Concerning the problem that the interpretable mapping relationship between data features and data categories do not be revealed by general feature selection algorithms. on the basis of Gene Expression Programming (GEP),by introducing the initialization methods, mutation strategies and fitness evaluation methods,an improved Feature Selection classification algorithm based on Layer Distance for GEP(FSLDGEP) was proposed. Firstly,the selection probability was defined to initialize the individuals in the population directionally, so as to increase the number of effective individuals in the population. Secondly, the layer neighborhood of the individual was proposed, so that each individual in the population would mutate based on its layer neighborhood, and the blind and unguided problem in the process of mutation was solved。Finally, the dimension reduction rate and classification accuracy were combined as the fitness value of the individual, which changed the population evolutionary mode of single optimization goal and balanced the relationship between the above two. The 5-fold and 10-fold verifications were performed on 7 datasets, the functional mapping relationship between data features and their categories was given by the proposed algorithm, and the obtained mapping function was used for data classification. Compared with Feature Selection based on Forest Optimization Algorithm (FSFOA), feature evaluation and selection based on Neighborhood Soft Margin (NSM), Feature Selection based on Neighborhood Effective Information Ratio (FS-NEIR)and other comparison algorithms, the proposed algorithm has obtained the best results of the dimension reduction rate on Hepatitis, Wisconsin Prognostic Breast Cancer (WPBC), Sonar and Wisconsin Diagnostic Breast Cancer (WDBC) datasets, and has the best average classification accuracy on Hepatitis, Ionosphere, Musk1, WPBC, Heart-Statlog and WDBC datasets. Experimental results shows that the feasibility, effectiveness and superiority of the proposed algorithm in feature selection and classification are verified.

To solve the Split Delivery Vehicle Routing Problem (SDVRP) more reasonably, overcome the shortcoming that the traditional two-stage solution method of first route and then optimization is easy to fall into local optimization, and handle the problem that the intelligent optimization algorithm fails to integrate competition and cooperation organically in the optimization stage, an Improved Pyramid Evolution Strategy (IPES) was proposed with the shortest delivery path and the least delivery vehicles as the optimization objectives. Firstly, based on the pyramid, the encoding and decoding methods and hierarchical cooperation strategy were proposed to solve SDVRP. Secondly, according to the characteristics such as the random of genetic algorithm, high parallelism of "survival of the fittest" and self-adaption, as well as the different labor division of different layers of pyramid structure, an adaptive neighborhood operator suitable for SDVRP was designed to make the algorithm converge fast to the optimum. Finally, the optimal solution was obtained. Compared with the piecewise solving algorithm, clustering algorithm, particle swarm algorithm, artificial bee colony algorithm, taboo search algorithm,the results of four simulation experiments show that, when solving the optimal path of each case, the proposed IPES has the solution accuracy improved by at least 0.92%, 0.35%, 3.07%, 9.40% respectively, which verifies the good performance of IPES in solving SDVRP.

Entity relation extraction is a critical basic step of question answering, knowledge graph construction and information extraction in the medical field. In view of the fact that there is no open dataset available in the process of building knowledge graph specialized for cardiovascular disease, a professional training set for entity relation extraction of specialized cardiovascular disease knowledge graph was constructed by collecting some medical guidelines for cardiovascular disease and performing the corresponding professional labeling of the categories of entities and relations. Based on this dataset, firstly, Bidirectional Encoder Representation from Transformers and Convolutional Neural Network (BERT-CNN) model was proposed to realize the relation extraction in Chinese corpus. Then, the improved Bidirectional Encoder Representation from Transformers and Convolutional Neural Networks based on whole word mask (BERT(wwm)-CNN) model was proposed to improve the performance of relation extraction in Chinese corpus, according to the fact that word instead of character is the fundamental unit in Chinese. Experimental results show that, the improved BERT(wwm)-CNN model has the accuracy of 0.85, the recall of 0.80 and the F ₁ value of 0.83 on the constructed relation extraction dataset, which are better than those of the comparison models, Bidirectional Encoder Representation from Transformers and Long Short Term Memory (BERT-LSTM) and BERT-CNN, verifying the superiority of the improved BERT(wwm)-CNN.

