Weihong Han

TL;DR: The real medical diagnostic data test shows that the proposed distribution-sensitive oversampling algorithm improves the accuracy rate of classification learning algorithm compared with the existing sampling algorithms, especially for the accuracy rates and recall rate of minority classes.

TL;DR: Wang et al. as discussed by the authors proposed a classification method for attribution organizations with APT malware in IoT using machine learning, which aims to mark the real attacking organization entities to better identify APT attack activity and protect the security of IoT.

TL;DR: Wang et al. as discussed by the authors proposed a community detection algorithm based on a deep sparse autoencoder, which combines the path weight matrix with the weighted adjacent paths of the node to obtain the similarity matrix, which can not only reflect the similarity relationship among connected nodes in the network topology but also the similarity relationships among nodes and second-order neighbors.

TL;DR: Wang et al. as discussed by the authors proposed a method for detecting malicious mining code in the cloud platforms, which constructs a detection model by fusing the Bagging and Boosting algorithms, by randomly extracting samples and letting models vote together to decide, the variance of model detection can be reduced obviously.

TL;DR: Different from traditional machine learning, the method introduces the ensemble models to solve the malware classification problem and the t-SNE algorithm to visualize the feature data and then determines the number of malware families.