To solve the problems of image detail loss and unclear texture caused by interference factors such as noise， imaging technology and imaging principles in the medical Magnetic Resonance Imaging （MRI） process， a multi-receptive field generative adversarial network for medical MRI image super-resolution reconstruction was proposed. First， the multi-receptive field feature extraction block was used to obtain the global feature information of the image under different receptive fields. In order to avoid the loss of detailed texture due to too small or too large receptive fields， each set of features was divided into two groups， and one of which was used to feedback global feature information under different scales of receptive fields， and the other group was used to enrich the local detailed texture information of the next set of features； then， the multi-receptive field feature extraction block was used to construct feature fusion group， and spatial attention module was added to each feature fusion group to adequately obtain the spatial feature information of the image， reducing the loss of shallow and local features in the network， and achieving a more realistic degree in the details of the image. Secondly， the gradient map of the low-resolution image was converted into the gradient map of the high-resolution image to assist the reconstruction of the super-resolution image. Finally， the restored gradient map was integrated into the super-resolution branch to provide structural prior information for super-resolution reconstruction， which was helpful to generate high quality super-resolution images. The experimental results show that compared with the Structure-Preserving Super-Resolution with gradient guidance （SPSR） algorithm， the proposed algorithm improves the Peak Signal-to-Noise Ratio （PSNR） by 4.8%， 2.7% and 3.5% at ×2， ×3 and ×4 scales， respectively， and the reconstructed medical MRI images have richer texture details and more realistic visual effects.

Video super-resolution methods based on deep learning mainly focus on the inter-frame and intra-frame spatio-temporal relationships in the video, but previous methods have many shortcomings in the feature alignment and fusion of video frames, such as inaccurate motion information estimation and insufficient feature fusion. Aiming at these problems, a video super-resolution model based on Attention Fusion Network(AFN) was constructed with the use of the back-projection principle and the combination of multiple attention mechanisms and fusion strategies. Firstly, at the feature extraction stage, in order to deal with multiple motions between neighbor frames and reference frame, the back-projection architecture was used to obtain the error feedback of motion information. Then, a temporal, spatial and channel attention fusion module was used to perform the multi-dimensional feature mining and fusion. Finally, at the reconstruction stage, the obtained high-dimensional features were convoluted to reconstruct high-resolution video frames. By learning different weights of features within and between video frames, the correlations between video frames were fully explored, and an iterative network structure was adopted to process the extracted features gradually from coarse to fine. Experimental results on two public benchmark datasets show that AFN can effectively process videos with multiple motions and occlusions, and achieves significant improvements in quantitative indicators compared to some mainstream methods. For instance, for 4-times reconstruction task, the Peak Signal-to-Noise Ratio(PSNR) of the frame reconstructed by AFN is 13.2% higher than that of Frame Recurrent Video Super-Resolution network(FRVSR) on Vid4 dataset and 15.3% higher than that of Video Super-Resolution network using Dynamic Upsampling Filter(VSR-DUF) on SPMCS dataset.

In order to solve the Knapsack Problem with a single Continuous variable (KPC) efficiently, a novel S-shape transfer function based on Gauss error function was proposed, and a new approach of transforming a real vector into a 0-1 vector by using the proposed transfer function was given, thereby a New Binary Particle Swarm Optimization algorithm (NBPSO) was proposed. Then, based on the second mathematical model of KPC and the combination of NBPSO and the effective algorithm to deal with the infeasible solutions of KPC, a new approach to solve KPC was proposed. For validating the performance of NBPSO in solving KPS, NBPSO was utilized to solve four kinds of large-scale KPC instances, and the obtained calculation results were compared with those of Binary Particle Swarm Optimization algorithms (BPSOs) based on other S and V-shape transfer functions, Single-population Binary Differential Evolution with Hybrid encoding (S-HBDE), Bi-population Binary Differential Evolution with Hybrid encoding (B-HBDE) and Binary Particle Swarm Optimization algorithm (BPSO). The comparison results show that NBPSO is superior to the comparison algorithms in average calculation result and stability, illustrating that NBPSO has the performance better than other algorithms.

