@article{Ozdemir_Sogukpinar_2014, title={An Android Malware Detection Architecture based on Ensemble Learning}, volume={2}, url={https://journals.scholarpublishing.org/index.php/TMLAI/article/view/261}, DOI={10.14738/tmlai.23.261}, abstractNote={In the scope of anomaly based Android malware detection, different type of features has been used to represent applications and lots of algorithms have been applied to evaluate these features. Although researchers have reported accurate results, in order to improve accuracy, sensitivity and generalization, we suggest using an ensemble learning approach for Android malware detection. In this study, we propose to use an ensemble learning system whose base learners are built with different feature subsets which are extracted and processed with multiple methods, and selected with a proposed selective ensemble approach which is based on three criteria: Accuracy, sensitivity and diversity.}, number={3}, journal={Transactions on Engineering and Computing Sciences}, author={Ozdemir, Mehmet and Sogukpinar, Ibrahim}, year={2014}, month={Jun.}, pages={90–106} }