Aiming at the problem that it is difficult to capture the temporal information during the dynamic change of video popularity, a Deep Attention video popularity prediction model Fusing Content and Temporal information (DAFCT) was proposed. Firstly, according to the users' feedback information, an Attention mechanism based Long Short-Term Memory network (Attention-LSTM) model was constructed to capture the popular trend and mine the temporal information. Secondly, Neural Factorization Machine (NFM) was used to process multi-modal content features and embedding techniques were adopted to reduce the computational complexity of the model by reducing the dimension of sparse high-dimensional features. Finally, the concatenate method was employed to fuse the temporal information and content features, and a Deep Attention Video Popularity Prediction (DAVPP) algorithm was designed to solve the proposed DAFCT. Experimental results show that compared with Attention-LSTM model and NFM model, the recall of DAFCT is improved by 10.82 and 3.31 percentage points, and the F1 score was improved by 9.80 and 3.07 percentage points, respectively.

In order to improve the intelligence level of waterway traffic safety supervision, and further improve the positioning precision and detection accuracy in the ship detection algorithms based on deep learning, based on the traditional YOLOv3, an enhanced YOLOv3 algorithm for ship detection was proposed. First, the prediction box uncertain regression was introduced in the network prediction layer in order to predict the uncertainty information of bounding box. Second, the negative logarithm likelihood function and improved binary cross entropy function were used to redesign the loss function. Then, the K-means clustering algorithm was used to redesign the scales of prior anchor boxes according to the shape of ship, and prior anchor boxes were evenly distributed to the corresponding prediction scales. During training phase, the data augmentation strategy was used to expand the number of training samples. Finally, the Non-Maximum Suppression (NMS) algorithm with Gaussian soft threshold function was used to post-process the prediction boxes. The comparison experiments of various improved methods and different object detection algorithms were conducted on real maritime video surveillance dataset. Experimental results show that, compared to the traditional YOLOv3 algorithm, the YOLOv3 algorithm with prediction box uncertainty information has the number of False Positives (FP) reduced by 35.42%, and the number of True Positives (TP) increased by 1.83%, thus improving the accuracy. The mean Average Precision (mAP) of the enhanced YOLOv3 algorithm on ship images reaches 87.74%, which is improved by 24.12% and 23.53% respectively compared to those of the traditional YOLOv3 algorithm and Faster R-CNN algorithm. The proposed algorithm has the number of images detected per second reaches 30.70, meeting the requirement of real-time detection. Experimental results indicate that the proposed algorithm can achieve high-precision, robust and real-time detection of ships under adverse weather and conditions such as fog weather and low-light condition as well as the complex navigation backgrounds.

In order to more effectively combine the detail information of high resolution PANchromatic (PAN) image and the spectral information of low resolution MultiSpectral (MS) image, an improved panchromatic sharpening algorithm based on sparse representation was proposed. Firstly, the intensity channel of an MS image was down-sampled and then up-sampled to get its low-frequency components. Secondly, the MS image intensity channel minus low-frequency components to obtain its high-frequency components. Random sampling was performed in the acquired high and low frequency components to construct a dictionary. Thirdly, the PAN image was decomposed to get the high-frequency components by using the constructed overcomplete dictionary. Finally, the high-frequency components of the PAN image were injected into the MS image to obtain the desired high-resolution MS image. After a number of experiments, it was found that the proposed algorithm subjectively retains the spectral information and injects a large amount of spatial details. Compared with component substitution method, multiresolution analysis method and sparse representation method, the reconstructed high resolution MS image by the proposed algorithm is more clear, and the correlation coefficient and other objective evaluation indicators of the proposed algorithm are also better.

The security mechanism of REpresentational State Transfer (REST) architecture is not perfect. In order to solve the problem, the security analysis and evaluation of REST architecture based on attack graph was proposed, and the security quantitative evaluation of REST architecture was realized by using attack graph. Firstly, the possible attack of REST architecture was predicted, the REST architecture attack graph model was constructed accordingly, and the attack probability parameter and attack realization parameter were calculated. Then, according to the attack state and attack behavior of attack graph, the security protection measures were proposed. In view of the above, the REST architecture attack graph model was reconstructed, and the attack probability parameter and attack realization parameter were recalculated too. By comparison, after the adoption of security protection measures, the attack possibility parameter has been reduced to about 1/10, and the attack realization parameter has been reduced to about 1/86. The comparison results show that the constructed attack graph can effectively and quantitatively evaluate the security performance of REST architecture.

