Class imbalance has drawn much attention of researchers in software defect prediction. In practice, the performance of defect prediction models may be affected by the class imbalance problem. In this paper, we present an approach to evaluating the performance stability of defect prediction models on imbalanced datasets. First, random sampling is applied to convert the original imbalanced dataset into a set of new datasets with different levels of imbalance ratio. Second, typical prediction models are selected to make predictions on these new constructed datasets, and Coefficient of Variation (C•V) is used to evaluate the performance stability of different models. Finally, an empirical study is designed to evaluate the performance stability of six prediction models, which are widely used in software defect prediction. The results show that the performance of C4.5 is unstable on imbalanced datasets, and the performance of Naive Bayes and Random Forest are more stable than other models.
Software defect prediction has attracted much attention of researchers in software engineering. At present, feature selection approaches have been introduced into software defect prediction, which can improve the performance of traditional defect prediction (known as within-project defect prediction, WPDP) effectively. However, the studies on feature selection are not sufficient for cross-project defect prediction (CPDP). In this paper, we use the feature subset selection and feature ranking approaches to explore the effectiveness of feature selection for CPDP. An empirical study is conducted on NASA and PROMISE datasets. The results show that both the feature subset selection and feature ranking approaches can improve the performance of CPDP. Therefore, we should select the representative feature subset or set a reasonable proportion of selected features to improve the performance of CPDP in future studies. INDEX TERMS Software defect prediction, cross-project defect prediction, feature selection, feature ranking.
Carbon adsorbent materials that were prepared from sunflower straw by a combination of pre-treatment and low-temperature pyrolysis showed better adsorption compared with untreated carbon. Four different pretreatment agents (steam, alkali (KOH), phosphoric (H3PO4), and salt (ZnCl2)) were analyzed with respect to their effects on the maximum surface area and the micropore area. Samples were measured by thermogravimetric analysis (TGA), X-ray powder diffraction (XRD), scanning electron microscopy (SEM), surface area analysis, and pore size analysis. The surface area, pore volume, and N2-adsorption capacity of the samples were closely correlated with the pre-treating agent. A biochar with a maximum surface area of 877.6 m 2 /g and a micropore area of 792.8 m 2 /g was prepared with phosphoric acid (H3PO4) as the pre-treatment agent at a temperature of 400 °C. The main result of the one-stage pre-treatment procedure was the number of micropores. The two-stage, low-temperature pyrolysis procedure focused on the volume of the pores. Carbonized sunflower straw, with pretreated and lowtemperature pyrolysis procedures, was judged to be a highly effective and economic method to prepare carbon adsorbents.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.