Computational Sciences and Optimization 

Abstract: Scheduling is one of the core steps to efficientlyexploit the capabilities of heterogeneous distributedcomputing systems and is an NP-complete problem.Therefore using meta-heuristic algorithms is asuitable approach in order to cope with its difficulty.In meta-heuristic algorithms, generating individualsin the initial step has an important effect on theconvergence behavior of the algorithm and finalsolutions. Using some heuristics for generating one ormore near-optimal individuals in the initial step canimprove the final solutions obtained by meta-heuristicalgorithms. Different criteria can be used forevaluating the efficiency of scheduling algorithms, themost important of which are makespan and flowtime.In this paper we propose an efficient heuristic methodand then we will compare with five popular heuristicsfor minimizing makespan and flowtime inheterogeneous distributed computing systems.

Abstract: Forest fire is a usual disaster in real life, causing huge live, property and ecology losses. A risk assessment model to identify, classify and map forest fire risk areas is presented in this paper. This model considers three parts, i.e. hazards identification, vulnerability analysis, and emergency response capacity analysis. The first part concentrates on several influence factors in forest fires, including the land use, topography and meteorology where the forest situate. The second part is made up of population density and value of forest resources. The forest fire response capacity including forest fire-brigade, watch-tower and helicopter water source is the third part. Through GIS spatial analytical procedure, the forest fire risk ranging from high to low is derived, according to its sensitivity to fire or fire-inducing capability. Spatial analyst is used to combine some single influence factors in risk maps to display the total fire risk map. The weight to each factor is determined by Grey Relativity Analysis (GRA). This model is illustrated with a case study of forest fire risk of area in China. It is suggested that risk mapping is helpful for the forest fire management to minimize forest fire hazard.

Abstract: In this study, a novel modular-type Support Vector Machine (SVM) is presented to simulate rainfall prediction. First of all, a bagging sampling technique is used to generate different training sets. Secondly, different kernel function of SVM with different parameters, i.e., base models, are then trained to formulate different regression based on the different training sets. Thirdly, the Partial Least Square (PLS) technology is used to select choose the appropriate number of SVR combination members. Finally, a $ u$-SVM can be produced by learning from all base models. The technique will be implemented to forecast monthly rainfall in the Guangxi, China. Empirical results show that the prediction by using the SVM combination model is generally better than those obtained using other models presented in this study in terms of the same evaluation measurements. Our findings reveal that the nonlinear ensemble model proposed here can be used as an alternative forecasting tool for a Meteorological application in achieving greater forecasting accuracy and improving prediction quality further.

Abstract: To analyze the resilience of transportation networks, it is proposed to use a quantificational resilience evaluation approach. First, we represent transportation networks by an undirected graph with the nodes as cities and edges as traffic roads. Because the survival ability of transportation of a pair of cities depends on the number of independent paths between them, the resilience of a city node can be evaluated by the weighted average number of reliable independent paths with all other city nodes in the networks. The network resilience can then be calculated by the weighted sum of all node resilience. Based on the recommended approaches, the resilience of a transportation network is evaluated and analyzed. Several interesting conclusions are drawn from the computational results.