Imbalanced learning based on adaptive weighting and Gaussian function synthesizing with an application on Android malware detection

The existence of imbalanced classes can considerably degrade the performance of most standard learning algorithms. This paper presents a new imbalanced learning method called AWGSENN to address this problem on data level. In AWGSENN, each minority instance is firstly weighted based on the number of majority class neighbors and the distance of the minority instance to its neighbors. Then, a Gaussian distribution probability density function is designed to generate new instances nonlinearly. Finally, the edited nearest neighbor rule is used as a data cleaning technique to remove overlapping and noisy instances. The proposed method is evaluated in extensive experiments by comparing it with five over-sampling and two hybrid sampling methods on 37 data sets from the KEEL data repository. Empirical study results show that our approach can achieve significant performance improvement on G-mean and the area under curve metrics. Wilcoxon signed-rank test results show that our approach is superior to other resampling approaches. We apply the proposed method for Android malware detection, and the results further demonstrate the promising performance of our approach.