@Article{cmc.2020.010117,
AUTHOR = {Nana Zhang, Kun Zhu, Shi Ying, Xu Wang},
TITLE = {KAEA: A Novel Three-Stage Ensemble Model for Software Defect Prediction},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {64},
YEAR = {2020},
NUMBER = {1},
PAGES = {471--499},
URL = {http://www.techscience.com/cmc/v64n1/39153},
ISSN = {1546-2226},
ABSTRACT = {Software defect prediction is a research hotspot in the field of software 
engineering. However, due to the limitations of current machine learning algorithms, we 
can’t achieve good effect for defect prediction by only using machine learning algorithms. 
In previous studies, some researchers used extreme learning machine (ELM) to conduct 
defect prediction. However, the initial weights and biases of the ELM are determined 
randomly, which reduces the prediction performance of ELM. Motivated by the idea of 
search based software engineering, we propose a novel software defect prediction model 
named KAEA based on kernel principal component analysis (KPCA), adaptive genetic 
algorithm, extreme learning machine and Adaboost algorithm, which has three main 
advantages: (1) KPCA can extract optimal representative features by leveraging a nonlinear 
mapping function; (2) We leverage adaptive genetic algorithm to optimize the initial 
weights and biases of ELM, so as to improve the generalization ability and prediction 
capacity of ELM; (3) We use the Adaboost algorithm to integrate multiple ELM basic 
predictors optimized by adaptive genetic algorithm into a strong predictor, which can 
further improve the effect of defect prediction. To effectively evaluate the performance of 
KAEA, we use eleven datasets from large open source projects, and compare the KAEA 
with four machine learning basic classifiers, ELM and its three variants. The experimental 
results show that KAEA is superior to these baseline models in most cases.},
DOI = {10.32604/cmc.2020.010117}
}