Linguistics

Engineering

Philosophy

Extreme learning machine

Exploit

Support vector machine

Computer security

Systems engineering

Weighting

Data mining

Computer science

Radiology

Software

Kernel (algebra)

Kernel principal component analysis

Task (project management)

Software bug

Mathematics

Kernel method

Feature selection

Feature (linguistics)

Artificial intelligence

Combinatorics

Meta learning (computer science)

Medicine

Programming language

Artificial neural network

Class (philosophy)

Machine learning

Information and Software Technology

Software defect prediction strives to detect defect-prone software modules by mining the historical data. Effective prediction enables reasonable testing resource allocation, which eventually leads to a more reliable software. The complex structures and the imbalanced class distribution in software defect data make it challenging to obtain suitable data features and learn an effective defect prediction model. In this paper, we propose a method to address these two challenges. We propose a defect prediction framework called KPWE that combines two techniques, i.e., Kernel Principal Component Analysis (KPCA) and Weighted Extreme Learning Machine (WELM). Our framework consists of two major stages. In the first stage, KPWE aims to extract representative data features. It leverages the KPCA technique to project the original data into a latent feature space by nonlinear mapping. In the second stage, KPWE aims to alleviate the class imbalance. It exploits the WELM technique to learn an effective defect prediction model with a weighting-based scheme. We have conducted extensive experiments on 34 projects from the PROMISE dataset and 10 projects from the NASA dataset. The experimental results show that KPWE achieves promising performance compared with 41 baseline methods, including seven basic classifiers with KPCA, five variants of KPWE, eight representative feature selection methods with WELM, 21 imbalanced learning methods. In this paper, we propose KPWE, a new software defect prediction framework that considers the feature extraction and class imbalance issues. The empirical study on 44 software projects indicate that KPWE is superior to the baseline methods in most cases.

Software defect prediction based on kernel PCA and weighted extreme learning machine