To solve the problem that the reconstructed 3D model of a single image has high uncertainty, a network model based on depth image estimation, spherical projection mapping and 3D generative adversarial network was proposed. Firstly, the depth image of the input image was obtained by the depth estimator, which was helpful for the further analysis of the image. Secondly, the obtained depth image was converted into a 3D model by spherical projection mapping. Finally, 3D generative adversarial network was utilized to judge the authenticity of the reconstructed 3D model, so as to obtain 3D model closer to reality. In the comparison experiments with LVP algorithm which learning view priors for 3D reconstruction, the proposed model has the Intersection-over-Union (IoU) increased by 20.1% and the Charmfer Distance (CD) decreased by 13.2%. Theoretical analysis and simulation results show that the proposed model has good generalization ability in the 3D model reconstruction of a single image.

It is impractical to have a large size of training dataset in real work for neural network training, so a two-input stream generative neural network which can generate a new image with the given parameters was proposed, hence to augment the training dataset. The framework of the proposed neural network consists of a two-input steam convolution network and a deconvolution network. The two-input steam network has two convolution networks to extract features, and the deconvolution network is connected to the end. Two images with different angle were input into the convolution network to get high-level description, then an interpolation target image with a new perspectives was generated by using the deconvolution network with the above high-level description and set parameters. The experiment results on ShapeNetCore show that on the same dataset, the recognition rate of the proposed network has increased by 20% than the common network framework. This method can enlarge the size of the training dataset and is useful for multi-angle recognition.

Concerning the fact that the existing rate adaptation algorithms based on Dynamic Adaptive Streaming over HTTP (DASH) have frequent bitrate switching and low average bitrate in wireless network, a Rate Smooth Switching (RSS) algorithm based on DASH standard was proposed. Firstly, a sliding window was used by the bandwidth detection mechanism of the algorithm to sample the download speed of historical segments to calculate the bandwidth offset coefficient, the fluctuation of the bandwidth was initially determined according to the value of offset coefficient, and the situation of the fluctuation was further determined whether there was a consistent variation trend, thereby distinguishing continuous variation and short-term jitter of the bandwidth, and the bandwidth prediction value corresponding to each circumstance was calculated. Secondly, with bandwidth fluctuation, buffer occupancy and variation, bandwidth prediction value considered, the rate decision model of the algorithm adopted Fast Buffering (FB), Slow Switching (SS), Fast Rising (FR), Limited Declining (LD), Stable Holding (SH) strategies and sleeping mechanism to dynamically control the video bitrate selection process. The experimental results show that compared with fuzzy-based DASH rate adaptation algorithm and modulated throughput driven rate adaptation algorithm, the proposed algorithm can not only increase the bitrate to optimum level in the shortest time at the beginning of video playback to improve the average bitrate, but also minimize the number of bitrates' switching in the case of sudden change and frequent fluctuation of bandwidth, thus obtaining a good quality of experience for wireless video users.

In order to achieve effective integration and accurate fusion of multi-source Point of Interest (POI) data, a Mutually-Nearest Method considering Distance and Category (MNMDC) was proposed. Firstly, for spatial attributes, standardized weight algorithm was used to calculate the spatial similarity of the object to be fused, and the fusion set was obtained. Secondly, for non-spatial attributes, Jaro-Winkle algorithm was used to eliminate some objects with consistent categories by a low threshold, and exclude some objects with inconsistent categories by a high threshold. Finally, non-spatial Jaro-Winkle algorithm with distance constraint, category consistency constraint and high threshold was used to find out the missing objects in the spatial algorithm. The experimental results show that the average accuracy reaches 93.3%, compared with Combined Normal Weight and Title-similatity algorithm (COM-NWT) and the grid correction methods, the accuracy of MNMDC method in seven different groups of coincidence degree data, the average accuracy increases by 2.7 percentage points and 1.6 percentage points, the average recall increases by 2.3 and 1.4 percentage points. The MNMDC method allows more accurate fusion of POI data during actual fusion.

