期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：2
页码：391-394
语种：English
出版社：Ayushmaan Technologies
摘要：Software complexity metrics of a software module represent a measure of the functional complexity of the module. Identifying software modules based on their software complexity metrics into different error prone categories is a difficult problem in software engineering. This research investigates the applicability of neural network classifiers for identifying fault-prone software modules using a dataset from a software system. A prototype multi layer perceptron neural network classifier using a modified back propagation algorithm is constructed for this purpose. Our preliminary results suggest that a multi layer perceptron network can be used as a tool for identifying fault-prone software modules. Other issue such as representation of software metrics is also discussed.
