Abstrait

Predicting the Software Fault Using the Method of enetic Algorithm

Mrs.Agasta Adline, Ramachandran .M

Software metrics and fault data belonging to a previous software version are used to build the software fault prediction model for the next release of the software. However there are certain cases when previous fault data are not present. In other words predicting the fault-proneness of program modules when the fault labels for modules are unavailable is a challenging task frequently raised in the software industry. There is need to develop some methods to build the software fault prediction model based on supervised learning which can help to predict the fault–proneness of a program modules when fault labels for modules are not present. One of the methods is use of classification techniques. Supervised techniques like classification may be used for fault prediction in software modules, more so in those cases where fault labels are not available. In this study, we propose a Genetic algorithm based software fault prediction approach for classification.