With the explosive growth of video streaming applications, the use of Network Coding (NC) to improve the network performance and then to provide a better quality of video streaming is becoming a hot topic. In order to efficiently exploit the benefits of NC for video delivery, the proposed transmission strategies should be adapted for the characteristics of video traffic and the network environment should also be considered. Firstly, the basic concepts and methods of NC were presented. Then, a variety of NC based techniques that have been specifically designed for video streaming were analyzed and summarized into three main categories, including unequal error protection to give priority to important video packets, reducing packet transmission delay to meet realtime video streaming requirements, enhancing network error recovery strategy to improve transmission reliability. Thirdly, the applications of video streaming with NC in the P2P networks, multi-source cooperative and content-centric network scenarios were introduced respectively. Finally, based on this study, open issues and further research topics were elaborated.

Since the data forwarding in Vehicular Ad Hoc Network (VANET) is inefficient, a technology on data forwarding and routing selection based on Software Defined Network (SDN) was proposed. Firstly, a hierarchical architecture of SDN based VANET, which was consist of local controller and global controller, was used to separate data forwarding from transmission control and decide the direction of data forwarding flexibly. Secondly, a vehicular routing mechanism of single road section was designed and data could be transmitted stably by predicting vehicular position and using greedy strategy. Thirdly, to achieve the goal of path disjoint which could avoid the bandwidth bottleneck between multiple demands, a road section routing mechanism was proposed, which combined the Breadth First Search (BFS) and edge set. Finally, compared with Ad Hoc On-demand Distance Vector (AODV) routing, the proposed algorithm could increase data reception rate by 40% and reduce average delay by 60%. The simulation results show that the technology on data forwarding and routing for software defined VANET can effectively improve the data delivery rate, and reduces the average packet delay.

To combat low efficiency of Artificial Bee Colony (ABC) algorithm on solving combinatorial problem, a parallel ABC optimization algorithm based on Spark was presented. Firstly, the bee colony was divided into subgroups among which broadcast was used to transmit data, and then was constructed as a resilient distributed dataset. Secondly, a series of transformation operators were used to achieve the parallelization of the solution search. Finally, gravitational mass calculation was used to replace the roulette probability selection and reduce the time complexity. The simulation results in solving the Traveling Salesman Problem (TSP) prove the feasibility of the proposed parallel algorithm. The experimental results show that the proposed algorithm provides a 3.24x speedup over the standard ABC algorithm and its convergence speed is increased by about 10% compared with the unimproved parallel ABC algorithm. It has significant advantages in solving high dimensional problems.

Aiming at improving the users' high viscosity in social networks, an algorithm based on user loyalty in social network system was proposed. In the proposed algorithm, double Recency Frequency Monetary (RFM) model was used for mining the different loyalty kinds of users. Firstly, according to the double RFM model, the users' consumption value and behavior value were calculated dynamically and the loyalty in a certain time was got. Secondly, the typical loyal users and disloyal users were found out by using the founded standard curve and similarity calculation. Lastly, the potential loyal and disloyal users were found out by using modularity-based community discovery and independent cascade propagation model. On some microblog datasets of a social network, the quantitative representation of user loyalty was confirmed in Social Network Service (SNS), thus the users could be distinguished based on users' loyalty. The experimental results show that the proposed algorithm can be used to effectively dig out different loyalty kinds of users, and can be applied to personalized recommendation, marketing, etc. in the social network system.

Since the efficiency of data forwarding in Vehicular Ad Hoc Network (VANET) is low, a data forwarding mechanism in VANET based on Software-Defined Network (SDN) was proposed. Firstly, a hierarchical architecture of SDN based VANET was designed. This architecture was consist of local controller and vehicular, it could implement the separation of control and data forwarding, and also could achieve high scalability, reliability and efficiency. Secondly, a new data forwarding mechanism was proposed, which used dynamic programming and binary search. Finally, compared with Ad Hoc On-demand Distance Vector routing (AODV), Destination Sequenced Distance Vector routing (DSDV), Dynamic Source Routing (DSR) and Optimized Link State Routing (OLSR) algorithm, the proposed algorithm could improve packet delivery fraction and end-to-end delay. Therein, the average increase of packet delivery fraction was about 100%, while the average reduction of end-to-end delay was about 20%. The simulation results show that the data forwarding mechanism in software-defined VANET can effectively improve the packet delivery and reduce the end-to-end delay.

Vehicular Ad Hoc Network (VANET) is a highly dynamic communication network, which means it's a great challenge to design a stable data dissemination mechanism. Applying Named Data Networking (NDN), which focused on the content of the data, to VANET could effectively relive the problems brought by the frequent change of network topology. Firstly, the message types and data structure of NDN were improved. Secondly, the way of establishing routes according to section was put forward with the combination of characteristics of VANET so as to reduce the cost of data dissemination. The simulation results show that compared to the traditional NDN algorithm which is applied to VANET data dissemination, Average Hit Rate (AHR) and Average Forward Times (AFT) can be significantly improved by VANET data dissemination mechanism based on NDN. Therein, the average increase of AHR is about 53 percent points, while the average reduction of AFT is about 0.4 times. Therefore, the improved VANET data dissemination mechanism can improve the efficiency of data dissemination by using the new routing method.

