Deep learning has superior performance in defect detection， however， due to the low defect probability， the detection process of defect-free images occupies most of the calculation time， which seriously limits the overall effective detection speed. In order to solve the above problem， a section steel surface defect detection algorithm based on cascade network named SDNet （Select and Detect Network） was proposed. The proposed algorithm was divided into two stages： the pre-inspection stage and the precise detection stage. In the pre-inspection stage， the lightweight ResNet pre-inspection network based on Depthwise Separable Convolution （DSC） and multi-scale parallel convolution was used to determine whether there were defects in the surface image of the section steel. In the precise detection stage， the YOLOv3 was used as the baseline network to accurately classify and locate the defects in the image. In addition， the improved Atrous Spatial Pyramid Pooling （ASPP） module and dual attention module were introduced in the backbone feature extraction network and prediction branches to improve the network detection performance. Experimental results show that the detection speed and the accuracy of SDNet on 1 024 pixel×1 024 pixel images reach 120.63 frames per second and 92.1% respectively. Compared to the original YOLOv3 algorithm， the proposed algorithm has the detection speed of about 3.7 times and the detection precision improved by 10.4 percentage points. The proposed algorithm can be applied to the rapid detection of section steel surface defects.

The heterogeneous multi-core platform provides flexibility for system design by integrating different types of processing cores, so that applications can dynamically select different types of processing cores according to their requirements and realize efficient operation of applications. With the development of semiconductor technology, the number of integrated cores on a single chip has increased, making the modern multi-core processors have a higher power density, and this will cause the chip temperature to rise, which will eventually cause a certain negative impact on the system performance. To make the performance advantages of heterogeneous multi-core processing system fully utilized, a dynamic mapping method was proposed to maximize the performance of heterogeneous multi-core systems under the premise of satisfying temperature safe power. In this method, two heterogeneous indices of heterogeneous multi-core systems including core type and thermal susceptibility were considered to determine the mapping scheme:the first heterogeneous index is the core type. Different types of processing cores have different characteristics, so they are suitable for processing different applications. The second heterogeneous index is thermal susceptibility. Different processing core positions on the chip have different thermal susceptibility. The processing cores closer to the center receive more heat transfer from other processing cores, so that they have higher temperature. For the above, a neural network performance predictor was created to match threads to processing core types, and the Thermal Safe Power (TSP) model was used to map the matched threads to specific locations on the chip. Experimental results show that the proposed method achieves about 53% increase of the average number of instructions executed by the program in each clock cycle-Instruction Per Cycle (IPC) under the premise of ensuring thermal safety constraints compared with the common Round Robin Scheduler (RRS).

Fitness action recognition is the core of the intelligent fitness system. In order to improve the accuracy and speed of fitness action recognition algorithm, and reduce the influence of the global displacement of fitness actions on the recognition results, a fitness action recognition method based on human skeleton feature encoding was proposed which included three steps:firstly, the simplified human skeleton model was constructed, and the information of skeleton model's joint point coordinates was extracted through the human pose estimation technology; secondly, the action feature region was extracted by using the human central projection method in order to eliminate the influence of the global displacement on action recognition; finally, the feature region was encoded as the feature vector and input to a multi-classifier to realize the action recognition, at the same time the length of the feature vector was optimized for improving the recognition rate and speed. Experiment results showed that the proposed method achieved the recognition rate of 97.24% on the self-built fitness dataset with 28 types of fitness actions, which verified the effectiveness of this method to recognize different types of fitness actions; on the public KTH and Weizmann datasets, the recognition rates of the proposed method were 91.67% and 90% respectively, higher than those of other similar methods.

Concerning the problems of large scale change and small sample dataset in rail tread block defects, a rail tread block defects detection method based on improved Faster Region-based Convolutional Neural Network (Faster R-CNN) was proposed. Firstly, based on the basic network structure of ResNet-101, a multi-scale Feature Pyramid Network (FPN) was constructed to achieve the fusion of deep and shallow feature information in order to improve the detection accuracy of small-scale defects. Secondly, the Generalized Intersection over Union (GIoU) loss was used to solve the problem of insensitivity to the position of the predicted border caused by regression loss SmoothL1 in Faster R-CNN. Finally, a method of Region Proposal Network by Guided Anchoring (GA-RPN) was proposed to solve the problem of the imbalance of positive and negative samples in the training of the detection network due to the large redundancy of anchor points generated by Region Proposal Network (RPN). During the training process, the RSSDs dataset was expanded based on image preprocessing methods such as flipping, cropping and adding noise to solve the problem of insufficient training samples of rail tread block defects. Experimental results show that the mean Average Precision (mAP) of the rail tread block defects detection based on the proposed improved method can reach 82.466%, which is increased by 13.201 percentage points compared with Faster R-CNN, so that the rail tread block defects can be detected accurately by the proposed method.

