Concerning the low accuracy and long running time of link prediction between dynamic network nodes, a dynamic network representation learning model using denoising AutoEncoder (dAE) as the framework and combining with Graph Convolutional Network (GCN) and Long Short-Term Memory (LSTM) network, named dynGAELSTM, was proposed. Firstly, the GCN was used in the front-end of this model to capture the feature information of the high-order graph neighborhood of the dynamic network nodes. Secondly, the extracted information was input into the coding layer of the dAE to obtain the low-dimensional feature vectors, and the spatio-temporal dependent features of the dynamic network were obtained on the LSTM network. Finally, a loss function was constructed by comparing the prediction map reconstructed through the decoding layer of the dAE with the real map, so as to optimize the model to complete the link prediction. Theoretical analysis and simulation experiments showed that compared with the model with the second-best prediction performance, the dynGAELSTM model had the prediction performance improved by 0.79, 1.19 and 3.13 percentage points respectively, and the running time reduced by 0.92% and 1.73% respectively. In summary, the dynGAELSTM model has higher accuracy and lower complexity in the link prediction tasks compared to the existing models.

The low-rank constraint model based on traditional Nuclear Norm Minimization(NNM)tends to cause local texture detail loss in the denoising of Low-Dose CT(LDCT)image. To tackle this issue,a regional-content-aware weighted NNM algorithm was proposed for LDCT image denoising. Firstly,a Singular Value Decomposition(SVD)based method was proposed to estimate the local noise intensity in LDCT image. Then,the target image block matching was performed based on the local statistical characteristics. Finally,the weights of the nuclear norms were adaptively set based on both the local noise intensity of the image and the different singular value levels,and the weighted NNM based LDCT image denoising was realized. The simulation results illustrated that the proposed algorithm decreased the Root Mean Square Error(RMSE)index by 30. 11%,14. 38% and 8. 75% respectively compared with the traditional NNM,total variation minimization and transform learning algorithms,and improved the Structural SIMilarity(SSIM)index by 34. 24%,23. 06% and 11. 52% respectively compared with the above three algorithms. The experimental results on real clinical data illustrated that the mean value of the radiologists' scores of the results obtained by the proposed algorithm was 8. 94,which is only 0. 21 lower than that of the corresponding full dose CT images,and was significantly higher than those of the traditional NNM,total variation minimization and transform learning algorithms. The simulation and clinical experimental results indicate that the proposed algorithm can effectively reduce the artifact noise while preserving the texture detail information in LDCT images.

It is difficult to obtain the overall optimal solution by the traditional order batching and the picking path step-by-step optimization of picking operation in the logistics distribution center. In order to improve the efficiency of picking operation, a joint picking strategy based on nested genetic algorithm for order batching and path optimization was proposed. Firstly, the joint optimization model of order batching and picking path was established with the shortest total picking time as the objective function. Then, a nested genetic algorithm was designed to solve the model with the consideration of the complexity of double optimizations. The order batching result was continuously optimized in the outer layer, and the picking path was optimized in the inner layer according to the order batching result in the outer layer. Results of the examples show that, compared with the traditional strategies of order step-by-step optimization and step-by-step optimization in batches, the proposed strategy has reduced the picking time by 45.6% and 6% respectively, and the joint optimization model based on nested genetic algorithm results in shorter picking path and less picking time. To verify that the proposed algorithm has better performance on orders with different sizes, the simulation experiments were performed to the examples with 10, 20, 50 orders respectively. The results show that, with the increase of order quantity, the overall picking distance and time are further reduced, the decrease of picking time is risen from 6% to 7.2%.The joint optimization model of picking operation based on nested genetic algorithm and its solution algorithm can effectively solve the joint optimization problem of order batching and picking path, and provide the basis for the optimization of picking system in the distribution center.

In the edge computing, the communication between edge computing nodes and terminal devices is vulnerable to impersonation attacks, therefore a physical-layer impersonation attack detection algorithm based on Deep Q-Network (DQN) was proposed. Firstly, an impersonation attack model was built in the edge computing network, a hypothesis test based on the physical-layer Channel State Information (CSI) was established by the receiver, and the Euclidean distance between the currently measured CSI and the last recorded CSI was taken as the test statistics. Secondly, for the dynamic environment of edge computing, the DQN algorithm was used to adaptively select the optimal test threshold with the goal of maximizing the gain of the receiver. Finally, whether the current sender was an impersonation attacker was determined by comparing the statistics with the test threshold. The simulation results show that the Signal-to-Interference plus Noise Ratio (SINR) and channel gain ratio have certain effect on the performance of the detection algorithm, but when the relative change of channel gain is lower than 0.2, the false alarm rate, miss rate and average error rate of the algorithm are less than 5%. Therefore, the detection algorithm is adaptive to the dynamical environment of edge computing.