In order to overcome the disadvantages of Differential Evolution (DE) algorithm such as low optimization accuracy, slow convergence and poor stability, an Adaptive Differential Evolution algorithm based on Multi-Mutation strategy (ADE-MM) was proposed. Firstly, two disturbance thresholds with learning functions were used in the selection of three mutation strategies to increase the diversity of the population and expand the search scope. Then, according to the successful parameters of the last iteration, the current parameters were adjusted adaptively to improve the search accuracy and speed. Finally, vector particle pool method and central particle method were used to generate new vector particles to further improve the search effect. Tests were performed on 8 functions for 5 comparison algorithms (Random Mutation Differential Evolution (RMDE), Cross-Population Differential Evolution algorithm based on Opposition-based Learning (OLCPDE), Adaptive Differential Evolution with Optional External Archive (JADE), Self-adaptive Differential Evolution (SaDE), Modified Differential Evolution with p-best Crossover (MDE_pBX)), and each example was independently performed 30 times. The ADE-MM algorithm achieves a complete victory in the comparison of mean and variance, 5 independent wins and 3 tie wins are achieved in the 30-dimensional case; 6 independent wins and 2 tie wins are obtained in the 50-dimensional case; in 100-dimensional case, all are won independently. At the same time, in the Wilcoxon rank sum test, winning rate and time-consuming analysis, the ADE-MM algorithm also achieves excellent performance. The results show that ADE-MM algorithm has stronger global search ability, convergence and stability than other five comparison algorithms.

Aiming at the problem that serial Particle Swarm Optimization (PSO) algorithms are time-consuming to deal with big tasks, a novel shared parallel PSO (Shared-PSO) algorithm was proposed. The multi-core processing power was used to reduce time to get resolution. In order to facilitate communication of particles, a shared area was set up and a random strategy was applied to switch particles. Several serial PSO algorithms could be permitted to update particle information because of the universality of its algorithm flow. Shared-PSO was applied on the standard optimization test set CEC (Congress on Evolutionary Computation) 2014. The experiment results show that the execution time of Shared-PSO is a quarter of the serial PSO's. The proposed algorithm can effectively improve the execution efficiency of serial PSO, and expand applied range of PSO.

In order to overcome the problems of low convergence precision and easily relapsing into local optimum in Fruit fly Optimization Algorithm (FOA), by introducing the Levy flight strategy into the FOA, an improved FOA called double subgroups FOA with the characteristics of Levy flight (LFOA) was proposed. Firstly, the fruit fly group was dynamically divided into two subgroups (advanced subgroup and drawback subgroup) whose centers separately were the best individual and the worst individual in contemporary group according to its own evolutionary level. Secondly, a global search was made for drawback subgroup with the guidance of the best individual, and a finely local search was made for advanced subgroup by doing Levy flight around the best individual, so that not only both the global and local search ability balanced, but also the occasionally long distance jump of Levy flight could be used to help the fruit fly jump out of local optimum. Finally, two subgroups exchange information by updating the overall optimum and recombining the subgroups. The experiment results of 6 typical functions show that the new method has the advantages of better global searching ability, faster convergence and more precise convergence.

Concerning the problems of the low accuracy of community detection in bipartite network and the strong dependence on additional parameters, depending on the original network topology, based on the idea of spectral clustering algorithm, a new community algorithm was proposed. The proposed algorithm mined community by mapping a bipartite network to a single network, substituted resource distribution matrix for traditional similarity matrix, effectively guaranteed the information of the original network, improved the input of spectral clustering algorithm and the accuracy of community detection. The modularity function was applied to clustering analysis, and the modularity was used to measure the quality of community mining, effectively solved the problem of automatically determining the clustering number. The experimental results on the actual network and artificial network show that, compared with ant colony optimization algorithm, edge clustering coefficient algorithm etc., the proposed algorithm can not only accurately identify the number of the communities of the bipartite network, but also obtain higher quality of community partitioning without previously known parameters. The proposed algorithm can be applied to the deep understanding of bipartite network, such as recommendation and influence analysis.

