Research on Target Tracking Algorithm based on Improved Mean Shift and Kalman Filter

Bian Minjie,Honghao Gao 보안공학연구지원센터 2014 International Journal of Database Theory and Appli Vol.7 No.3

The Research of Data Mining Based on Application Data Pool

Minjie Bian,Jue Gao,JiePin Xu,Honghao Gao 보안공학연구지원센터 2014 International Journal of u- and e- Service, Scienc Vol.7 No.5

Today, people use various kinds of information technology applications to deal with applications in our daily life, which generates lots of information. However,most of the informationis just stored in many Distributed Heterogeneous Databases (DHDs) as log records, instead of being used abundantly and effectively. In this paper, we mainly discusses about how to use these data in useful ways by Data Mining (DM). Relative to thetraditional Data Mining based on Data Warehouse (WD),we propose a definition named Application Data Pool (ADP)replacing WD in this paper. And we design a KnowledgeDiscovery in Databases (KDD) model with ADP to use these data more efficiently. At last we use an application in Shanghai University ID Card designed with the ADP to prove the effectiveness and feasibility in KDD.

Research on Probabilistic Optimization to Dynamic Composition for Service Replacement

Honghao Gao,Minjie Bian,Yucong Duan,Yonghua Zhu 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.10

A growing number of enterprises have been moving their works to encapsulate system functions, business logics and processing modules into Web service because of its flexibility and low-cost. However, service-oriented software calls for constantly adjusting its architecture in order to respond to varying user requirements and instable runtime environments. One of the most challenging issues is how to effectively implement a reconfiguration to ensure the business-critical application is trustworthy. In this paper, it proposes a method to dynamic composition for service replacement, which focuses on the probabilistic optimization to service planning of candidate compositions when the service failure is occurred. First, the input and output data specification is defined to describe interface behaviors, and then the probabilistic solution graph is introduced to formalize replacement strategies. Second, corresponding algorithms are discussed for optimization selection purpose, which includes reliability calculation process and model modification process. The former computes the probability value of each service planning generated from probabilistic solution graph. The latter modifies probabilistic solution graph model to recommend Top-k solutions, pruning the service planning which does not satisfy the specified probability value. Third, the architecture of prototype is presented to demonstrate the feasibility of the proposed method. Our method provides a reference to guarantee the reliability of service process in E-commerce.

Research on Parallel KD-Tree Construction for Ray Tracing

Zhang Peicheng,Xu Huahu,Bian Minjie,Honghao 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.11

Many computer graphics rendering algorithms and techniques use ray tracing for generation of photo-realistic images, and kd-tree is the most popular acceleration data structure for ray tracing. In order to avoid the inefficient parallel performance of kd-tree construction based on surface area heuristic (SAH), an algorithm using Morton code and path compression was present in this paper. Instead of building a kd-tree layer-by-layer, the proposed approach can be performed in parallel from bottom of a conceptual perfect binary tree. Experimental results on GPU show that our work achieves a faster kd-tree construction procedure.

Fast Pedestrian Detection with Adaboost Algorithm Using GPU

Chong Chao Cai,Jue Gao,Bian Minjie,Peicheng Zhang,Honghao Gao 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.6

Pedestrian detection is one of the hot research problems in computer vision field. The Cascade AdaBoost System is a commonly used algorithm in this region. However, when the training datasets become larger, it is still a time consuming process to build one Adaboost classifier. In this paper we detail an implementation of the AdaBoost algorithm using the NVIDIA CUDA framework based on the haar features as feature vectors, and downscaling with integral image. The result shows that we can get nearly 6x from the standard code to with our CPU implementation to achieve a near real-time performance and ensure better classification results in misjudgment.

A Novel Approach to Task Scheduling using The PSO Algorithm based Probability Model in Cloud Computing

Li Ruizhi,Gao Jue,Gao Honghao,Bian Minjie,Xu Huahu 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.11

With the development of cloud computing technology, people not only want to pursue the shortest time to complete the tasks by using cloud computing, but also hope to take into the running costs of machines. Existing task scheduling algorithm in the cloud computing environment has been unable to meet people's needs. As an extension and generalization of the model checking theory, probability model checking is also used in many fields, such as random distributed algorithm and other areas. The task scheduling algorithm based on the particle swarm optimization algorithm combined with probability model is proposed in this paper. The algorithm defines the fitness functions of the time cost and the running cost. The fitness functions can improve the efficiency of the cloud computing platform. At the same time, the probability model can be used to analyze the running states of machines and the computing capability of the nodes in the cloud cluster. The probability, which is calculated by the probability model, provides the basis for changing particle swarm algorithm’s the inertia factor and the learning factor, so as to solve the drawback that the inertia factor and the learning factor solely depend on the fixed value.

Research on Improved Hadoop Distributed File System in Cloud Rendering

Ren Qin,Gao Jue,Gao Honghao,Bian Minjie,Xu Huahu,Feng Weibing 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.11

With the rapid development of cloud computing technology, it’s the cloud rendering that cloud computing is applied to render the job in CG (Computer Graphic) industry. The cloud rendering can handle a large number of rendering requests which are enormous pressure for back-end servers in system. Facing with massive data and computing resources, the bottleneck of original HDFS (Hadoop Distributed File System) based on cloud computing has become more and more prominent, such as the failure of single Namenode, scalability issues. Therefore, the paper proposed an improved HDFS which evolved a single Namenode into multi-Namenode. In HDFS, Metadata management is very important. So this paper presented a two-level Metadata distribution algorithm. The two-level algorithm was based on the principle that different distribution strategies were used to different categories of Metadata. The experiments verified that the improved HDFS effectively improved the performance of the system.

Research and Application of Collision Detection in Virtual Roam based on WebGL and HTML5

Li Ruizhi,Xu Huahu,Gao Honghao,Yan Yingmin,Bian Minjie,Xu Jiepin 보안공학연구지원센터 2015 International Journal of u- and e- Service, Scienc Vol.8 No.11

With the development of the Internet technology, people’s life and work are more and more dependent on the Internet. Remote rendering techniques permit streaming of high-quality 3D graphics to apply onto a wide range of smart devices, and recent years have also seen many solutions of Web3D applications. Web3D is a kind of technology, which can perform the 3D visualization on the Internet, and virtual roam can present information in a far more intuitive and interactive way to people. So, Web3D technology is the foundation of virtual roam technology. Today, Web3D technology and virtual roam technology has become the research focus of computer technology. This paper presents the basic concept and characteristics of Web3D, and designs a solution concerning the virtual roam by combining WebGL and HTML5. This solution has characteristics of good compatibility, GPU acceleration and free plug-ins. Meanwhile, this paper aims at researching collision detection in the virtual roam and presenting a fast collision detection and correction algorithm.