At present, the researches of ensemble clustering mainly focus on the optimization of ensemble strategy, while the measurement and optimization of the quality of basic clustering are rarely studied. On the basis of information entropy theory, a quality measurement index of basic clustering was proposed, and a three-way screening method for basic clustering was constructed based on three-way decision. Firstly, α, β were reset as the thresholds of three-way decision of basic clustering screening. Secondly, the average cluster quality of each basic clustering was calculated and was used as the quality measurement index of each basic clustering. Finally, the three-way decision was implemented. For one three-way screening, its decision strategy is:1) deleting the basic clustering if the quality measurement index of the basic clustering is less than the threshold β; 2) keeping the basic clustering if the quality measurement index of the basic clustering is greater than or equals to the threshold α; 3) recalculating the quality of a basic clustering and if the quality measurement index of the basic clustering is greater than β and less than α or equals to β. For the third option, the decision process continues until there is no deletion of basic clustering or reaching the times of iteration. The comparative experiments show that the three-way screening method of basic clustering can effectively improve the ensemble clustering effects.

The manual processing method is mainly used for the detection, tracking and information editing of key objects in indoor scene video, which has the problems of low efficiency and low precision. In order to solve the problems, a new learning method of indoor scene semantic annotation based on texture information was proposed. Firstly, the optical flow method was used to obtain the motion information between video frames, and the key frame annotation and interframe motion information were used to initialize the annotation of non-key frames. Then, the image texture information constraint of non-key frames and its initialized annotation were used to construct an energy equation. Finally, the graph-cuts method was used for optimizing to obtain the solution of the energy equation, which was the non-key frame semantic annotation. The experimental results of the annotation accuracy and visual effects show that, compared with the motion estimation method and the model-based learning method, the proposed learning method of indoor scene semantic annotation based on texture information has the better effect. The proposed method can provide the reference for low-latency decision-making systems such as service robots, smart home and emergency response.

Concerning the high computational complexity and communication overhead of wireless network node localization algorithm based on message passing algorithm, a ranging-based hybrid message passing node localization method with low complexity and cooperative overhead was proposed. The uncertainty of the reference nodes was taken into account to avoid error accumulation, and the messages on factor graph were restricted to be Gaussian distribution to reduce the communication overhead. Firstly, the factor graph was designed based on the system model and the Bayesian factorization. Secondly, belief propagation and mean filed methods were employed according to the linear state transition model and the nonlinear ranging model to calculate the prediction messages and the cooperation messages, respectively. Finally, in each iteration, the non-Gaussian beliefs were approximated into Gaussian distribution by Taylor expansions of the nonlinear terms. The simulation results show that the positioning accuracy of the proposed algorithm is compareable to that of Sum-Product Algorithm over a Wireless Network (SPAWN), but the information transmitted between nodes decreases from a large number of particles to mean vector and covariance matrix, and the comupational complexity is also dramatically reduced.

Concerning the problem in pencil drawing generation that the pencil lines lack flexibility and textures lack directions, a method of combining directional textures and pencil sketches was proposed to produce pencil drawing from natural images. First, histogram matching was employed to obtain the tone map of the image, and an image was segmented into several regions according to color. For each region, tone and direction were computed by its color and its shape, to decide the final tone and direction of the pencil drawing. Then, an adjusted linear convolution was used to get the pencil sketches with certain randomness. Finally, the directional textures and sketches were combined to get the pencil drawing style. Different kinds of natural images could be converted to pencil drawings by the proposed method, and the renderings were compared with those of existing methods including line integral convolution and tone based method. The experimental results demonstrate that the directional texture can stimulate the manual pencil texture better and the adjusted sketches can mimic the randomness and flexibility of manual pencil drawings.