Due to the popularity of smart mobile terminals, sensitive information such as personal location privacy, check-in data privacy and trajectory privacy in the collected spatio-temporal data are easy to be leaked. In the current researches, protection technologies are proposed for the above privacy leakages respectively, and there is not a personalized spatio-temporal data privacy protection method to prevent the above privacy leakages for users. Therefore, a personalized privacy protection model for spatio-temporal data named ( p, q, ε)-anonymity and a Personalized Privacy Protection for Spatio-Temporal Data (PPP _ST) algorithm based on this model were proposed to protect the users' privacy data with personalized settings (location privacy, check-in data privacy and trajectory privacy). The heuristic rules were designed to generalize the spatio-temporal data to ensure the availability of the published data and realize the high availability of spatio-temporal data. In the comparison experiments, the data availability rate of PPP _ST algorithm is about 4.66% and 15.45% higher than those of Information Data Used through K-anonymity (IDU-K) and Personalized Clique Cloak (PCC) algorithms on average respectively. At the same time, the generalized location search technology was designed to improve the execution efficiency of the algorithm. Experiments and analysis were conducted based on real spatio-temporal data. Experimental results show that PPP _ST algorithm can effectively protect the privacy of personalized spatio-temporal data.

The existing biomedical named entity recognition methods do not use the syntactic information in the corpus, resulting in low precision. To solve this problem, a biomedical named entity recognition model with graph network based on syntactic dependency parsing was proposed. Firstly, the Convolutional Nerual Network (CNN) was used to generate character vectors which were concatenated with word vectors, then they were sent to Bidirectional Long Short-Term Memory (BiLSTM) network for training. Secondly, syntactic dependency parsing to the corpus was conducted with a sentence as a unit, and the adjacency matrix was constructed. Finally, the output of BiLSTM and the adjacency matrix constructed by syntactic dependency parsing were sent to Graph Convolutional Network (GCN) for training, and the graph attention mechanism was introduced to optimize the feature weights of adjacency nodes to obtain the model output. On JNLPBA dataset and NCBI-disease dataset, the proposed model reached F1 score of 76.91% and 87.80% respectively, which were 2.62 and 1.66 percentage points higher than those of the baseline model respectively. Experimental results prove that the proposed method can effectively improve the performance of the model in the biomedical named entity recognition task.

Concerning the problems in traditional house price evaluation method, such as single data source, over-reliance on subjective experience, idealization of considerations, an intelligent evaluation method based on multi-source data and ensemble learning was proposed. First, feature set was constructed from multi-source data, and the optimal feature subset was extracted using Pearson correlation coefficient and sequential forward selection method. Then, with Bagging ensemble strategy used as a combination method, multiple Light Gradient Boosting Machines (LightGBMs) were integrated based on the constructed features, and the model was optimized by using Bayesian optimization algorithm. Finally, this method was applied to the problem of house price evaluation, and the intelligent evaluation of house prices was realized. Experimental results on the real house price dataset show that, compared with traditional models such as Support Vector Machine (SVM) and random forest, the new model introduced with ensemble learning and Bayesian optimization improves the evaluation accuracy by 3.15%, and the evaluation results with percent error within 10% account for 84.09%. It can be seen that, the proposed model can be well applied to the field of intelligent house price evaluation, and has more accurate evaluation results.

The community evolution relationships extracted by the traditional adjacent time slice analysis cannot fully describe the entire community evolution process in dynamic graphs. Therefore, an improved community evolution relationship analysis method was proposed. First, the community events were defined, and the evolution states of the community were described according to the occurred community events. Then, the event matching was performed on two communities within different time slices to obtain community evolution relationships. Results of comparison with the traditional methods show that the total number of community events detected by the proposed method is more than twice that revealed by the traditional method, which proves that the proposed method can provide more useful information for describing the evolution process of communities in dynamic graphs.