Combined with virtualization technology, a realization scheme of private cloud platform based on multi-framework technology was put forward in order to improve hardware utilization of distributed cluster system and avoid the economic loss caused by the idle equipment. This scheme met the demand for resource allocation, dynamic allocation and dynamic migration, thus the bottom hardware was integrated. Aiming at unbalanced loading in the traditional virtual machine deployment method, the virtual machine deployment mechanism based on dynamic deployment allocation was proposed. According to the characteristics of virtual machine resources and the load of the current physical nodes, dynamic deployment of virtual machine was carried out. At last, private cloud computing platform with strong flexibility and good scalable performance was realized, which had been tested by Fourier finite difference pre-stack depth migration in oil exploration. The results proved the feasibility and effectiveness of the private cloud platform. By deployment test on virtual machine, the results show that the dynamic allocation decision can be used to deploy a large number of virtual machines, and keep good load balancing of private cloud platform at the same time.

In the research and application of multi-cross channel model, to maximize fault recovery of individual channel is the basis of the correctness to vote. There is some time redundancy in a task period. For a task processing in a given step, to summarize the time redundancy of pre-voting step, and assume fault-free on succedent step, then there will be a time redundancy on succedent step. The redundancy time of previous and succedent steps was counted, then a superior time window was used to do more deep recovery of fault. Based on the above ideas, a dynamic time series of multi-cross channel model was proposed, which was analyzed for deep recovery, and a backward recovery algorithm was given, which endowed more time to the fault unit, then the instantaneous fault could be eliminated to the utmost. Moreover, a monitoring logic was put forward to support the recovery algorithm. Theoretical analysis and experiments show that the backward recovery algorithm is effective to enhance the recovery rate and to reduce in the number of steps falling out. Compared with the statical recovery, the recovery rate increased by 47.49% and 72.35% respectively, and the number of out of step decreased by 58% and 85% respectively in the condition of 4 channel and 6 channel, which boosts the reliability of multi-cross channel model, especial in the condition of a large number of voting steps.

In traditional Proxy Re-Encryption (PRE), a proxy is too powerful as it has the ability to re-encrypt all delegator's ciphertexts to delegatee once the re-encryption key is obtained; And for more than one delegatees, delegator needs to generate different re-encryption key for different delegatee, which wastes a lot of resources in the calculation process. To solve these problems, an identity-based conditional proxy broadcast re-encryption was introduced. The delegator generated a re-encryption key for some specified condition during the encryption, like that the re-encryption authority of the proxy was restricted to that condition only. Moreover, the delegator's ciphertexts could be re-broadcasted to ensure the important communication and save a lot of computation and communication cost. Finally, the theoretical analysis verified the security of the scheme.

Concerning the address correctness check of parity, address irregular naming and address jumping in the geographic coding system, this paper established a conversion model of hierarchical address by the theory of finite state machine. It also created every address conversion functions in the finite state machine through the Trie tree. Then, it gave the initialization and training process of the conversion function. Through the verification of the model, the address model established in this paper can initially solve these above problems.

Software security measurement is critical to the development of software and improvement of software security. Based on the entropy and attack surface proposed by Manadhata et al. (MANADHATA P K, TAN K M C, MAXION R A, et al. An approach to measuring a system's attack surface, CMU-CS-07-146. Pittsburgh: Carnegie Mellon University, 2007; MANADHATA P K, WING J M. An attack surface metric. IEEE Transactions on Software Engineering, 2011, 37(3): 371-386), a method of software security measurement was used to assess the threat of the software's resources and provide the threat weight of these resources. Based on the threat weight, the attack surface metric was calculated for determining whether a software product is secure in design, or in what aspect the software product can be improved. The method is demonstrated in a case to show that, when using the method, the probable security threats can be found as early as possible to prevent from producing the software products that may have vulnerabilities, and the directions for the improvement of software security are pointed out clearly.

