A Comparative Analysis of SVM and ELM Classification on Software Reliability Prediction Model

Abstract

By creating an effective prediction model, software defect prediction seeks to predict potential flaws in new software modules in advance. However, unnecessary and duplicated features can degrade the model’s performance. Furthermore, past research has primarily used standard machine learning techniques for fault prediction, and the accuracy of the predictions has not been satisfactory. Extreme learning machines (ELM) and support vector machines (SVM) have been demonstrated to be viable in a variety of fields, although their usage in software dependability prediction is still uncommon. We present an SVM and ELM-based algorithm for software reliability prediction in this research, and we investigate factors that influence prediction accuracy. These worries incorporate, first, whether all previous disappointment information ought to be utilized and second, which type of disappointment information is more fitting for expectation precision. In this article, we also examine the accuracy and time of SVM and ELM-based software dependability prediction models. Then, after the comparison, we receive experimental results that demonstrate that the ELM-based reliability prediction model may achieve higher prediction accuracy with other parameters, such as specificity, recall, precision, and F1-measure. In this article, we also propose a model for how feature selection utilization with ELM and SVM. For testing, we used NASA Metrics datasets. Further, in both technologies, we are implementing feature selection techniques to get the best result in our experiment. Due to the imbalance in our dataset, we initially applied the resampling method before implementing feature selection techniques to obtain the highest accuracy.