Applied Mechanics and Materials Vols. 44-47

Abstract: In this paper, we develop an algorithm to globally solve a kind of mathematical problem. Firstly, by utilizing equivalent problem and linear relaxation method, a linear relaxation programming of original problem is established. Secondly, by using branch and bound technique, a determined global optimization algorithm is proposed for solving equivalent problem. Finally, the convergence of the proposed algorithm is proven and numerical examples showed that the presented algorithm is feasible to solve the kind of mathematical problems.

Abstract: It’s important that the short-time traffic flow forecasting has good real-time performance and high accuracy. In order to satisfy this demand, weekly similarity is imported and an improved fractal forecast model is established. In order to improve forecast accuracy furthermore, one-rank local-region forecasting principle is referenced to determine parameters which influence weekly similarity degree. Finally, the improved fractal model based on variable dimension is employed to predict the traffic flow in Hangzhou city. The experiment result shows that the improved fractal method proposed here possesses high forecast accuracy.

Abstract: The RSVPWM (Random SVPWM) is one key type of technology in the motor control and other electronic power transformation applications because of many advantages. The detailed procedure to build the simulation model of RSVPWM is presented and discussed. The ports and parameters, the program flowchart and the method to realize the randomization are given and illustrated. The built model can simulate random frequency SVPWM, random zero-vector distribution SVPWM and random pulse position SVPWM. The simulation results verify the model.

Abstract: In this paper, we concentrate on how to automatic detect landmarks of a city leveraging the community-contributed collections of rich media on the Web, as landmark for a given city could provide helpful information for tourist guides. Our approach only need the user to provide the city name, and then submit it to Flickr website to obtain photos and related metadata. Next, these Flickr photos are clustered by simultaneously integrating multiple types of metadata which are related to Flickr photos. Finally, landmarks are mined from the photos clustering results. Experiments conducted on the photos in Flickr demonstrate the effectiveness of the proposed approach and our approach could enhance the performance of tourist guiding systems greatly.

Abstract: We present an approach to tag image automatically via visual topic detecting and initial annotations expanding. Visual topics are detected from corel5k dataset by probabilistic latent semantic analysis (PLSA) model. For an image which is to be tagged, PLSA is used to find visual topic of this image, and then construct initial annotations set. After initial annotations are generated, we use a weighted voting scheme and Flickr API to expand initial annotations. After the above two process, we combine initial annotations and expanded annotations together to construct final annotations. From experimental results, the conclusions can be draw that our PLSA based image tagging approach works effectively.

Abstract: The methods of pruning have great influence on the effect of the decision tree. By researching on the pruning method based on misclassification, introduced the conception of condition misclassification and improved the standard of pruning. Propose the conditional misclassification pruning method for decision tree optimization and apply it in C4.5 algorithm. The experiment result shows that the condition misclassification pruning can avoid over pruned problem and non-enough pruned problem to some extent and improve the accurate of classification.

Abstract: Considering the characteristics of fuzziness, gray and dynamic of the debt risks in highway project, build a method of grey fuzzy comprehensive evaluation. According to the characteristics of project on financing for development and operational, establish the corresponding debt risk subsets. It not only can evaluation the risk of different stages, also can comprehensive evaluation the risk of the whole project, so that the investors can according to the evaluation value of general risk and each stage to targeted for prevention and control.

Abstract: Degeneracy problem is an inevitable result of sequential importance re-sampling (SIR) particle filter, and a mass of degenerated particles will influence the tracking ability of particle filter seriously. As a result, SIR particle filter based predication algorithm can’t predict system faults accurately. Artificial immune algorithm is characterized by a global ability to search for optimum, so it is introduced into the particle filter, named artificial immune particle filter (AIPF). Particles are regarded as antibodies in AIPF and particles with large weight aberrance and are cloned, and then the better particles are selected for states evaluation. A fault predication algorithm based on AIPF is proposed to improve the predication accuracy, and simulation results have demonstrated the feasibility of the proposed algorithm.

Abstract: The 2-D dual-tree complex wavelet and fractal dimension of image texture is proposed to objective evaluation of seam pucker for the garment manufacturing. Because the complex 2-D dual-tree DWT also gives rise to wavelets in six distinct directions, extract feature of seam pucker is advantage over 2-D wavelet which only has four distinct directions. In terms of the theory of pattern recognition in an image process, Euclidean distance between seam pucker of sample clothes and standard template classified into five classes (AATCC method) on seam pucker is computed. Thus, automatic and objective class evaluation of seam pucker is realized, a practice example proves the method boosts the degree of accuracy of inspector than other methods.

Abstract: In the research of CSCL (Computer Supported Collaborative Learning), interaction behavior analysis is an important part. In order to effectively analyze the learning interaction and find ways to promote collarative learning, it is necessary to establish a classified framework on micro-level for interaction behavior. This paper proposed the concept of micro-interaction firstly, then in view of text-based interaction is still the most important form of interaction, establishment of classification framework for the micro-interaction lauguage behavior. This article also describes the determination of the classification framework and development process, and finally discusses the value of its in CSCL system through an example．