Application of the basic ant colony algorithm for anti-ship missile path planning problem has such shortcomings as slow convergence speed, long computation time, and easily falling into local optimum. Concerning these shortcomings, roulette selection strategy, elite strategy and path optimization strategy were adopted on traditional ant colony algorithm to optimize it, and the optimization algorithm was applied in anti-ship missile route planning. At the same time, by means of limiting the feasible course of anti-ship missile, the maximum search range for route planning was reduced. Simulation results show that the anti-ship missile route planning based on improved ant colony algorithm not only shortens the optimal route length but also speeds up the convergence rate of the optimal route search process.

In view of the characteristics of limited energy and dynamic change in Ad Hoc network, an identity-based group key agreement scheme was presented. The topology was in a structure composed by clusters, and allowed the synchronous execution of multi-party key agreement protocols based on pairings. The number of cluster members did not affect the key agreement, and it did not require interactivity during the key agreement. It provided the authentication and dynamics. In addition, the scheme was proved semantics secure under the Decisional Bilinear Diffie-Hellman (DBDH) problem. At last, compared with the previous schemes, the proposed scheme has advantages in terms of negotiation rounds and authentication.

Concerning the contradiction between convergence speed and convergence precision when the traditional fixed pace Least Mean Square (LMS) algorithm was used to radar clutter adaptive filter system, the paper put forward a new kind of variable-pace adaptive filter algorithm. Through combining the relevant error and the former pace to real-time update next iteration of the pace in its basic pace iterative formula, which could reach with higher convergence speed and smaller disorder, and it also could prevent the bad effect from the existing related noise. The simulation results show that, compared with the traditional fixed-pace LMS algorithm and context improved algorithm, the convergence rate, convergence accuracy and noise prevention have been greatly improved. It proves that the proposed algorithm is effective, feasible, and consistent with the theoretical analysis.

Authenticated key agreement protocol allows a group of users in an open network environment to identify each other and share a security session key. This article proposed a new scheme of ID-based authenticated multi-party key agreement based on McCullagh-Barreto scheme. Key seed was introduced to update temporary public/private key pairs. The new scheme is able to realize the authentication, improve the security, resist Reveal query attack and the key compromise impersonation attack successfully, and it has many properties such as non-key control and equal contribution.

Concerning the issue of extracting features more efficiently from a sequence of gait frames and real-time recognition, an effective human recognition method based on Mean Gait Energy Image (MGEI) was described, which utilized Kernel Principal Component Analysis (KPCA). A pre-processing technique was used to segment the moving silhouette from the walking figure. The algorithm obtained the gait quasi-periodicity through analyzing the width information of the lower limbs' gait contour edge, and the MGEI was calculated from gait period. KPCA extracted principal component with nonlinear method and described the relationship among three or more pixels of the identified images. In this paper, KPCA could make use of the high correlation between different MGEIs for feature extraction by selecting the proper kernel function, and Euclidean distance weighted by variance reciprocal was designed as the classifier. The experimental results show that the proposed approach has better recognition performance and the computation time is greatly reduced.

With the development of programming technology and theory, some problems in practice, which can not be solved by the traditional OO theory, are attracting more and more interests of researchers. A generative programming-based approach was proposed to solve such kind of problems by constructing domain-neutral models and low-coupling modules. One implementation of our proposed approach, AOP, was analyzed to demonstrate the advantages and shortcomings of our approach. Finally, a comparison between AOP-based and OO-based Observer models was conducted to show the superiority of our approach over traditional OO approaches.