To address the poor robustness of the extracted image features in traditional smoke detection methods, a smoke recognition method based on Dense convolution neural Network (DenseNet) was proposed. Firstly, the dense network blocks were constructed by applying convolution operation and feature map fusion, and the dense connection mechanism was designed between the convolution layers, so as to promote the information circulation and feature reuse in the dense network block structure. Secondly, the DenseNet was designed by stacking the designed dense network blocks for smoke recognition, saving the computing resources and enhancing the expression ability of smoke image features. Finally, aiming at the problem of small smoke image data size, data augmentation technology was adopted to further improve the recognition ability of the training model. Experiments were carried out on public smoke datasets. The experimental results illustrate that the proposed method achieves high accuracy of 96.20% and 96.81% on two test sets respectively with only 0.44 MB model size.

Heterogeneous multi-core processor is the mainstream solution for modern embedded systems now. Good online mapping or scheduling approaches play important roles in improving their advantages of high performance and low power consumption. To deal with the problem of dynamic mapping and scheduling of applications on heterogeneous multi-core processing systems, a dynamic mapping and scheduling solution was proposed to effectively determine remapping time in order to maximize the system performance by using the machine learning based detection technology of quickly and accurately evaluating program performance and program behavior phase change. In this solution, by carefully selecting the static and dynamic features of processing cores and programs to running to effectively detect the difference in computing power and workload running behaviors brought by heterogeneous processing, a more accurate prediction model was built. At the same time, by introducing phase detection technology, the number of online mapping computations was reduced as much as possible, so as to provide more efficient scheduling scheme. Finally, the effectiveness of the proposed scheduling scheme was verified on the SPLASH-2 dataset. Experimental results showed that, compared to the Completely Fair Scheduler (CFS) of Linux, the proposed method achieved about 52% computing performance gains and 9.4% improvement on CPU resource utilization rate. It shows that the proposed method has excellent performance in system computing performance and processor resource utilization, and can effectively improve the dynamic mapping and scheduling effect of applications of heterogeneous multi-core systems.

In order to achieve robust, accurate and real-time recognition of surface scratches under complex texture background with uneven brightness, a surface scratch recognition method based on deep neural network was proposed. The deep neural network for surface scratch recognition consisted of a style transfer network and a focus Convolutional Neural Network (CNN). The style transfer network was used to preprocess surface scratches under complex background with uneven brightness. The style transfer networks included a feedforward conversion network and a loss network. Firstly, the style features of uniform brightness template and the perceptual features of the detected image were extracted through the loss network, and the feedforward conversion network was trained offline to obtain the optimal parameter values of network. Then, the images with uniform brightness and uniform style were generated by style transfer network. Finally, the proposed focus convolutional neural network based on focus structure was used to extract and recognize scratch features in the generated image. Taking metal surface with light change as an example, the scratch recognition experiment was carried out. The experimental results show that compared with traditional image processing methods requiring artificial designed features and traditional deep convolutional neural network, the false negative rate of scratch detection is as low as 8.54% with faster convergence speed and smoother convergence curve, and the better detection results can be obtained under different depth models with accuracy increased of about 2%. The style transfer network can retain complete scratch features with the problem of uneven brightness solved, thus improving the accuracy of scratch recognition, while the focus convolutional neural network can achieve robust, accurate and real-time recognition of scratches, which greatly reduces false negative rate and false positive rate of scratches.

Heterogeneous Multi-core Processors (HMPs) platform has become the mainstream solution for modern embedded system design, and online mapping or scheduling plays a vital role in making full use of the advantages of high performance and low power consumption. Aiming at the dynamic mapping problem of application tasks in HMPs, a mapping and scheduling approach based on machine learning prediction model was proposed. On the one hand, a machine learning model was constructed to predict and evaluate the performance of different mapping strategies rapidly and efficiently, so as to provide support for online scheduling. On the other hand, the machine learning model was integrated with genetic algorithm to find out the optimal resource allocation strategy efficiently. Finally, an Motion-Join Photographic Experts Group (M-JPEG) decoder was used to verify the effectiveness of the proposed approach. The experimental results show that, compared with the Round Robin Scheduler (RRS) and sampling scheduling approaches, the proposed online mapping/scheduling approach has reduced the average execution time by about 19% and 28% respectively.

