Increasing the Accuracy of Software Fault Prediction Using Majority Ranking Fuzzy Clustering* - Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing - page 172

Increasing the Accuracy of Software Fault
Prediction Using Majority Ranking Fuzzy
Clustering *
Golnoush Abaei and Ali Selamat
Abstract. Although many machine-learning and statistical techniques have been
proposed widely for defining fault prone modules during software fault prediction,
but this area have yet to be explored as still there is a room for stable and con-
sistent model with high accuracy. In this paper, a new method is proposed to in-
crease the accuracy of fault prediction based on fuzzy clustering and majority
ranking. In the proposed method, the effect of irrelevant and inconsistent modules
on fault prediction is decreased by designing a new framework, in which the entire
project's modules are clustered. The obtained results showed that fuzzy clustering
could decrease the negative effect of irrelevant modules on accuracy of estima-
tions. We used eight data sets from NASA and Turkish white-goods software to
evaluate our results. Performance evaluation in terms of false positive rate, false
negative rate, and overall error showed the superiority of our model compared to
other predicting strategies. Our proposed majority ranking fuzzy clustering ap-
proach showed between 3% to 18% and 1% to 4% improvement in false negative
rate and overall error respectively compared to other available proposed models
(ACF and ACN) in at least half of the testing cases. The results show that our
systems can be used to guide testing effort by prioritizing the module's faults in
order to improve the quality of software development and software testing in a
limited time and budget.
Keywords: Software fault prediction, Fuzzy clustering, False negative rate (FNR),
False positive rate (FPR).