Concerning the problem that in complex and non-cooperative situations the number of matching feature pairs and the accuracy of feature matching results in video stitching can not meet the requirements of subsequent image stabilization and stitching at the same time, a method of constructing matching model to match features accurately after feature points being scored by grayscale tower was proposed. Firstly, the phenomenon that the similiar grayscales would merged together after grayscale compression was used to establish a grayscale tower to realize the scoring of feature points. Then, the feature points with high score were selected to establish the matching model based on position information. Finally, according to the positioning of the matching model, regional block matching was performed to avoid the influence of global feature point interference and large error noise matching, and the feature matching pair with the smallest error was selected as the final result of matching pair. In addition, in a motion video stream, regional feature extraction could be performed by using the information of previous and next frames to establish a mask, and the matching model could be selectively passed on to the next frame to save the computation time. The simulation results show that after using this matching model based on grayscale tower score, the feature matching accuracy is about 95% and the number of matching feature pairs of the same frame is nearly 10 times higher than that of the traditional method. The proposed method has good robustness to environment and illumination while guaranteeing the matching number and the matching accuracy without large error matching result.

Mobile application crowdsourcing testers are anonymous, non-contractual, which makes it difficult for task publishers to accurately evaluate the ability of crowdsourcing testers and quality of test results.To solve these problems, a new evaluation model of Analytic Hierarchy Process (AHP) for mobile application crowdsouring testers was proposed. The ability of crowdsourcing testers was evaluated comprehensively and hierarchically by using the multiple indexes, such as activity degree, test ability and integrity degree. The combination weight vector of each level index was calculated by constructing the judgment matrix and consistency test. Then, the proposed model was improved by introducing the requirement list and description list, which made testers and crowdsourcing tasks match better. The experimental results show that the proposed model can evaluate the ability of testers accurately, support the selection and recommendation of crowdsourcing testers based on the evaluation results, and improve the efficiency and quality of mobile application crowdsourcing testing.

Aiming at the problem of quality evaluation of color restoration image for digital protection of faded cultural relics, the objective quality evaluation methods were researched. Combined the computational advantage of Peak Signal-to-Noise Ratio (PSNR) and structure characteristic of human visual feature information entropy, a color image quality evaluation method was proposed based on information entropy of visual features. A quality evaluation function with weights and the corresponding evaluation algorithm process were established, and the weights were determined by normalization method. Then the function value for comparing the similarity between the color restoration image and the reference color image was calculated by using the evaluation algorithm process. The smaller the value was, the higher the similarity was, and the better the corresponding color restoration image quality was, which could be used for the objective judgement of color restoration method. The quality evaluation parameters of four different performance restoration methods were compared. The experimental results show that, the evaluation results are consistent with the subjective perception of human eyes, and the proposed method is effective.

In view of the bending properties of cloth, an approximate model of nonlinear bending was proposed based on the analysis of the fabric characteristics and internal structure of cloth. Firstly, the parameters of bending properties were obtained through the measurement of bending properties of real cloth. Then, the bending model based on mean curvature was put forward to calculate the bending force. Secondly, the surface mean curvature and Gauss curvature were used to segment the triangular mesh model of cloth in the dynamic simulation. Finally, the bending force was updated according to the change of the mean curvature. In the comparison experiments with the Volino's bending model, the key frame speed of the proposed model increased by an average of 2.7% in the process of bending and 4.1% in the process of lifting arms without affecting the quality of cloth simulation. The experimental results show that the proposed model is simple and accurate, and it can fully show the details of clothing folds in a natural way.

In order to enhance the defensive ability and prediction ability of mobile network,a method for constructing mobile botnet based on a URL Shortening Services Flux (USSes-Flux) and Google Cloud Messaging for Android (GCM) was proposed. The mobile botnet model was designed with hybrid topology of central structure and peer-to-peer (P2P), USSes-Flux algorithm was presented, which increased robustness and stealthiness of Command and Control (C&C) channel. The control model was discussed. The states change of different bot, command design and propagation algorithm were also analyzed. In the test environment, the relationship between probability of short URL invalidness and number of required short URL was discussed. The static analysis, dynamic analysis and power testing of the mobile botnet and the samples of different C&C channel were carried out. The results show that the proposed mobile botnet is more stealthy, robust and low-cost.

