Software defect prediction using K‐PCA and various kernel‐based extreme learning machine: an empirical study

Abstract

Predicting defects during software testing reduces an enormous amount of testing effort and help to deliver a high‐quality software system. Owing to the skewed distribution of public datasets, software defect prediction (SDP) suffers from the class imbalance problem, which leads to unsatisfactory results. Overfitting is also one of the biggest challenges for SDP. In this study, the authors performed an empirical study of these two problems and investigated their probable solution. They have conducted 4840 experiments over five different classifiers using eight NASA projects and 14 PROMISE repository datasets. They suggested and investigated the varying kernel function of an extreme learning machine (ELM) along with kernel principal component analysis (K‐PCA) and found better results compared with other classical SDP models. They used the synthetic minority oversampling technique as a sampling method to address class imbalance problems and k‐fold cross‐validation to avoid the overfitting problem. They found ELM‐based SDP has a high receiver operating characteristic curve over 11 out of 22 datasets. The proposed model has higher precision and F‐score values over ten and nine, respectively, compared with other state‐of‐the‐art models. The Mathews correlation coefficient (MCC) of 17 datasets of the proposed model surpasses other classical models' MCC.

RETRACTED: PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

“…The receiver operating characteristic (ROC) curve ( 32) and the area under the curve (AUC) are introduced to provide a graphical plot and a quantitative value of measuring the proposed PSCNN model, respectively. ROC and AUC are obtained through the following two procedures: (i) ROC plot is firstly generated by charting the TP rate against the FP rate at different threshold degrees (33). (ii) AUC is then estimated by measuring the complete 2D area beneath the ROC curve from point (0, 0) to point (1, 1) (34).…”

Computer assisted diagnosis of bipolar disorder using invariant features

“…But kernel principal component analysis (kernel PCA) provides less computational cost. In the method, kernel PCA [16][17][18] is used for projecting feature vectors and it is performed on the extracted feature matrix. The following steps are involved in kernel PCA.…”

Cross-Project Defect Prediction Method based on Feature Distribution Alignment and Neighborhood Instance Selection

“…Predicting defects in a software project is very important to the software development process because the later errors in the software are discovered, the greater the cost of fixing the errors. The purpose of software defect prediction [6][7][8][9][10][11][12] is to help software developers find software defects in the early stages of development to allocate software testing resources reasonably to improve software reliability. The rapid development of machine learning technology allows software testers to build software defect prediction models based on existing data to focus on testing those classes or files that may have defects based on the prediction results [13].…”