By Topic

Early Software Quality Prediction Based on a Fuzzy Neural Network Model

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Bo Yang ; Univ. of Electron. Sci. & Technol. of China, Chengdu ; Lan Yao ; Hong-Zhong Huang

For the management of a software development project, a software quality prediction model is very helpful since it can provide the management with useful information needed for decision-makings. Many software quality prediction models and techniques have been proposed and studied in the literature. Nevertheless, the complicated situations of software development process call for a more flexible model that can cater for all factors that have impact on the quality of the target software, including the characteristics of the software product, the characteristics of the development process and the operation conditions. In this paper, a software quality prediction model based on a fuzzy neural network is presented. 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. The model exhibits some favorable features such as being able to deal with objective data collected in the software development process as well as knowledge/experiences obtained from experts or from similar projects, which is the main information that is available in the early phases of a software development process. Using this model, early prediction of software quality becomes feasible and the management can have knowledge of the quality of target software product as early as possible, which helps to identify design errors and avoid expensive rework. Experimental results show that for problems of small-to-medium scale, the proposed model can be easily trained and thus can be of practical use.

Published in:

Natural Computation, 2007. ICNC 2007. Third International Conference on  (Volume:1 )

Date of Conference:

24-27 Aug. 2007