Lizhi Peng

TL;DR: This paper presents an automatic way of evolving hierarchical Takagi-Sugeno fuzzy systems (TS-FS) using probabilistic incremental program evolution (PIPE) with specific instructions and fine tuning of the if - then rule's parameters encoded in the structure using evolutionary programming (EP).

TL;DR: This study combines network traffic analysis with machine learning methods to identify malicious network behavior, and eventually to detect malicious apps, and proposes a machine learning based comparative benchmark prototype system, which provides users with substantial autonomy, such as multiple choices of the desired classifiers or traffic features.

TL;DR: Experimental results illustrate that the proposed DGC method is very efficient for data classification and feature selection and a novel feature selection algorithm is investigated based on the idea of DGC and weighted features.

TL;DR: A lightweight framework for Android malware identification that combines network traffic analysis with machine learning algorithm (C4.5) that is capable of identifying Android malware with high accuracy and performs better than other state-of-the-art approaches.

TL;DR: This study develops a specific DGC model namely Imbalanced DGC (IDGC) model for imbalanced problems, based on the amplified gravitation coefficient (AGC), which is a type of coefficient that contains class imbalance information, which can strengthen and weaken the gravitational field of the minority and majority classes.