Aiming at the problem of slow convergence and being easy to fall into local optimum in the route planning of the traditional teaching-learning-based optimization algorithm, an adaptive crossover teaching-learning-based optimization algorithm was proposed. Firstly, the teaching factor of the algorithm was changed with the number of iterations, so the learning speed of the algorithm was improved. Secondly, when the algorithm was likely to fall into local optimum, a certain disturbance was added to make the algorithm jump out of local optimum as far as possible. Finally, in order to improve the convergence effect, the crossover link of genetic algorithm was introduced into the algorithm. Then the path planning of Unmanned Aerial Vehicle (UAV) was carried out by using the traditional teaching-learning-based optimization algorithm, the adaptive crossover teaching-learning-based optimization algorithm and the Quantum Particle Swarms Optimization (QPSO) algorithm. The simulation results show that in 10 times of planning, the adaptive crossover teaching-learning-based optimization algorithm finds the global optimal route for 8 times, while the traditional teaching-learning-based optimization algorithm and the QPSO algorithm find the route for only 2 times and 1 time respectively, and the convergence of the adaptive crossover teaching-learning-based optimization algorithm is faster than the other two algorithms.

In the processing of registration for multi-temporal high resolution remote sensing images, the phenomena of surface features change and relative parallax displacement caused by differences in acquisition conditions degrades the accuracy of registration. To resolve the aforementioned issue, a registration algorithm for multi-temporal high resolution remote sensing images based on abnormal region sensing was proposed, which consists of coarse and fine registration. The algorithm of Scale-Invariant Feature Transform (SIFT) has a better performance on scale space, the feature points from different scale space indicates the various size of spot. The high scale space points represent the objects which have a stable condition, the coarse registration can be executed depending on those points. For the fine registration, intensity correlation measurement and spatial constraint were used to decide the regions which were used to extract the efficacious points from low scale space, the areas for searching matching points were limited as well. Finally, the accuracy of the proposed method was evaluated from subjective and objective aspects. Experimental results demonstrate that the proposed method can effectively restrain the influence of abnormal region and improve registration accuracy.

To solve the problem that the vehicle monitoring technology in the bus was not perfect and few emergencies detection method were invented, a real-time detection algorithm based on image processing was proposed to detect the emergency which mainly refers to the rapid flow of the crowd in the bus. First, the main motion area was grouped according to the trajectory of the passengers. Second, an improved moving foreground extraction method was used to extract moving foreground. Then the characteristic points in the moving foreground were extracted by Harris operator, and the optical flow constraint algorithm was used to establish the motion vector filed for characteristic points. At last, the KPA (Kinetic Potential Area) model was built to recognize the emergency. Theoretical analysis and experimental results show that, in testing the emergency under different environment, the proposed algorithm has a success rate of more than 83.9%. In addition, it has advantages of real-time detection in a practical application.

Concerning the problem that the data in distributed system usually has many replicas among several datacenters and a robust mechanism was required to maintain data consistency, an algorithm of geographically distributed replication management was proposed after further research on the replication theory of distributed systems. Microsoft Research used Service Level Agreements (SLA) to divide the consistency requirements of users into several levels, each of which was associated with tolerable delay. The system ensured that users could have higher service levels within tolerable delay. Tuba system extends Pileus, it can dynamically change the location of primary and secondary replicas according to statistics sent by all users, so as to raise the average performance of the system. But the replication of Tuba system was carried out based on a single target unit. Improving the method in Tuba system, a set of algorithms independently to change the location of primary and secondary replicas was proposed. The mechanism was implemented in the replication among the HBase distributed systems. After the system is completed, the results show that taking the correlation between two regions into consideration when changing the location of primary and secondary replicas can improve the overall utility of the system.

Distortion of H.264 video over 802.11e is jointly caused by transmission packet loss and encoder quantization, to tackle this issue, this paper proposed a distortion-driven cross-layer video transmission optimization. The relationship between Quantization Parameter (QP) and quantization distortion was obtained firstly by a rate-distortion model. Then according to the loss rate of video data partition, the transmission and total distortions at the receiver side were estimated. Based on the total distortion, a selection algorithm of optimal quantization parameter was presented. The experimental results show that, compared with the method of up-bottom cross-layer optimization with various queue priorities for video data partitions and bottom-up cross-layer optimization with an adaptive quantization parameter selection, the proposed method gets 1~2dB average Peak Signal-to-Noise Ratio (PSNR) improvement, and it has less distortion at the receiver side.

