Luo Zhong

Wuhan University of Technology, Wu-han-shih, Hubei, China

Are you Luo Zhong?

Claim your profile

Publications (48)2.27 Total impact

  • Luo Zhong, Hui Yu, Jingling Yuan, Lin Li
    International Conference on Information Engineering; 03/2014
  • Source
    Luo Zhong, Bo Zhu, Li Yang, Huazhu Song
    [Show abstract] [Hide abstract]
    ABSTRACT: Grid aims at sharing all kinds of geographically distributed and heterogeneous resources. The key to resource organization is how to accomplish the resource discovery efficiently. In this paper, a Layered Resource Discovery Model (LRDM) was proposed firstly according to different resource type in grid. Then the components of LRDM were analyzed and designed in detail with resource discovery module in Globus Tookit 4, mainly including resource description, resource information storage, resource information organization, resource request processing, and resource selection. Finally, the model was implemented and proved to have the characteristics high discovery efficiency and scalability because of combining the advantages of both centralized and distributed mechanisms.
    Procedia Environmental Sciences. 09/2013; 11:77–84.
  • [Show abstract] [Hide abstract]
    ABSTRACT: A kind of tunnel environment monitoring system based on SCADA (Supervisory Control and Data Acquisition) and Qt integrated development environment was designed and realized in this paper. The data center module, interface module and data processing module were integrated. The observer pattern was applied to this system including custom widget technology, XML technology, and database technology and so on. A lot of configuration parameters were selected for the extension of this system. This system was proved having a good expansibility, reusability, flexibility and maintainability in the practical engineering.
    Proceedings of the 2012 Second International Conference on Electric Technology and Civil Engineering; 05/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: The current city tunnel monitoring system is commonly composed by several independent subsystems, and the monitoring data has feature of multi source and heterogeneous. As a result, it is difficult to analyze this data and realize the linked control between subsystems. A novel linked control scheme based on XML was proposed in this paper. The unified record of each subsystem data, the storage of control strategies and the implement of control commands exist with the form of XML file in this scheme. The realization of linked control scheme has greatly improved the practicability and intelligence of city tunnel monitoring system.
    Proceedings of the 2012 Second International Conference on Electric Technology and Civil Engineering; 05/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: The city tunnel monitoring platform was studied based on the city tunnel monitoring system in order to share information and resources in this paper. The characteristics of the data which are collected from different city tunnel monitoring systems were analyzed. The XML(eXtensive Makeup Language) based multisource description method was proposed to uniformly express various data in the monitoring platform. Then, the common architecture of city tunnel monitoring platform was discussed. The city tunnel monitoring platform aimed at solving the problems that the monitoring data of the city tunnel is isolated and hardly to share, enhancing the monitoring level of city tunnel.
    01/2012;
  • [Show abstract] [Hide abstract]
    ABSTRACT: More and more attention is paid for energy consumption aware and power control for data center with the emergency of energy crisis. The use of virtualization technology makes it possible for dynamic configuration of data center resources. The N:1 mapping visualization technology is employed to integrate many physical machines into an virtual resource pool to control resources centralized, and then reinforcement learning is applied to resource management and decision making for an uncertain task flow data center. Finally, an automatic resource control algorithm with energy consumption aware is proposed. This algorithm is implemented in the Cloud Sim platform to improve the energy consumption of the data center. The experimental results show that our algorithm can reduce about 40% of the energy consumption of the non-power-aware data center and reduce 1.7% of that of the greedy scheduling algorithm in data center.
    Intelligent Computation Technology and Automation, International Conference on. 01/2012;
  • Luo Zhong, Li Yang, Bo Zhu, Huazhu Song
    [Show abstract] [Hide abstract]
    ABSTRACT: In the grid environment, resources are distributed, heterogeneous, dynamical and autonomous. Resource discovery takes a part of a bridge between resource requester and resource provider. Its primary function is to devise effective location strategy and find the optimal resource combination to meet the demands of users. In this paper, on the premise of the Layered Resource Discovery Model (LRDM), a layered resource location strategy was proposed, mainly including two parts: local location and global location. At last, the location strategy was simulated by using OPNET in order to demonstrate the feasibility and effectiveness of the proposed strategy.
