Applied Mechanics and Materials Vols. 536-537

Abstract: In this paper, a sparsity based model is proposed for feature selection in kernel minimum squared error (KMSE). By imposing a sparsity shrinkage term, we formulate the procedure of subset selection as an optimization problem. With the chosen small portion of training examples, the computational burden of feature extraction is largely alleviated. Experimental results conducted on several benchmark datasets indicate the effectivity and efficiency of our method.

Abstract: With the emerging of RFID technology and increasing pressure on maintenance, higher request is posed on the maintenance action. This paper introduces a combined intelligent system to complete the maintenance task. SVM and SVR model has been trained to classify machine fault types and predict the degradation. The proposed system can carry out maintenance action with the staff position information form RFID tags and the machine condition information. Genetic algorithm will be used to search the best maintenance sequence, then, the combined information will help make most efficient maintenance decision.

Abstract: Determining how to select path efficiently in complex transportation networks was one of the main problems in-car navigation systems. For the drawbacks of slow convergence and easy to fall into local optimal solution of basic ant colony algorithm in solving the optimal path problem, a method of improving the expect-heuristic function is proposed in this paper, which enhances search direction and improves the convergence rate. Meanwhile, with the introduction of a new strategy to update the pheromone on ant colony system, the contradiction that convergence speed brings stagnation is balanced. The results show that the improved ant colony algorithm is easier to get the optimal solution compared with basic ant colony algorithm, and the convergence speed is faster, having a good navigation effect.

Abstract: Taking an immune operator added to the framework of the genetic algorithm, individuals vaccinated to further enhance the survival ability of the individual, the immune genetic algorithm as a set of immune mechanisms and evolutionary mechanisms in one of the new evolutionary algorithm is applied to reverse genome rearrangement problem is a new attempt, the genetic algorithm can be avoided premature shortcomings, while the immune genetic algorithm parallelization can improve convergence speed.

Abstract: Due to the features of being fluctuant, intermittent, and stochastic of wind power, interconnection of large capacity wind farms with the power grid will bring about impact on the safety and stability of power systems. Based on the real-time wind power data, wind power prediction model using Elman neural network is proposed. At the same time in order to overcome the disadvantages of the Elman neural network for easily fall into local minimum and slow convergence speed, this paper put forward using the GA algorithm to optimize the weight and threshold of Elman neural network. Through the analysis of the measured data of one wind farm, shows that the forecasting method can improve the accuracy of the wind power prediction, so it has great practical value.

Abstract: The most existing constrained optimization evolutionary algorithms (COEAs) for solving constrained optimization problems (COPs) only focus on combining a single EA with a single constraint-handling technique (CHT). As a result, the search ability of these algorithms could be limited. Motivated by these observations, we propose an ensemble method which combines different style of EA and CHT from the EA knowledge-base and the CHT knowledge-base, respectively. The proposed method uses two EAs and two CHTs. It randomly combines them to generate novel offspring individuals during each generation. Simulations and comparisons based on four benchmark COPs and engineering optimization problem demonstrate the effectiveness of the proposed approach.

Abstract: According to the characteristics of the optimization theory and arrival flights.Established static and dynamic model which take the aircraft delay cost as target. The limit of maximum allowable delay time variable are introduced to reduce the delay cost, take into account fairness of flights landing at the same time. The solution of the model is filtered beam search algorithm (FBS).

Abstract: To extend the flexibility of data integrity verification method,adapted to the different verification environment, proposed an improved solution that can support multi-granularity.It organizes files into three kinds of granularity such as data blocks,data sub-blocks and basic-blocks,basic-block realize data gathered to form data sub-block.Sign in the data sub-block,using signature of the sub-block to generate signature of block. Improvement program can achieve the verification of data blocks and sub-blocks. Validation of data block can reduce the data traffic in the validation process,two particle combination can improve the overall efficiency.In the proposed layered merkel hash tree is put forward,the dynamic operation can be supported by the sub-block or the block.Securitycommunication performance analysis show that the improvement program is effective and has a better practicability

Abstract: With the rapid development of information technology, the growth of heterogeneous Web data and the requirements of access to the Web of data also is growing. In view of this, a method of heterogeneous data integration based on SOA(Service-Oriented Architecture) is proposed. This method combines the technology of middleware and SOA design, using XML and Web services technologies, presents a framework of heterogeneous data integration based on SOA, and introduces the architecture of SOA data integration middleware. Experimental results show that this method reduces the coupling of heterogeneous data integration system effectively, and improves the scalability of the system.

Abstract: Change-point detection is the problem of finding abrupt changes in time-series. However, the meaningful changes are usually difficult to identify from the original massive traffics, due to high dimension and strong periodicity. In this paper, we propose a novel change-point detection approach, which simultaneously detects change points from all dimensions of the traffics with three steps. We first reduce the dimensions by the classical Principal Component Analysis (PCA), then we apply an extended time-series segmentation method to detect the nontrivial change times, finally we identify the responsible applications for the changes by F-test. We demonstrate through experiments on datasets collected from four distributed systems with 44 applications that the proposed approach can effectively detect the nontrivial change points from the multivariate and periodical traffics. Our approach is more appropriate for mining the nontrivial changes in traffic data comparing with other clustering methods, such as center-based Kmeans and density-based DBSCAN.