Aiming at the inaccuracy of the methods based on ground textures and space features in detecting new ground buildings, a novel Change Detection model based on Generative Adversarial Networks (CDGAN) was proposed. Firstly, a traditional image segmentation network (U-net) was improved by Focal loss function, and it was used as the Generator (G) of the model to generate the segmentation results of remote sensing images. Then, a convolutional neutral network with 16 layers (VGG-net) was designed as the Discriminator (D), which was used for discriminating the generated results and the Ground Truth (GT) results. Finally, the Generator and Discriminator were trained in an adversarial way to get a Generator with segmentation capability. The experimental results show that, the detection accuracy of CDGAN reaches 92%, and the IU (Intersection over Union) value of the model is 3.7 percentage points higher than that of the traditional U-net model, which proves that the proposed model effectively improves the detection accuracy of new ground buildings in remote sensing images.

An image stitching method based on Scale-Invariant Feature Transform (SIFT), thin-plate spline function and power function was proposed to solve the problem of low efficiency, mismatching of feature points, ghosting and stitching seam in image stitching algorithm. The point mapping relationship and overlapping area between the images were calculated by sampling and matching the input images. The local distortion model of the image was calculated by the feature point set, and the deformation of the image was completed by image interpolation. The power function weighting model was used to realize smooth transaction of the pixels in the deformed image to complete the image stitching. Experimental results show that the proposed method improves the registration efficiency of the feature points approximately by 59.78% and obtains more pairs of feature points compared to the traditional SIFT algorithm. Moreover, compared with the classical image stitching algorithm, the method solves the problems of image ghosting and stitching seam, and improves the score of image quality evaluation index.

Focusing on the detection problem of false data that conform to a certain pattern or rule, a false trend time series detection method based on randomness analysis was proposed. Based on the analysis of time series composition, firstly the simple forgery method and complex forgery method of false trend time series were explored, and decomposed into two parts:false trendness and false randomness. Then the false trend of time series was extracted by the approximation of base function, the false random of time series was analyzed with the randomness theory. Finally, monobit frequency and frequency within a block were adopted to test whether the false random part has randomness, which established a detection method of false time series with a certain trend feature. The simulation results show that proposed method can decompose the false time series and extract the false trend part effectively, meanwhile realize the detection of simple and complex forged data. It also supports the authenticity analysis for the numerical data obtained by means of observation or monitoring equipment, which improves the discrimination range of false data with average detection accuracy of 74.7%.

Nowadays, flight delay prediction has a large amount of data and the feature extraction is difficult. Traditional models can not solve these problems effectively, so a flight delay prediction model based on Dual-Channel Convolutional Neural Network (DCNN) was proposed. Firstly, flight data and meteorological data were fused in the model. Then, a DCNN was used to extract features automatically, and Batch Normalization (BN) and Padding strategy were used to improve the classification prediction performance of arrival delay level. Secondly, to guarantee the lossless transmission of feature matrix and enhance the patency of deep network, a straight channel was used in the Convolutional Neural Network (CNN). Meanwhile, convolution attenuation factor was introduced to control the sparseness of feature matrix, it also was used to control the proportion of feature matrix from different depth and guarantee the stability of the model. The experimental results indicate that the proposed model has a stronger data processing capability than the traditional model, and through fusion of meteorological data, the accuracy of the proposed model is improved 1 percentage point. When the networks are deepened, the model can guarantee the stability of gradients and train the deeper network, thus improves the accuracy to 92.1%. The proposed model based on DCNN algorithm has sufficient feature extraction and better prediction performance than the contrast model, it can better serve the civil aviation decision-making.