    Advances in Computer Science, Environment, Ecoinformatics, and Education - International Conference, CSEE 2011, Wuhan, China, August 21-22, 2011. Proceedings, Part V; 01/2011
  • Luo Zhong, Li Yang, Bo Zhu, Huazhu Song
    [Show abstract] [Hide abstract]
    ABSTRACT: Combined the technology of service-oriented with learning resource grid, this paper proposed its solution of demonstration system. Firstly, the architecture of learning demonstration system was given, and the services in the system were discussed. Then the learning resource grid demonstration system was designed from the data supporting layer and visualization layer in detail. Finally, the implemented system not only showed the service invocation process visually, but also let learners or users get a deeper understanding about grid.
    01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: With the development of 3G mobile technology, the mobile learning (M-Learning) platform research becomes the demand of the Times. Based on cloud service for convenient hardware resource allocation and ontology for good individual learning, the system architecture of mobile learning platform is proposed and some key techniques are studied in this paper. Finally, a kind of M-learning platform framework is designed and realized.
    01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper mainly discusses the simulation aspect of online payment in e-commerce teaching by means of the cloud and virtualization technologies. The various transaction entities in online payment are simulated so that students and teachers access the simulation programs for virtual trading entity through the online or wireless means under cloud architecture. Students are able to fully experience the actual functionality of the entities and roles. The open-source cloud platform Eucalyptus is employed to configure and manage the Virtual Machines(VMs) for various trading entities to achieve persistence mechanisms of trading entities and Citrix ICA/Microsoft RDP/VNC protocol are also used to remotely access and control the VMs of various trading entities.
    01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper discusses the characteristics and key techniques of 3G mobile learning based on cloud services. Our research mainly focuses on mobile learning mode including active mode, passive mode and hybrid mode. And personalized learning method and resource integration approach are applied and analyzed. At last, we propose to employ cloud computing to mobile learning and build basic framework and simulation application for 3G mobile learning based on cloud services.
    E-Product E-Service and E-Entertainment (ICEEE), 2010 International Conference on; 12/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Grid job scheduling is an NP complete problem, concerning the large-scale resource and job scheduling, and the adoptive and efficient job scheduling algorithm is required. Genetic algorithms show good capability to solve the problem of the small-scale, but with the increase in the number of jobs and resources, genetic algorithm is hard to convergence or slow convergence. This paper proposed a Memetic Algorithm which designed crossover operators and mutation operator with hill-climbing algorithm and Tabu search algorithm for processing grid job scheduling. Hill Climbing scheduling usually can enhance processor utilization, and Tabu search algorithm have shorter completion times for job scheduling in computing grid. And then the algorithms’ search ability and convergence speed were compared. The simulation results shown that the proposed algorithm can effectively solve the grid job scheduling problem.
    Information and Automation - International Symposium, ISIA 2010, Guangzhou, China, November 10-11, 2010. Revised Selected Papers; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Granular Computing (GrC) is a new concept and novel approach to solve the complex problems and provide a method for massive data-mining in the field of artificial intelligence. This paper applied granular space theory to hierarchical clustering method to generate a more efficient two-stage hierarchical clustering algorithm based on granular theory. This Method can reduce the time and memory complexities significantly and make validation very efficient and accurate. so it is very meaningful to the Hierarchical clustering algorithm.
    01/2010;
  • Jingling Yuan, Hongfu Du, Luo Zhong
    [Show abstract] [Hide abstract]
    ABSTRACT: In order to solve complex knowledge reduction, the relative conditional partition granularity and new knowledge significance, quantitative representations for the relative classification ability of decision attributes are defined in this paper. And new knowledge partition granularity and new relative conditional partition granularity are constructed to transform inconsistent decision tables into "consistent" decision table. On this basis, common knowledge reduction algorithm is proposed for both consistent and inconsistent decision tables. The algorithm can effectively obtain the optimal or a sub-optimal relative reduction of decision table and its time complexity is relatively low as O(|U|2|U|) through theoretical analysis. Finally, we show that this algorithm is effective through an example.
