Applied Mechanics and Materials Vols. 333-335

Abstract: Identification of definition for digital image is an important aspect of digital imaging system. To improve the efficiency of the present image definition identification methods with a high accuracy, an algorithm based on the compound model of Lifting Wavelet Transform and Naive Bayes classifier is proposed. Firstly, the two-dimensional Lifting Wavelet Transform is used to extract the image feature, and 28 statistical values obtained from 7 wavelet components by statistical process are treated as image eigenvalues for the follow-up identification. Then Naive Bayes classifier is used to achieve the identification, which has a high computational efficiency and competitive accuracy, and the classifier applied to the experiments of this paper is from OpenCV. The experiment consists of two phases. In phase one, the compound model is trained by 200 images from the training set. Similarly, in phase two, the model is tested by 100 images from the testing set. The results show that the algorithm based on the compound model is very effective, and obtains a high recognition rate.

Abstract: Based on the TM remote sensing data of the Huadian city in 1991 and 2011 and based on the DEM data,using the normalized difference vegetation index (NDVI) change classification method,to Extraction the elevation,slope,slope direction data and the vegetation index data of the study area.Then using the spatial analysis function of GIS software to overlay the two different period NDVI data and analysis the NDVI change of area and spatial. Using the same method to overlay and analysis the relationship of NDVI data and elevation,slope,slope direction.Research shows that the variation of NDVI in the study area has relationship with the topographic factors change.

Abstract: Shadows will exist in Many images which will affect many computer vision problems processing, such as image segmentation, image matching. This paper reviewed the recent research and methods about the image shadow detection and removal, and introduced each methods advantages and disadvantages in the shadow of treatment, so that two or more than two kinds of methods can we combine to the image shadow processing and obtain satisfactory results which is also the image shadow detection and eliminate development trend currently.

Abstract: Less of edge and texture information existed in traditional visual attention model in target detection due to extract only the color, brightness, directional characteristics, as well as direct sum fusion rule ignoring the difference in each characteristic. A improved model is proposed by introduced the edge, texture and the weights in fusion rules in visual computing model. First of all, DOG is employed in extracting the edge information on the basis of obtained brightness feature with multi-scale pyramid using the ITTI visual computing model; the second, the non-linear classification is processing in the six parameters of the mean and standard deviation of the gray contrast, relativity and entropy based on the GLCM; finally, the fusion rule of global enhancement is employed for combination of multi-feature saliency maps. The comparison experimental results on variegated natural scene display, relative to the ITTI calculation model, there is more effective with the application of the model in this paper, the interested area and the order to shift the focus are more in line with the human visual perception, the ability of target detection is strengthening in variegated natural scene. Further shows that the proposed edge and texture features introduced in the primary visual features to be effective, the introduction of each feature significant weighting factor is reasonable in the feature map integration phase.

Abstract: The digital map is an important and indispensable resource to the national strategic security and social economic development. At the present, needs to focus on resolving the utility question of digital vector map copyright protection technology, furthermore, the information hiding technology is the basic content of the research areas of the digital vector maps copyright protection. It is proposed a digital copyright protection scheme, based on the principle of unauthorized cannot resume, copyright embedding operation selection partly transform for the map content. Processing area determined by the spatial clustering analysis method that is based on grid density.

Abstract: Recently, global change research has reflected the great challenge of massive distributed remote sensing image processing. Faced with such challenge, massive pixel-level remote sensing image processing reconstruction based on Hadoop is proposed, which focuses on the support of data format and the design of paralle computing. In order to support a variety of formats of remote sensing images and simplify the process of data parse, the processing flow transforms the remote sensing image into image information in binary format, as well as metadata information in xml format. Compared with converting to text format, there are two advantages for this conversion, reducing the amount of data after converted and remaining metadata information. To avoid MapReduce parallel computing performance interference caused by the algorithmic complexity, remote sensing image point operation is selected to do research about the design of parallel computing. The experimental results show that the proposed method has good scalability in the distributed Hadoop environment, along with the changing of the data quantity.

Abstract: With the disadvantages of volatility, intermittent and randomness of wind power, a research on constructing a fairly accurate prediction model is imperative to improve the quality of power system. Considering the optimization ability of heuristic algorithm and the regression ability of support vector machine, a HA-SVM model is constructed.Case study shows that, compared with other heuristic algorithms, the search efficiency and speed of differential evolution are good, and the prediction accuracy of the model is high.

Abstract: Aim to the weak intelligence and humanity of current electric nursing-bed control modes, the recommended movement control mode is proposed, which is based on the existing manual, timing and speech control pattern. First, on the basis of accumulating some control data, the Affinity Propagation algorithm (AP algorithm) is employed to cluster in order to acquire the clustering centers, which reflect the prefer movement and corresponding value at special time of the special user. Then, according to the mechanical and electric constraints, some rules are established to adjust the clustering centers. And the nursing-bed movement sequence is obtained, which is logical. Finally, the rationality of the recommended movement sequence is analyzed according to the distribution characteristic of the dataset. The movement sequence that passes the rationality analysis will be recommended to the user and automatically saved as the recommended pattern. The experimental results show that the recommended movement sequence can basically reflect the users habits, which is more intelligent and human than other control modes.

Abstract: Aiming at the problem that most of weighted association rules algorithm have not the anti-monotonicity, this paper presents a weighted support-confidence framework which supports anti-monotonicity. On this basis, Boolean weighted association rules algorithm and weighted fuzzy association rules algorithm are presented, which use pruning strategy of Apriori algorithm so as to improve the efficiency of frequent itemsets generated. Experimental results show that both algorithms have good performance.

Abstract: Conflict resolution problem (CRP) plays a crucial role in the guarantee of safety. This paper formulates CRP as a multi-agent path planning problem which aims to find optimal paths for aircrafts. An algorithm named CCDG is proposed to tackle it based on cooperative coevolutionary (CC) with a dynamic grouping strategy for aircraft. CCDG makes aircraft divided into several equal sub-groups according to the dynamic grouping strategy. Each sub-group can adopt an evolutionary algorithm (EA) to optimize the aircrafts paths fully distributed and in parallel. Optimal solution is obtained through cooperation and coordination with all sub-populations. Empirical studies using extremely scenario adopted by previous research show that CCDG outperformed the existing approach (the fast GA), and the popular path planner that each aircraft uses an EA. Moreover, CCDG succeed to improve the airspace safety and reduce cost for CR.