Applied Mechanics and Materials Vols. 530-531

Abstract: In order to improve the speed of compressed sensing image reconstruction algorithm, a rapid gradient projection algorithm for image reconstruction is proposed. In traditional Gradient Projection algorithm, the pursuit direction is alternating, in rapid gradient projection algorithm, we use the Newton's method to calculate the gradient descent direction, thus the constraints conditions of gradient projection is satisfied. And the target function is updated in each iteration computing. The effect of approximation matrix to target function is reduced. The iteration computing times is reduced, because the algorithm works in accurate search direction. Experiment results show that, compared with the GPSR algorithm, the RGPSR algorithm improves the signals reconstruction accuracy, improves PSNR of reconstruction signals, and exhibits higher robustness under different noise intensities.

Abstract: This paper proposed knowledge content tag recommendation algorithm in cloud computing Environment, and applied to police information knowledge. The algorithm analyzed user behavior history of operation and considered the similarity knowledge of the entries on the tag of police information, marked weight of tag in predicting when a user rating. On this basis, the police information implementations specific recommendations based on the specific user application knowledge. Meanwhile, combined the tag of system entry contents correlation with user correlation analysis, and solved the problems of system sparse matrix. Finally, the results demonstrated the effectiveness and superiority of recommendation algorithm.

Abstract: The expected number of crossings of Buffon's needle problem is linear if the distance d between the lines of the ruled paper is less than or equal to the length l of the needle. With the help of Dynamic Geometry Super Sketchpad software, two vivid simulations of the linearity of Buffon's problem are given, that is, the expected number E(l ) satisfies E(x+y) = E(x) + E(y) and E(rx) = rE(x).

Abstract: According to the characteristics of steel strip, This paper propose the strip defect detection algorithm which is based on visual attention mechanism. First, extract the input image color, brightness and orientation characteristics and form simple feature map; secondly, prognosis on the features, get defective attention region by threshold segmentation to color characteristics of colored defect image. The wavelet decomposition to colorless defect image of brightness and direction features will form the multi-feature subgraph; then construct feature difference molecular graph through the feature decomposition map around central difference operations, and the characteristic difference of molecular graph is formed by the fusion of feature saliency map; finally, defect targets by using local threshold method and region growing segmentation. The experimental results show that this method can rapidly and accurately detect the defects of the strip image, at the same time it can improve the efficiency of detection.

Abstract: Due to limited energy wireless sensor networks, in order to extend the life cycle of WSN, the need for wireless sensor network routing protocol has been improved, based on the original model of hierarchical routing protocol LEACH algorithm, combined with efficient use of energy, new determine the clustering structure methods. The paper used in each sub-clan structures BP neural network algorithm for nodes preclude the data set is processed to reduce the amount of data transmitted to the sink node, reduce communication energy consumption to prolong the network lifetime goal.

Abstract: This paper developed a turntable positioning error measurement system based on machine vision. The system consists of image acquisition devices, the image acquisition card, computer and data processing software and other components. Among them, the image acquisition devices consisted of two digital CCD cameras and two microscope objectives. The image acquisition devices capture images of fixture fixed on the turntable in horizontal and vertical direction. Then, the collected images are processed by adopting the filtering method, binarization method, edge detection method, calibration method and other steps. The high-accuracy measure of turntables positioning errors is realized, and the error histogram is drawn. Theoretical analysis and experimental results show that the method is correct and feasible.

Abstract: According to the Life Cycle Cost theory, the paper sets up the Life Cycle Cost model of the transformer that covers initial investment cost, operation cost, failure cost and retirement cost, and puts forward a new concept of economic life, determining the economic life of transformer through comparing the annual net profit of the old transformer with the largest annual net profit of the new transformer. As the transformer serves for a long time and the running environment is complicated, parameters, which are required for in evaluation, are both random and fuzzy. Then, introduce random and fuzzy theory that can handle the uncertainties at the same time to assess the economic life of the transformer. This model not only can get the expectancy of economic life of the transformer, but also can get the economic life interval under different confidence level and the economic life interval whose chance measure is the biggest under the same economic life span. Finally, take the assessed transformer as a example to verify the rationality and validity of the model.

Abstract: The ranking results of semantic label are the important reference index on the point whether the image sematic automatic tagging results are right. To the problem of the disorder of the current image sematic labels, this paper suggests a method of the image semantic label automatic sorting which is based on the base classifier weighted voting. This method based on the content in the significant image regional, it weighted votes on every part of the semantic label, with the help of the base classifier. In this way, it tests the relevance of each semantic label and the image that makes the right order of the image label.

Abstract: Local binary pattern (LBP) spectrum is a powerful feature for texture image, which is invariant to local illumination changes. Pulse coupled neural network (PCNN) is a biologically inspired algorithm, which is well suited for image processing and can generate rotation, scale, translation invariant image signature. This paper proposed an image retrieval tool named LBP-PCNN which combined the advantages of LBP and PCNN. First, images are mapped into local structural domain with rotation invariant LBP. Then, the simplified PCNN was adapted to extract the image signature in structural domain. At last, texture image retrieval was completed by measuring the signature similarity of input sample texture image and texture database. Experimental results on Brodatz texture gallery show that LBP-PCNN overbears LBP and PCNN in texture image retrieval and has potential applications.

Abstract: Identifying the most important node is a research hotspot in complex networks. For different types of network there are different methods to cope with. In this paper, we use five methods: degree method, betweenness method, node contraction method, node importance evaluation matrix method, K-shell decomposition method to identify the key node and compare the effects through SIR propagation model. In the simulation experiments, we use three artificial networks: random network (ER), small-world network (NW) and scale-free network (BA). The experimental results show that the nodes identified by node importance evaluation matrix method and K-shell method are more important. Besides, in BA the infection velocity is faster and the infection scale is larger than in ER and NW.