As the existing distributed subgradient optimization algorithms are mainly based on ideal assumptions:the network topology is balanced and the communication among the network is usually the exact information of a state variable of each agent. To relax these assumptions, a distributed subgradient optimization algorithm for switched networks was proposed based on limited quantized information communication. All information along each dynamical edge was quantified by a uniform quantizer with a limited quantization level before being sent in an unbalanced switching network, then the convergence of the multi-agent distributed quantized subgradient optimization algorithm was proved by using non-quadratic Lyapunov function method. Finally, the simulation examples were given to demonstrate the effectiveness of the proposed algorithm. The simulation results show that, under the condition of the same bandwidth, the convergence rate of the proposed optimization algorithm can be improved by adjusting the parameters of the quantizer. Therefore, the proposed optimization algorithm is more suitable for practical applications by weakening the assumptions on the adjacency matrix and the requirement of the network bandwidth.

Concerning the problems of high-dimensional data, such as non-linearity, low-rank form, and feature redundancy, an unsupervised feature selection algorithm based on kernel function was proposd, named Low Rank Non-linear Feature Selection algroithm (LRNFS). Firstly, the features of each dimension were mapped to a high-dimensional kernel space, and the non-linear feature selection in the low-dimensional space was achieved through the linear feature selection in the kernel space. Then, the deviation terms were introduced into the self-expression form, and the low rank and sparse processing of coefficient matrix were achieved. Finally, the sparse regularization factor of kernel matrix coefficient vector was introduced to implement the feature selection. In the proposed algorithm, the kernel matrix was used to represent its non-linear relationship, the global information of data was taken into account in low rank to perform subspace learning, and the importance of feature was determined by the self-expression form. The experimental results show that, compared with the semi-supervised feature selection algorithm via Rescaled Linear Square Regression (RLSR), the classification accuracy of the proposed algorithm after feature selection is increased by 2.34%. The proposed algorithm can solve the problem that the data is linearly inseparable in the low-dimensional feature space, and improve the accuracy of feature selection.

The existed TD-FTT (Time Dependent Fast Travel Time) algorithm, for answering K Nearest Neighbors ( KNN) query in time dependent road network, requires that the issued time and the arrival time of a query must be in the same time interval, which costs a long time in the preprocessing phase. To solve these problems, an Improved TD-FTT (ITD-FTT) algorithm based on dynamically selecting heuristic values was proposed. Firstly, in the preprocessing phase, the road network G _min with the minimum cost for each time interval was created by using time functions of edges. Secondly, a parallel method of utilizing Network Voronoi Diagram (NVD) in road network G _min was used to compute the nearest neighbors of nodes to reduce the time cost. Finally, in the query phase, the heuristic value was dynamically selected to get rid of the time interval limitation by calculating the time interval of the current arrival time of nodes. The experimental results show that in the preprocessing phase, the time cost of ITD-FTT is reduced by 70.12% compared with TD-FTT. In the query phase, the number of traversal nodes of ITD-FTT is 46.52% and 16.63% lower than TD-INE (Time Dependent Incremental Network Expansion) and TD-A (Time Dependent A star) algorithm respectively, and the response time of ITD-FTT is 47.76% and 18.24% lower than TD-INE and TD-A. The experimental results indicate that the ITD-FTT algorithm reduces the number of nodes by query expansion, decreases the time of searching the KNN results and improves the query efficiency.

Since New Approach to Multi-Objective A ^* combined with dimensionality reduction technique (NAMOA _dr ^*) algorithm has the phenomenon of plateau exploration, a Random Walk assisted NAMOA _dr ^* (RWNAMOA _dr ^*) algorithm which invoked a random walk procedure was proposed to find an exit (labels with heuristic value not dominated by the last extended label's) when the NAMOA _dr ^*was stuck on a plateau. To determine when NAMOA _dr ^* algorithm was stuck on a plateau exploration, a method of detecting plateau exploration was proposed. When the heuristic value of the extended label was dominated by the last extended label's for continuous m times, NAMOA _dr ^* algorithm was considered to fall into the plateau exploration. In the experiments, a randomly generated grid was used, which was a standard test platform for the evaluation of multi-objective search algorithms. The experimental results reveal that compared with NAMOA _dr ^* algorithm, RWNAMOA _dr ^* algorithm's running time is reduced by 50.69% averagely and its space consuming is reduced by about 10% averagely, which can provide theoretical support for accelerating multi-objective path searching in real life.

