Applied Mechanics and Materials Vols. 713-715

Abstract: This paper proposes a novel method to deal with the target tracking. Specifically, the information of observation model, appearance model, exclusion model, dynamic model, trajectory persistence model and trajectory regulation model are first used to construct objective tracking functions; then, the gradient descent method is adopted to achieve an approximate minimum of the constructed objective functions, and to obtain the status of tracking targets; finally, continuous energy minimization based intelligent extrapolation method is utilized to obtain the final continuous and smooth trajectories. Experimental results on PETS 2009/2010 benchmark video database demonstrate the effectiveness and efficiency of the proposed scheme.

Abstract: The bus scheduling algorithm is researched and the algorithm is improved, the traditional bus scheduling algorithm has not fully considered the time-sharing distribution of passengers, the shift scheduling is not reasonable, resulted in the waste of resources, and the passenger satisfaction rate is low. An improved bus scheduling algorithm is proposed based on time-sharing passenger flow distribution and statistical prediction. According to the past period of time, the statistics record data are collected, and the passenger flow of each period and each line of the station are calculated. The required number of buses of each period time is determined, the optimal solution of energy saving buses scheduling result is obtained. The experimental results show that, the new method can consider the passenger flow distribution of each time, and it can greatly improve the full-load ratio of bus, the bus scheduling optimal scheme is obtained, it has good application value in practice.

Abstract: As we all known, artificial neural network can be used in the process of environmental quality assessment. To improve the accuracy and science of assessment, a method of environmental quality assessment is presented in this paper, which is based on spline weight function (SWF) neural networks. The weigh functions of the neural network are composed of rational spline functions with cubic numerator and linear denominator (3/1 rational SWF). The simulation results show that, compared with the conventional BP neural networks, this method can get very high precision and accuracy. This case demonstrates that SWF neural networks can offer a very prospective tool for environmental quality assessment.

Abstract: We present a novel and powerful parallel algorithm, PMFI, for mining all the maximal frequent itemsets from a big database. PMFI utilizes novel technologies to make the I/O overhead down drastically. The key principle is to utilize prefix-based equivalence classes to decompose the search space. It distributes the work among the processors by equivalence class weights. It re-represents the database with vertical format, so the frequency counting can be done by simple tid-list intersection operations. It bases a novel serial algorithm MaxMining which utilizes multiple-level backtrack pruning strategy, so that each processor can count the maximal frequent itemsets independently by selectively duplicating the pieces of database. These techniques eliminate the need for synchronization. The dynamic load balance schema is applied in PMFI, it would be hopeful to achieve better performance.

Abstract: In order to describe the generalization ability, this paper discusses the error analysis of neural network with multiply neurons using rational spline weight functions. We use the cubic numerator polynomial and linear denominator polynomial as the rational splines for weight functions. We derive the error formula for approximation, the results can be used to algorithms for training neural networks.

Abstract: According to the problem of New Year woodblock pictures damaged area in complicated cases and low efficiency of inpainting, fast inpainting algorithm based on combination of texture distribution analysis and anisotropic diffusion technique is proposed. To digital image of New Year woodblock pictures by using this algorithm to repair has similar effects with the traditional algorithm, but the operation time is far lower than traditional methods. Experiments show that this algorithm not only reduce the numerical computational complexity of the model and inpainting effect is good.

Abstract: We formulate an age structured SEIRS model with general screen function and contact rate. A condition is obtained, and under which the endemic equilibrium is locally stable. By constructing suitable Lyapunov function, the global stability of the endemic equilibrium is discussed.

Abstract: Existing regulatory and regulated methods do not contain recommendations on the appointment of the aerodynamic coefficients for the complex shape of tall buildings, however, for such buildings wind loads can be decisive. In this paper, the problem of the calculated characteristics giving is solved by numerical simulation, the estimated pressure indicates average components of the aerodynamic forces and moments are calculated, localization of peak pressure values are defined.

Abstract: According to the low efficiency of vegetable leaf image data mining problems, proposed an improved algorithm based on Apriori algorithm to get greatly related groups. Using rough intensive set algorithm and further processing, excavated every attribute correlation of disease by reasonable divided attribute interval. conclusion shows that the most associated with the suffering degree of size and color, grayscale average.

Abstract: The first minimum spanning tree of length constraint problem (MSTLCP) is put forward, which can not be solved by traditional algorithms. In order to solve MSTLCP, improved genetic algorithm is put forward based on the idea of global and feasible searching. In the improved genetic algorithm, chromosome is generated to use binary-encoding, and more reasonable fitness function of improved genetic algorithm is designed according to the characteristics of spanning tree and its cotree; in order to ensure the feasibility of chromosome, more succinct check function is introduced to three kinds of genetic operations of improved genetic algorithm (generation of initial population, parental crossover operation and mutation operation); three kinds of methods are used to expand searching scope of algorithm and to ensure optimality of solution, which are as follows: the strategy of preserving superior individuals is adopted, mutation operation is improved in order to enhance the randomness of the operation, crossover rate and mutation rate are further optimized. The validity and correctness of improved genetic algorithm solving MSTLCP are explained by a simulate experiment where improved genetic algorithm is implemented using C programming language. And experimental results are analyzed: selection of population size and iteration times determines the efficiency and precision of the simulate experiment.