Focusing on the issue that the data acquisition amount of Photoacoustic Computed Tomography (PACT) based on ultrasonic array is generally huge, and the imaging process is time-consuming, a fast photoacoustic computed tomography method with Principal Component Analysis (PCA) was proposed to extend its applications to the field of hemodynamics. First, the matrix of image samples was constructed with part of full-sampling data. Second, the projection matrix representing the signal features could be derived by the decomposition of the sample matrix. Finally, the high-quality three-dimensional photoacoustic images could be recovered by this projection matrix under three-fold under-sampling. The experimental results on vivo back-vascular imaging of a rat show that, compared to the traditional back-projection method, the data acquisition amount of PACT using PCA can be decreased by about 35%, and the three-dimensional reconstruction speed is improved by about 40%. As a result, both the fast data acquisition and high-accurate image reconstruction are implemented successfully.

In order to improve the performance of obstacle avoidance for mobile robots in continuous obstacle environment, a fuzzy algorithm of obstacle avoidance with speed feedback was proposed. Ultrasonic sensors were utilized to perceive the surroundings, and based on fuzzy control, the mobile robot adjusted its speed according to the distribution of obstacles. Then the graceful degradation was introduced combined with the improved fuzzy obstacle avoidance to enhance the robustness of the mobile robot. The experimental results show that the method can adjust the speed through interaction with the environment, control the robot in a collision-free way and optimize the obstacle avoidance path. Simultaneously, the method shows good effectiveness.

The judgment of reachability is one of the fundamental issues in Petri net analysis. The paper analyzed the existing method and the method based on constraint programming for the reachability of Petri net, and then proposed the judgment method for reachability problem based on constraint optimization. The method was based on the state equation method, separately using the constraint programming and the optimization to seek the feasible solution and the optimal solution, thereby decreased the searching path and attained the purpose of reducing the solution space of the state equation. Finally an example was given to prove that the algorithm can improve the determination efficiency.

In order to obtain the useful information that can satisfy the user requirements, this paper proposed a distributed information retrieval system based on Hadoop and Lucene handling the Web electronic products information retrieval. In order to improve the retrieval efficiency, using the Map and Reduce method of Hadoop technology implemented the storage of distributed index files and using Lucene technology implemented the file access of distributed index files. At the same time, it also proposed an improved method at fine grain retrieval level, which reduced the index building time. The experiment demonstrates that our distributed information retrieval system has a good retrieval performance for Web electronic products information.

Recognition of hand-written ballot symbols is crucial in vote-counting system based on image understanding. To improve the accuracy of ballot symbol recognition, a symbol recognition approach based on run feature was proposed. Firstly, the concept of run was presented and a discriminant model was established based on run features of ballot symbols. Secondly, the relative positions of runs were described with a ternary tree. In addition, the main run regions were extracted in noisy environment by merging run regions, and an approach of recognizing ambiguous symbols was also given. Finally, the experimental results show that the run features can accurately reflect the geometrical features of ballot symbols. The proposed approach achieves high accuracy, and its accuracy is 6.07% higher than that of template matching algorithm.

The lane change decision-making model was established based on the fuzzy multi-objective theory. The predicted results of lane change models which considered and did not consider driving tendency difference were calculated according to the experiment data of road. The predicted traffic flow macroscopic parameter (lane change rate) was compared with the result of road experiment to verify the inferential results. The experimental results show that accuracy of the method used for identifying vehicle driving tendency can be improved significantly.

Concerning the problem of performance loss due to limited feedback in multiuser MIMO downlink systems, a new limited feedback precoding for multiuser Multiple Input Multiple Output (MIMO) systems based on double codebook was proposed. The maximum SINR criteria was used for selecting optimal codeword from the Grassmannian codebook and perturbation codeword at the receiving, and feedback the Grassmannian precoding codeword index and perturbation codeword index to the transmitter, then the perturbation codeword was used at the transmitter to get optimal capacity, and compensating for the capacity performance loss due to the limited feedback. The simulation results show that the proposed method ensures Bit Error Rate (BER) performance and the cost of the feedback link, and the system throughput is improved effectively.

Evolving new software component based on previous software components is a key technique to improve software reusability and satisfy users' various demands. In this paper, an interactive evolution model was proposed based on multiple Agents, which could autonomously process consistent data. Then, the aspect weaving mechanism, which can effectively reduce the coupling degree of different function areas, was introduced in evolution to insert new codes into the exact places of target component. Furthermore, the evolution complexity was also discussed and several indicators and a model were given to calculate evolution cost. Finally, a data exchange component used in digital campus system was given to illustrate the effectiveness of above evolution methods.

A new scheme of interfusing relational database based on IIMS was proposed. With this scheme, a preliminary study of the way to build meta data for relational database was study, and a typical application case by using this scheme was given.