Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bin Cheng has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Personalized Privacy Protection-Preserving Collaborative Filtering Algorithm for Recommendation Systems

    by Bin Cheng, Ping Chen, Xin Zhang, Keyu Fang, Xiaoli Qin, Wei Liu

    With the rapid development of ubiquitous data collection and data analysis, data privacy in a recommended system is facing more and more challenges. Differential privacy technology can provide strict privacy protection while reducing the risk of privacy leakage, but it also introduces unwanted noise, which makes the performance of the recommender system worsen. Among different users, the degree of their sensitivity to privacy is usually different. Thus, through considering the impact of users’ personalized requirements, the collaborative filtering algorithm can be designed to reduce the amount of unwanted noise. Taking the above assertions into account, we propose a collaborative filtering algorithm based on personalized privacy protection. First, it locally classifies ratings by privacy sensitivity on the user side, then utilizes the random flip mechanism to protect the privacy-sensitive ratings. Then, after the server catches the perturbed rating data, we reconstruct the joint item-item distribution through the Bayesian estimation method. Experimental results show that our proposed algorithm can significantly improve the recommendation performance of recommendation systems while protecting users’ privacy.


  • Open Access

    A self-adaptive deployment model of UAV cluster for emergency communication network

    by Ying Fang, Bin Cheng, KunPeng Kang, Hai Tan

    Equipped with micro wireless sensor nodes, a unmanned aerial vehicle) cluster can form an emergency communication network, which can have several applications such as environmental monitoring, disaster relief, military operations and so on. However, situations where there is excessive aggregation and small amount of dispersion of the unmanned aerial vehicle cluster may occur when the network is formed. To mitigate these, a solution based on a 3D virtual force driven by self-adaptive deployment (named as 3DVFSD) is proposed. As a result, the three virtual forces of central gravity, uniform force, and boundary constraint force are combined to act on each node of the communication network. By coordinating the distance between the nodes, especially the threshold of the distance between the boundary node and the boundary, the centralized nodes can be relatively dispersed. Meanwhile, the nodes can be prevented from being too scattered by constraining the distance from the boundary node to the end. The simulation results show that the 3DVFSD algorithm is superior to the traditional virtual force-driven deployment strategy in terms of convergence speed, coverage, and uniformity.


  • Dynamic Performance of Vehicle–Guideway Bridge Systems for Low–Medium-Speed Maglev Trains Under Earthquakes

    by Fenghua Huang, Bin Cheng, Nianguan Teng

    This paper developed a numerical model for predicting the seismic responses of vehicle–guideway bridge systems for low–medium-speed (LMS) maglev trains. Each vehicle was characterized as a multi-rigid-body with 50 degree of freedoms (DOFs), and the guideway bridge was modeled by the finite element method. The actively controlled electromagnetic forces were considered in simulating the vehicle–guideway interaction relationship. Subsequently, the equations of motion for the vehicle–guideway coupled system under earthquake were, respectively, established in relative and absolute coordinate systems to quantify the effect of structural pseudo-static components, so that the seismic effect can be taken into account. Case study was then conducted to thoroughly discuss the seismic responses of the vehicle–guideway coupled system in both time and frequency domains. Furthermore, parametric study was carried out to determine the effect of key parameters (i.e. vehicle speed, stiffness of guideway) on the system’s responses. The results show that the conventional seismic analysis method relative motion method (RMM) (ignoring the structural pseudo-static component) will considerably underestimate the seismic responses of the coupled system, especially of the vehicle. It is suggested that the formulation be established in the absolute coordinate system (i.e. using direct solution method, DSM) for more actual prediction. The frequency responses indicate that the vibrations of vehicle–guideway coupled system under earthquake relate significantly to the natural frequencies of vehicle and bridge, while the same is not true for the vehicle-induced excitation.