On-line detection of fabric defects is a major problem faced by textile industry. Aiming at the problems such as high false positive rate, high false negative rate and low real-time in the existing detection of fabric defects, an on-line detection algorithm for fabric defects based on deep learning was proposed. Firstly, based on GoogLeNet network architecture, and referring to classical algorithm of other classification models, a fabric defect classification model suitable for actual production environment was constructed. Secondly, a fabric defect database was set up by using different kinds of fabric pictures marked by quality inspectors, and the database was used to train the fabric defect classification model. Finally, the images collected by high-definition camera on fabric inspection machine were segmented, and the segmented small images were sent to the trained classification model in batches to realize the classification of each small image. Thereby the defects were detected and their positions were determined. The model was validated on a fabric defect database. The experimental results show that the average test time of each small picture is 0.37 ms by this proposed model, which is 67% lower than that by GoogLeNet, 93% lower than that by ResNet-50, and the accuracy of the proposed model is 99.99% on test set, which shows that its accuracy and real-time performance meet actual industrial demands.

In order to improve the recognition ability for online behavior continuous sequences and enhance the stability of behavior recognition model, a novel online behavior recognition method based on Probabilistic Latent-Dynamic Conditional Random Field (PLDCRF) from surveillance video was proposed. Firstly, the Space-Time Interest Point (STIP) was used to extract behavior features. Then, the PLDCRF model was applied to identify the activity state of indoor human body. The proposed PLDCRF model incorporates the hidden state variables and can construct the substructure of gesture sequences. It can select the dynamic features of gesture and mark the unsegmented sequences directly. At the same time, it can also mark the conversion process between behaviors correctly to improve the effect of behavior recognition greatly. Compared with Hidden Conditional Random Field (HCRF), Latent-Dynamic Conditional Random Field (LDCRF) and Latent-Dynamic Conditional Neural Field (LDCNF), the recognition rate comparison results of 10 different behaviors show that, the proposed PLDCRF model has a stronger recognition ability for continuous behavior sequences and better stability.

A large-scale Discount {0-1} Knapsack Problem (D{0-1} KP) is difficult to solve with the deterministic algorithms, thus a differential crow search algorithm based on Lévy flight named LDECSA was proposed. Firstly, the coding problem about the second mathematical model of D{0-1} KP was solved by using mixed coding. Secondly, a New greedy Repair and Optimization Algorithm (NROA) was used to deal with the infeasible solution. Thirdly, in order to avoid the problems of local optimum and slow convergence, Lévy flight and differential strategy were introduced. Finally, the reasonable value of awareness probability and flight length were determined through experiments, the differential strategy was also chosen. The experimental results on four types of large-scale D{0-1} KP show that LDECSA is very suitable for solving large-scale D{0-1} KP with very satisfactory approximate solution.

In Discount {0-1} Knapsack Problem (D{0-1}KP), the weight coefficients and the value coefficients in a large range, are difficult to solve by deterministic algorithms. To solve this problem, a Chaotic Crow Search Algorithm based on Differential Evolution strategy (DECCSA) was proposed. Firstly, the initial crow population was generated by chaotic mapping. Secondly, mixed coding and Greedy Repair and Optimization Strategy (GROS) were used to solve the coding problem of D{0-1}KP. Finally, Difference Evolution (DE) strategy was introduced to improve the convergence rate of the algorithm. The experimental results on four large-scale D{0-1}KP instances show that DECCSA is better than Genetic Algorithm (GA), bacterial foraging optimization algorithm, and mutated bat algorithm, and it can get the optimal solution or approximate optimal solution. It's very suitable for solving D{0-1}KP.

Since the deterministic algorithms are difficult to solve the Discounted {0-1} Knapsack Problem (D{0-1}KP) with large-scale and wide data range, a Mutated Double codes Binary Bat Algorithm (MDBBA) was proposed. Firstly, the coding problem of D{0-1} KP was solved by double coding. Secondly, the Greedy Repair and Optimization Algorithm (GROA) was applied to the individual fitness calculation of bats, and the algorithm was quickly and effectively solved. Then, the mutation strategy in Differential Evolution (DE) was selected to improve the global optimization ability. Finally, Lévy flight was carried out by the bat individual according to certain probability to enhance the ability of the algorithm to explore and jump out of local extrema. Simulation was tested on four large-scale instances. The result shows that MDBBA is very suitable for solving large-scale D {0-1} KP, which has better optimal value and mean value than FirEGA (First Genetic Algorithm) algorithm and Double Binary Bat Algorithm (DBBA), and MDBBA converges significantly faster than DBBA.

