10-15(万方平台首次上网日期,不代表论文的发表时间)