Abstract:

Software in the computer is significant in performing the important tasks in computer hardware and also plays a vital role in improving the efficiency of the daily assets of human individuals. The quality of the software is threatened due to various defects and it must be determined and resolved for the effective functioning of the system. In the Software development life cycle, the software defect prediction assists the system to enhance their quality and various researches are undertaken for the effective prediction of defects in software. In this research, the defects in the software are predicted using the deep CNN classifier by effectively optimizing the classifier using spiderhunt optimization. The effective communication and hunting characteristics of the spiderhunt are employed for tuning the classifier that boosts the classifier performance. The proposed spiderhunt optimization not only optimizes the classifier but also plays a significant role in the feature selection for the extraction of necessary features that helps in the defect prediction. The proposed spiderhunt optimization achieved the improvement in terms of accuracy, precision, recall and f-measure and is proved to be quite efficient compared to state of art methods

Description:

Deep CNN classifier, spiderhunt optimization, software defect prediction, threat, communication.