Applied Mechanics and Materials Vols. 701-702

Abstract: Word similarity computing is a crucial question in information processing technology. In this paper, an integrated word similarity computing method is proposed by analyzed morpheme's similarity, word order's similarity and word length's similarity, and parameters of the method are decided by experiments. The experiments show that this method has high efficiency.

Abstract: In this paper, a novel method for face recognition, called two-dimensional weighted and locality preserved discriminant analysis (2D-WLPDA) is proposed. The new algorithm is developed based on three techniques: (1) locality preserved embedding, by embedding nearest-neighbor graphs which characterize the within-class compactness of the same class samples, 2D-WLPDA discovers the submanifold of images space; (2) image based projection which can avoids the small sample problem and improves the computation efficiency;(3) weighting contributions of individual class pairs which alleviates the overlap of neighboring classes in Fisher criterion for a k-class problem with k>2. We experimentally compare 2D-WLPDA to other feature extraction methods, such as 2D-LDA, 2D-PCA and 2D-DLPP, 2D-WLPDA has better recognition performance.

Abstract: The sound absorption performance of MPA (micro perforated absorber) mainly depends on its structural parameters. Reasonable parameter combination will get a high absorption coefficient. In this paper numerical simulation was used to study sound absorption performance. By this means, the influence of the different parameters on the sound absorption performance are discovered. To verify the result of numerical simulation, MPA samples are fabricated using optimized parameters by laser machining method. The sound absorption performances of these samples are tested and the experimental result is consistent with that of numerical simulation.

Abstract: This article takes the industrial robot workpiece sorting issue as a background, introduces an embedded machine vision system based on DM642. The system realizes the image preprocessing, feature extraction, image recognition and other work in DSP, and transmits detection results to robot controller through network interface. Experimental results show that the system can effectively solve the problem of sorting regular geometric workpiece, and can meet the requirements of real-time and accuracy in industrial applications.

Abstract: The high range resolution profile samples are numerous and sparse. But less radar target recognition algorithms based on high range resolution profiles (HRRP) employed the sparseness of HRRP samples. A new radar target recognition algorithm using a fast sparse decomposition method is presented here. This algorithm was to be carried out in three major steps. First, the Gabor redundant dictionary was partitioned according to its atom characteristics to decrease the atoms storage. Then, the matching pursuit algorithm was improved by the genetic algorithm and the fast cross-correlations calculation to accelerate training samples decomposition and generate the taxonomic dictionaries. Finally, the reconstruction errors of testing samples were used to recognize different radar targets. The simulations show that this method can resist noise disturbs and its recognition rate is high.

Abstract: Low-dimensional chaotic encryption has a good operational efficiency but there is a problem of security flaws, therefore this paper proposes a composite chaos encryption system based on double mapping. Double mapping with mutual disturbance were used to generate the key sequence, and respectively with odd and even number of image pixels to realize the image encryption. The simulation results show that, the effect is very good; Correlation and so on security analysis shows that meet the requirements of the security; System overall evaluation results show that the proposed algorithm has better security and ease of implementation, can effectively resist brute force attack, statistic attack etc.

Abstract: To improve the accuracy and reliability of modulation recognition at low signal to noise ratio (SNR) and few knowledge of signal parameter, the novel method based on the cyclic spectral feature and support vector machine(SVM) is presented. In the process of novel algorithms, the cyclic spectral analysis is used to realize the feature extract of the modulated signals, and the Eigenface method is used to reduce the amount of spectral coherence feature. Then, a new scheme of classification based on support vector machine is presented to classify the modulation signal. The experiment shows that the modulation classification accuracy of presented method is significantly improved at low SNR environment.

Abstract: InSAR phase unwrapping is one of the key technologies in precise differential interferometry measurement. However, when the noise is more, wrapped phase easily make the unwrapping result’s errors more. To solve this problem, phase error is compensated, and extended Kalman filter gain is limited within a certain range, error is suppressed in a relatively small area. Finally, extended Kalman filter smooth reduce the errors’ spread. Using interference data of ESA ERS-1 satellite to do experiments, it show that this method is superior to least squares method, quality guided method and original Kalman filter method in unwrapping precision and quality, it has higher stability.

Abstract: Image Classification is an important means of image processing, Traditional research of image classification usually based on following assumptions: aiming for the overall classification accuracy, sample of different category has the same importance in data set and all the misclassification brings same cost. Unfortunately, class imbalance and cost sensitive are ubiquitous in classification in real world process, sample size of specific category in data set may much more than others and misclassification cost is sharp distinction between different categories. High dimension of eigenvector caused by diversity content of images and the big complexity gap between distinguish different categories of images are common problems when dealing with image Classification, therefore, one single machine learning algorithms is not sufficient when dealing with complex image classification contains the above characteristics. To cure the above problems, a layered cascade image classifying method based on cost-sensitive and class-imbalance was proposed, a set of cascading learning was build, and the inner patterns of images of specific category was learned in different stages, also, the cost function was introduced, thus, the method can effectively respond to the cost-sensitive and class-imbalance problem of image classifying. Moreover, the structure of this method is flexible as the layer of cascading and the algorithm in every stage can be readjusted based on business requirements of image classifying. The result of application in sensitive image classifying for smart grid indicates that this image classifying based on cost-sensitive layered cascade learning obtains better image classification performance than the existing methods.

Abstract: When the client thread try to process massive amounts of unstructured data such as video, images, text, the traditional architecture is difficult to deal with. The main task of data processing is how to process real-time data efficiently based on requirement of applications. In this paper, dynamic loading method is adopted based on JMX, and taking management component Mbean as core component to realize a synchronous, real-time processing to data. This only committed data is required for submitting your application for subscription, then wait for system reply patiently. Make connections to the primary database, then, begin working through the data, so as to realize rapid real-time processing. Experiments show that on high through put of data access, and more practical then deferred data synchronization.