The current deep learning-based salient object detection algorithms fail to produce accurate object boundaries, which makes the regions along object contours blurred and inaccurate. To solve the problem, a salient object detection algorithm based on multi-task deep learning model was proposed. Firstly, based on deep Convolutional Neural Network (CNN), a multi-task model was used to separately learn region and boundary features of a salient object. Secondly, the detected object boundaries were utilized to produce a number of region candidates. After that the region candidates were re-ranked and their weights were computed by combining the results of salient region detection. Finally, the entire saliency map was extracted. The experimental results on three widely-used benchmarks show that the proposed method achieves better accuracy. According to F-measure, the proposed method averagely outperforms the deep learning-based algorithm by 1.9%, while lowers the Mean Absolutely Error (MAE) by 12.6%.

To solve the problem that traditional video emotional analysis methods can not work effectively and the results are not easy to explain, a video shot emotional analysis approach based on time-sync comments was proposed, as a basis for the recommendation of video shots. First, a formal description of video shots recommendation based on emotion analysis was studied. Then, after analyzing the classification of time sync comments based on Latent Dirichlet Allocation (LDA) topic model, the emotional vector of the words in time-sync comments were evaluated. Meanwhile, the emotion relationships among the video shots were analyzed for video shots recommendation. The recommendation precision of the proposed method was 28.9% higher than that of the method based on Term Frequency-Inverse Document Frequency (TF-IDF), and 43.8% higher than that of traditional LDA model. The experimental results show that the proposed model is effective in analyzing the complex emotion of different kinds of text information.

Considering that the Cooperative Cognitive Radio Networks (CCRN) perform poorly with low flexibility and deficient ability to adapt to complex environment, which caused by working under a fixed architecture at present, a kind of network architecture self-adaption technology based on cooperation and cognition was proposed to improve the anti-jamming and anti-damage ability of the CCRN. The technology made CCRN switch among three kinds of architectures, including centralized control, self-organization and cooperative relay, autonomously and flexibly, to deal with electromagnetic interference, equipment failure and obstructions on communication link, which could greatly enhance the network robustness. The switch scheme design and protocol implementation of different nodes were introduced in detail. Moreover, a CCRN testbed which consists of GNU Radio and the second generation of Universal Software Radio Peripheral (USRP2) was set up to test and verify its performance including switching time consumption and throughput. Results show that the technology significantly improves the anti-destroying ability, connectivity and Quality of Service (QoS) of CCRN compared with the network working under single, and fixed architecture.

Spatial clustering is one of the vital research directions in spatial data mining and knowledge discovery. However, constrained by the complex distribution of uneven density, various shapes and multi-bridge connection of points, most clustering algorithms based on distance or density cannot identify high aggregative point sets efficiently and effectively. A point clustering method based on spatial proximity was proposed. According to the structure of point Voronoi diagram, adjacent relationships among points were recognized. The similarity criteria was defined by region of Voronoi, a tree structure was built to recognize point-target clusters. The comparison experiments were conducted on the proposed algorithm, K-means algorithm and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Results show that the proposed algorithm is capable for identifying clusters in arbitrary shapes, with different densities and connected only at bridges or chains, meanwhile also suitable for aggregative pattern recognition in heterogeneous space.

Aiming at the shortage of current mobile Wireless Sensor Network (WSN) localization, a localization algorithm based on improved flooding broadcast mechanism and particle filtering was proposed. For a given unknown node, firstly, by the improved flooding broadcast mechanism, the effective average hop distance of an unknown node from its closest anchor node was used to calculate the distances to its all neighbor nodes. Then a differential error correction scheme was devised to reduce the measurement error accumulated over multiple hops for the average hop distance. Secondly, the particle filter and the virtual anchor node were used to narrow the prediction area, and more effective particle prediction area was obtained so as to further decrease the estimation error of the position of unknown node. The simulation results show that compared with DV-Hop, Monte Carlo Baggio (MCB) and Range-based Monte Carlo Localization (MCL) algorithms, the proposed positioning algorithm can effectively inhibit the broadcast redundancy and reduce the message overhead related to the node localization, and can achieve higher-accuracy positioning performance with lower communication cost.