Aiming at the problems of the path planning algorithm, such as slow convergence and low efficiency, a multi-Agent path planning algorithm based on hierarchical reinforcement learning and artificial potential field was proposed. Firstly, the multi-Agent operating environment was regarded as an artificial potential field, the potential energy of every point, which represented the maximal rewards obtained according to the optimal strategy, was determined by the priori knowledge. Then, the update process of strategy was limited to smaller local space or lower dimension of high-level space to enhance the performance of learning algorithm by using model learning without environment and partial update of hierarchical reinforcement learning. Finally, aiming at the problem of taxi, the simulation experiment of the proposed algorithm was done in grid environment. To close to the real environment and increase the portability of the algorithm, the proposed algorithm was verified in three-dimensional simulation environment. The experimental results show that the convergence speed of the algorithm is fast, and the convergence procedure is stable.

In this paper, aiming at the priority selection of the Gaussian kernel parameter (β) in the Kernel Principal Component Analysis (KPCA), a kernel parameter discriminant method was proposed for the KPCA. It calculated the kernel window widths in the classes and between two classes for the training samples.The kernel parameter was determined with the discriminant method for the kernel window widths. The determined kernel matrix based on the discriminant selected kernel parameter could exactly describe the structure characteristics of the training space. In the end, it used Principal Component Analysis (PCA) to the decomposition for the feature space, and obtained the principal component to realize dimensionality reduction and feature extraction. The method of discriminant kernel window width chose smaller window width in the dense regions of classification, and larger window width in the sparse ones. The simulation of the numerical process and Tennessee Eastman Process (TEP) using the Discriminated Kernel Principle Component Analysis (Dis-KPCA) method, by comparing with KPCA and PCA, show that Dis-KPCA method is effective to the sample data dimension reduction and separates three classes of data by 100%,therefore, the proposed method has higher precision of dimension reduction.

Most existing algorithms for data streams mining utilize the true label of testing data to detect concept drift and adjust current model according to requirements. It is impractical in real-world applications as manual labeling of instances which arrive continuously at a high speed requires a lot of human and material resources. Therefore, a concept drift detection method with limited amount of labeled data was proposed. The proposed method used the model clusters generated by the fast KNNModel algorithm to classify instances. It was able to detect concept drift on whether the number of instances which were not covered by any model clusters on the current block increased remarkably at a certain significance level than that of the prior block. Once concept drift happened, the domain experts were asked to label a few instances which were not covered by the model clusters and these representative instances were used to update the current model. The experimental results show that, compared with the traditional classification algorithms, the proposed method not only adapts to the situation of concept drift, but also acquires approximate or better classification accuracy.

Current urban traffic noise mapping systems are not ideal for big scale project distributed computing in dynamic network. This paper proposed a noise mapping distributed computation method based on loosely-coupled services and the mechanism of Service Object Oriented Architecture (SOOA), investigated the generation approach of noise propagation calculation service, and introduced the deployment and management of services in the proposed system. At last, a demonstration indicated that the distributed computation approach considerably reduced the overhead of calculation and supplied flexible system architecture at the same time. The experimental results show that the imbalance of parallel subtasks will affect the parallel efficiency. Under normal circumstances, parallel efficiency can reach over 85%.

The algorithms for mining data streams have to make fast response and adapt to the concept drift at the premise of light demands on memory resources. This paper proposed an ensemble classification algorithm for high speed data stream. After dividing a given data stream into several data blocks, it computed the central point and subspace for every class on each block which were integrated as the classification model. Meanwhile, it made use of statistics to detect concept drift. The experimental results show that the proposed method not only classifies the data stream fast and adapt to the concept drift with higher speed, but also has a better classification performance.

Stream data clustering algorithm was improved in terms of cluster quality and efficiency. This paper adopted a new method to improve cluster quality and efficiency. Firstly, the technology of the time-based sliding window was applied. Secondly, the structure of improved micro-cluster was created to save the summary. Finally, a new strategy was designed to regularly delete expired micro-clusters and outlier micro-clusters. Compared with traditional clustering algorithms of landmark-based model, the proposed method is of better efficiency, less memory overhead and fast data processing capabilities.