Concerning the problem of low robustness of general watermarking algorithms in resisting JPEG compression and geometric transform attacks, a zero-watermarking algorithm based on Cellular Automata (CA) and Singular Value Decomposition (SVD) was proposed. Firstly, an image was transformed by 2-dimensional cellular automata transform and the low-frequency subband approximation image were isolated, then the CA parameters was saved as key. After that, the approximation image was sub-blocked, and the blocks were decomposed by SVD, then the zero-watermark was constructed by CA rule in SVD matrix. In image authentication, the image could be certificated by comparing the similarity of two watermarks with the threshold value. The experimental result shows that this algorithm has good invisibility and perfect robustness in resisting JPEG compression and geometric transform attacks.

In the available literatures, creating new files with New Technology File System (NTFS) that does not depend on calling Windows Application Program Interface (API) takes place in small directory. Therefore, a new technological realization of creating files in big directories was proposed in this paper. Firstly, it located the index buffer by traversaling the B+tree. Secondly, by judging whether the index buffer had an index node, it would put the created index entry into the specified location of index buffer respectively. Next, the index buffer inserted by the index was written to disk. Finally, it created new files in the big directories successfully. The experiments prove that the files can be created correctly in a large directory using the new creating technology.

Owing to that different users focus on attributes of the same item is not exactly the same, individuals' weight distribution for goods attributes are not the same. A method of the generalized interval-valued trapezoidal fuzzy soft set was proposed to deal with this kind of recommendation problems. First, the concept of generalized interval-valued trapezoidal fuzzy soft set was established by combining the concepts of generalized interval-valued trapezoidal fuzzy set and soft set, some basic operations on a generalized interval-valued trapezoidal fuzzy soft set were defined, such as “and” operation, and “or” operation. Using these operations, as well as the center of gravity method of the generalized interval-valued trapezoidal fuzzy numbers, commodities could be ranked. A group preference model from the preferences of the group members could be constructed. Finally, this paper used the car recommendation as an example to introduce the group preference aggregation algorithm and this numerical example was given to illustrate the feasibility and effectiveness of the proposed method.

This paper gave a solution to emergency task in space. When the emergency task occurred, at first, the existing satellite constellation was used to cover the target locations and the coverage rate was computed. If the coverage performance did not meet the mission requirements, the Non-Dominated Sorting Genetic Algorithm Ⅱ （NSGA-Ⅱ） was used to optimize the layout of satellite constellation, i.e. optimizing the anomaly of each satellite in the constellation. Then the phase modulation maneuver was used to achieve constellation optimization results, i.e. maneuvering the satellites to the specified locations, and calculating maneuver time and energy of each satellite. Finally, an emergency task example and its solution process were provided, and the time and energy of the satellite orbit maneuver were calculated.

Through the research for the type of network attack and the intrusion detection method,the fact that the normal intrusion detection method is not good enough for detecting U2R and R2L was found. To improve the detection rate of anomaly detection system for U2R and R2L, an anomaly detection model based on support vector machines and Bayesian classifying was suggested. In order to reduce the redundant records in the training data , the BIRCH clustering algorithm is used, besides, the detection model applys SVM for detecting DoS and Probe and uses Bayesian classifying to detect U2R and R2L. Experimental results show that the proposed model can improve obviously detection rate for U2R and R2L.

To solve the problem of minimum energy multicast in energy-constraint wireless Ad hoc networks, the communication model of MR-MCAAs multi-beam antennas was constructed, and the formal definition of the problem of the minimum energy multicast with MR-MCAAs multi-beam antennas was given, and then proposed a heuristic algorithm for this NP-hard problem. The algorithm proposed the two possible strategies for beam reassignment to optimize the scheme of the beam assignment and beam transmitting of every node, and constructed the minimum energy multicast tree with MR-MCAAs multi-beam antennas. The algorithm has the time complexity of O（n3logn）, where n denotes the number of nodes in the networks. The simulations show that the energy consumption of minimum energy multicast with 2–beam antennas reduced by 65～75 percent compared with the single beam directional antennas.

Available bandwidth is the main parameter to reflect the network status, of which the accurate measurement and estimation is an essential problem in traffic engineering and network monitoring. And there are many difficulties in its actual measurement. For Spruce, it converges slowly and needs high overhead. To solve the problems, Wspruce, an improved method of measuring available bandwidth was proposed. By using Hidden Markov Model (HMM)-series prediction features, more accurate analysis can be made on the available bandwidth. The actual measurements show that the method for estimating the available bandwidth measurement is faster, and of lower overhead.

According to the architecture of multi-core processors and the temporal local characteristics of network data flow, a division and dynamic adaptation algorithm was proposed based on multi-core processors. Classifying network data flow by the type and optimizing chain of rules dynamically by the temporal locality of network flow, the count of the multi-core's L7-Filter matching network data flow were reduced effectively and the processing efficiency was improved dramatically. The simulation result shows that given the number of packets in the same conditions, the algorithm has about 7 percent improvement of the multi-core processing performance. With the increasing number of network packets, the performance superiority becomes more obvious.