Since in the massive data management, the compressed data can be done some operations without decompressing first, under the condition of normal distribution, according to features of column data storage, a new compression algorithm which oriented column storage, called CCA (Column Compression Algorithm), was proposed. Firstly, the length of data was classified; secondly, the sampling method was used to get more repetitive prefix; finally the dictionary coding was utilized to compress, meanwhile the Column Index (CI) and Column Reality (CR) were acted as data compression structure to reduce storage requirement of massive data storage, thus the basic relational algebraic operations such as select, project and join were directly and effectively supported. A prototype database system based on CCA, called D-DBMS (Ding-Database Management System), was implemented. The theoretical analyses and the results of experiment on 1 TB data show that the proposed compression algorithm can significantly improve the performance of massive data storage efficiency and data manipulation. Compared to BAP (Bit Address Physical) and TIDC (TupleID Center) method, the compression rate of CCA was improved by 51% and 14%, and its running speed was improved by 47% and 42%.

Currently, due to the limitation of hardware for network protocol developing and huge cost of network building in hardware for performance evaluation, most of the literature focuses on software system which limits the results in theory. To solve these problems, a hardware-in-loop simulation system for distributed wireless network MAC (Media Access Control) protocols based on GNU Radio and the second generation of Universal Software Radio Peripheral (USRP2) was designed and implemented. Referring to the standard IEEE802.11 Distribution Coordination Function (DCF) protocol, the designed simulation system adopted the discrete-event simulation technique to realize simulation for multi-node distributed wireless networks with only the least hardware resources (i.e., one Personal Computer (PC) and two USRP2s). In the software, the MAC protocols were implemented using Python language, which is flexible and easy to change or extend. And in the physical layer, modularized modules in C++ language were adopted for signal processing, which further improves the scalability of the simulation system. The experimental results validate the reliability of the hardware-in-loop simulation system, in comparison with the Bianchi algorithm and time slot based saturation throughput calculation model.

The Automated Trust Negotiation (ATN) Model based on Interleaved Spiral Matrix Encryption (ISME) was proposed for the protection of sensitive information in the automated trust negotiation. The interleaved spiral matrix encryption and policy migration were used in the model to protect three kinds of sensitive information of negotiation. Compared with the traditional spiral matrix encryption algorithm, the concept of odd-even bit and triple were added into the interleaved spiral matrix encryption algorithm. In order to make the model adapt the application better, the concept of key attributes flag was introduced in the certification of negotiations, and thus it recorded the sensitive information which corresponded to the encrypted key effectively. Meanwhile, how to represent the negotiation rules through encryption function was listed in the negotiation model. To increase efficiency and success rate of the model, the 0-1 graph policy parity algorithm was proposed. The decomposition rules of six basic propositions were constructed by directed graph of graph theory in the 0-1 graph policy parity algorithm. The propositions abstracted by the access control policies could be determined effectively and the reliability and completeness was testified to prove the equivalence of semantics concept and syntax concept in logistic system. Finally, the simulation results demonstrate that the model of the average number of disclosure strategy is 15.2 less than the traditional model in 20 negotiations. The successful rate of the negotiation is increased by 21.7% and the efficiency of the negotiation is increased by 3.6%.

Concerning the problem that finding community structure in complex network is very complex, a community discovery algorithm based on node similarity was proposed. The basic idea of this algorithm was that node pairs with higher similarity had more posibility to be grouped into the same community. Integrating local and global similarity, it constructed a similarity matrix which each element represents the similarity of a pair of nodes, then merged nodes which have the most similarity to the same community. The experimental results show that the proposed algorithm can get the correct community structure of networks, and achieve better performance than Label Propagation Algorithm (LPA), GN (Girvan-Newman) and CNM (Clauset-Newman-Moore) algorithms in community detection.

Concerning that the increasement of accumulated error causes serious distortion of Unmanned Aerial Vehicle (UAV) remote sensing images stitching, a projection error correction algorithm based on space intersection was proposed, Using space intersection theory, the spatial coordinates of 3D points were calculated according to correspondence points. Then all 3D points were orthographic projected onto the same space plane, and the orthographic points were projected onto the image plane to get corrected correspondence points, Finally, M-estimator Sample Consensus (MSAC) algorithm was used to estimate the homography matrix, then the stitching image was obtained. The simulation results show that this algorithm can effectively eliminate the projection error, thus achieve the purpose of inhibiting UAV remote sensing image stitching error.