Applied Mechanics and Materials Vols. 380-384

Abstract: Social tagging has been widely used in Web2.0 applications. An optimized tagging recommendation model is showed in this article which can be divided into four layers. They are respectively based on essential data, character analysis, semantic data mining and user advanced behavior analysis. By using this model, flexible tag recommendation services can be provided to fit different application circumstances.

Abstract: Aiming at QoS multi-objective optimisation,this paper presents an improved genetic algorithm,which has been applied to solving the routing optimisation problem. This algorithm meets the requirements of bandwidth,delay and cost on the basis of router mathematical model. Also,it sets the targets of resource consumption and equilibrium load distribution,which makes the resource consumption least and balances the load distribution,thus, the occurrence of network congestion is reduced. Simulation proves that it has the advantages to certain extent.

Abstract: Based on unconstrained optimization and genetic algorithm, this paper presents a constrained genetic algorithm (CGA) for learning Bayesian network structure. Firstly, an undirected graph is obtained by solving an unconstrained optimization problem. Then based on the undirected graph, the initial population is generated, and selection, crossover and mutation operators are used to learn Bayesian network structure. Since the space of generating the initial population is constituted by some candidate edges of the optimal Bayesian network, the initial population has good property. Compared with the methods which use genetic algorithm (GA) to learn Bayesian network structure directly, the proposed method is more efficiency.

Abstract: According to the traditional UMDH network modeling with the least square method to recognize parameters ,it's easy to fall into local minimum ,and with the result that the prediction effect is not ideal. This paper puts forward to combine the simulated annealing algorithm and genetic algorithm, and introduces the combined algorithm to the UMDH network which is used to identify some of its description type coefficient. In this paper ,it describes the simulated annealing genetic algorithm ,and constructs the UMDH network model based on this algorithm, and the model is applied to the simulation of debris flow prediction research ,forecast average relative error reached 3. 54%. The results show that the algorithm not only ensuring the global optimization but also preventing premature convergence, improve the UMDH network model of global and local searching optimal ability further.

Abstract: Researches on simulation are always heavily dependent on a kind of particular techniques or tools so that it is difficult to perform horizontal comparison and integration. Most of all, there is no formal description for the simulation objects, which leads to the lack of semantic support in the simulation. In order to solve these problems, it is required to apply ontology engineering to provide correctness verification of simulation and to prove the consistency of simulation project itself. A method based on ontology engineering is proposed. Based on the idea of how to apply the approach, a test is performed as to a specific simulation task in which the ontology-based method and purely experimental method are compared.

Abstract: In this paper a method is introduced to simulate the Complex system by ABMS . space system can be considered a complex system that is composed of many satellites ,which need a powerful and flexible method to study , MAS structure of space system is gived by analyzing its hiberarchy , by studying the navigation agent , a typical agent structure is gived . introduce the RepastHPC agent platform using MPI , orbit forecasting method is studying , Finally, we realize the MAS simulation and run it on parallel cluster .

Abstract: Spatiotemporal data are widely visible in everyday life. This paper proposes an algorithm to represent them in a granular wayinformation granules. Information granules can be regarded as a collection of conceptual landmarks using which people can view the data and describe them in a semantic way. The key objective of this paper is to introduce a new granular way of data analysis through their granulation. Several experiments are done with synthetic data and the results show a clear way how our algorithm performs.

Abstract: C⁴ISR system is the core and base for improving the fight ability of SoS based on information system. Modeling and Simulation (M&S) is an efficient method to study on the C⁴ISR system. In order to meet the requirement for higher simulation performances due to the complexity and incessant development of the C⁴ISR system, and support parallel modeling and simulation to research on the design, analysis, assessment and application of C⁴ISR system, a parallel modeling and simulation environment is designed based on high performance computer. The architecture of software and hardware, system constructure and main application pattern are described. Practices proved that the environment solved the problem of complex models and large computing for C⁴ISR simulation system, and could be used in similar complex simulation system.

Abstract: In intelligent video surveillance system, there exists the defect that the background is multimodal when extracting the background image, so the extracted foreground objects are not very pure with the method of background subtraction. In this paper, we put forward an algorithm which adopts adaptive threshold to update the background. Firstly, the common background model algorithms and their defect are analysed. Then we propose the strategy of updating background template based on adaptive threshold and then give the specific algorithm steps. Finally, the algorithm is simulated and the results are analyzed.

Abstract: When modeling background model by Gaussian mixture model, there exist the defects that parameters can not be updated adaptively. In this paper, we adopt mean-shift algorithm to overcome these defects. Firstly, this paper introduces the initialized parameters, such as variance, mean, and weights and others, when modeling and then the parameters are constantly adjusted in the subsequent calculations. Then the statistical background model based on probability density estimation is put forward and using mean-shift algorithm updates the parameters adaptively. At last, the algorithm of mixture Gaussian background modeling method based on mean-shift is implemented. The experimental results show that the algorithm can effectively update parameters adaptively and the obtained background model is better.