    2010 IEEE International Conference on Granular Computing, GrC 2010, San Jose, California, USA, 14-16 August 2010; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: A stock information system, based on the technologies of semantic Web and Web services, is designed with Web interface layer and semantic Web layer. The former includes URI layer and XML/XML scheme layer, and the latter includes ontology layer and agent layer. The related ontology of this system is given including two kinds of main ontology-user ontology and stock information data ontology, and agent ontology. Agent ontology defines the interactive way between user ontology and stock information ontology, and is regarded as the functional carrier for user ontology and stock information ontology. The construction of ontology and interaction with agent in the system are achieved in the semantic Web layer. In Web interface layer, applying with the technology of service-oriented model, 3 critical components, connector component, user component and stock information component, are designed to complete the whole interactions among the system, different resources and the users. The construction methods of above 3 components are proposed in detail.
    01/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: The trend toward multi-/many- core processors will result in sophisticated large-scale architecture substrates that exhibit increasingly complex and heterogeneous behavior. Existing methods lack the ability to accurately and informatively forecast the complex behavior of large and distributed architecture substrates across the design space. Grey neural network is an innovative intelligent computing approach that combines grey system model and neural network. Grey neural network makes full use of the similarities and complementarity between grey system model and neural network to overcome the disadvantage of individual method. In this paper, we propose to use grey neural network to predict 2D space parameters produced by wavelet analysis,which can efficiently reason the characteristics of large and sophisticated multi-core oriented architectures during the design space exploration stage with less samples rather than using detailed cycle-level simulations. Experimental results show that the models achieve high accuracy while maintaining low complexity and computation overhead.
    Advances in Neural Networks - ISNN 2009, 6th International Symposium on Neural Networks, ISNN 2009, Wuhan, China, May 26-29, 2009, Proceedings, Part I; 01/2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: Grey model and support vector machine are fit for prediction in the small size of data, their advantages and disadvantages are probed in this paper at first. And then, the combined model is proposed, which combines grey model and support vector machine with optimal weights. The weights are obtained and optimized by minimizing the sum of squared residuals standard. Some experiments compared with grey model and support vector machine are done, and the experimental results show that the combined model proposed are not only more effective and reliable, but also can further improve the precision prediction.
    01/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Efficient application assignment algorithm is important for high performance and low power consumption in NoC architecture. In this paper, we apply novel algorithm based on GA (genetic algorithm) and maximal free matrix constraint, which aim at using confliction avoidance and minimization between router communications in order to provide less network contentions during several running applications and get global optimization in a given NoC platform (16 �? 16 cores). After applying our GA based congestion-aware placement algorithm, we observe dramatic reduction of congestion and improvement of performance compared to random selection results.
    01/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: An improved Greedy based global optimized Placement algorithm was proposed in this paper. Probability controlling was applied to avoid local minimization of traditional Greedy algorithm. Some new technique such as Marker bit method, dynamical selection and weight matrix were introduced to improve efficiency of this algorithm. From the experiments and comparison with Simulated Annealing algorithm, this novel algorithm shows better stability and accuracy.
    The Sixth International Symposium on Neural Networks, ISNN 2009, Wuhan, China, May 26-29, 2009, Proceedings, Part IV; 01/2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: The elementary theories and methods of data mining technology is introduced, and specifically applied the data mining technology to the Uprising Square Tunnel traffic flow in the city of Wuhan. Using the clustering analysis tools provided by SQL SERVER 2000, we first carry on the clean to the primary data, and then set up a data mining model, finally carry on the analysis to the result to obtain some traffic characteristics of the tunnel. This information not only helps the tunnel administrative personnel to manage the tunnel more effectively, but also facilitate driving personnel's going on a journey.
    First International Workshop on Database Technology and Applications, DBTA 2009, Wuhan, Hubei, China, April 25-26, 2009, Proceedings; 01/2009