Junheng Huang

Learn More
Phishing website is becoming a major threat to the information security in Social Network. The attacks not only lessen the users' trust but also influence the benefit of the third party who develops the platform. In order to solve the time lag in phishing website passive detection, this paper proposes a solution to discover phishing website initiatively(More)
The traditional collaborative filtering recommendation algorithm can be divided into the user-based and the item-based two methods, which only uses the information in the rating matrix. Because of the limitation of the information capacity they used, it is difficult to further improve the accuracy of the recommendation, and cold start problem also affects(More)
In traditional collaborative filtering recommendation, the matrix sparsity and cold start restricted the accuracy of system. In this paper, we develop a way to enhance the recommendation effectiveness by merging neighborhood relationship and users keyword of social network information into collaborative filtering. We extend the calculation method of the TOP(More)
Wireless Sensor Network (WSN) is an important part of the Internet of Things, The design of routing strategies is very important as well in WSN just like in Ad hoc. The paper firstly describes the characteristics of WSN routing protocols; Secondly analyzes in details the AODV which is the typical on-demand routing protocol in Ad hoc, transplants it into WSN(More)
Biochemical reaction network simulation is the core task in the new virtual cell simulation technology, because it carries out a lot of complex biochemical reactions. A new general algorithm is proposed to simulate the biochemical reactions in virtual cell using multi-agent. The algorithm is based on a deterministic algorithm for biochemical reactions in(More)
—On the basis of the assumption that diseases with similar phenotypes are caused by functionally related genes, We describe a candidate gene prioritization method that is entirely based on mutual information of human protein–protein interactions and disease phenotypic similarities, and develop a tool named GENEDIG to calculate the mutual information(More)
Recently, object tracking is viewed as a foreground/background two-class classification problem. In this paper, we propose a non-parameter approach to model the observation model for tracking via graph, which is a semi-supervised approach. More specially, the topology structure of graph is carefully designed to reflect the properties of the sample's(More)