In order to solve the problem that large amounts of supervised information was needed to achieve satisfactory performance, owing to the implementation of the semi-supervised community detection methods based on Non-negative Matrix Factorization (NMF) which selected prior information randomly, an Active Link Selection algorithm for semi-supervised community detection based on Graph regularization NMF (ALS_GNMF) was proposed. Firstly, in the iteration framework, the most uncertain and informative links were selected actively as prior information links. Secondly, the must-link constraints of these links, which generated the prior matrix, were added to enhance the connections in a certain community. At the same time, the cannot-link constraints were added, which modified the adjacency matrix, to weaken the connections between communities. Finally, the prior matrix was used as a graph regularization term to incorporate into the optimization objective function of NMF. And combining with network topology information, higher community discovery accuracy and robustness were achieved with less prior information. At the same prior ratio on both synthetic and real networks, experimental results demonstrate that the ALS_GNMF algorithm significantly outperformes the existing semi-supervised NMF algorithms in terms of efficiency, and it is stable especially on networks with unclear structure.

Focusing on the issue that the significant localized characteristics of the influence of skull on the facial surface shape are not fully considered in the existing joint statistical craniofacial reconstruction methods based on Principal Component Analysis (PCA) modeling, which leads to the inadequate description ability of the craniofacial morphological correlation models, by employing these methods and describing the morphological relationship between skull and face, a new craniofacial reconstruction method based on a Partial Least Squares Regression (PLSR) model of local craniofacial morphological correlation was proposed. Firstly, the defects of the joint statistical shape model based on PCA with skull and face as a whole and the advantages of the local morphological correlation model based on PLSR were deeply analyzed. Secondly, by introducing PLSR into the modeling of craniofacial morphological correlation, and based on craniofacial 3D surface model, whose physiological consistent correspondence was established, and classified according to forensic anthropology knowledge, the PLSR coordinate calculation model for each vertex of facial surface was constructed, with those closely related vertex set on skull as its independent variables. Thirdly, with the coordinates of the unknown skull surface model as input values of the coordinate calculation model, the coordinate of each vertex of the predicted face model was acquired, from which the predicted face could be reconstructed, and the concrete procedure of the new reconstruction method was elaborated. Finally, several craniofacial reconstruction experimentations by applying the new reconstruction method based on PLSR were given, and the new reconstruction method was comparatively analyzed and evaluated by the indicators including effectiveness of reconstruction and absolute error. The experimental results show that the new reconstruction method significantly improves the accuracy of craniofacial reconstruction.

In Mobile Ad Hoc Network (MANET), the movements of nodes are liable to cause link failures, while the local repair in the classic Ad Hoc On-demand Distance Vector (AODV) routing algorithm is performed only after the link breaks, which has some limitations and may result in the cached data packet loss when the repair process fails or goes on too slowly. In order to solve this problem, an optimized AODV routing algorithm named ARB-AODV was proposed, which can avoid route breaks. In ARB-AODV algorithm, the link which seemed to break was predicted and the stability degrees of the nodes' neighbors were calculated. Then the node with the highest stability was added to the weak link to eliminate the edge effect of nodes and avoid route breaks. Experiments were conducted on NS-2 platform using Random Waypoint Mobility Model (RWM) and Constant Bit Rate (CBR) data. When the nodes moved at a speed higher than 10m/s, the packet delivery ratio of ARB-AODV algorithm maintained at 80% or even higher, the average end-to-end delay declined up to 40% and the overhead of normalized routing declined up to 15% compared with AODV. The simulation results show that ARB-AODV outperforms AODV, and it can effectively improve network performance.

Incomplete utilization of polarimetric information is one of the important factors that impact the result of polarimetric Synthetic Aperture Radar (SAR) image classification. In order to achieve the comprehensive utilization of polarimetric information, quotient space granularity composition theory, combined with multiple classifiers to construct different quotient space, was applied in classification of polarimetric SAR. Firstly, using different polarization decomposition method to get different characteristics, and based on these characteristics, setting different Support Vector Machine (SVM) classifiers to classify the image. Secondly, integrating these quotient spaces based on granularity composition theory to get more fine-grained result in order to achieve the upgrading of the classification accuracy. Finally, an experiment for AIRSAR image was given. The result shows the misclassification of targets is inhibited significantly and the classification accuracy of each class is improved.

The Firefly Algorithm (FA) has a few disadvantages in the global searching, including slow convergence speed, low solving precision and high possibility of being trapped in local optimum. A FA based on chaotic dynamic population was proposed. Firstly, chaotic sequence generated by cube map was used to initiate individual position, which strengthened the diversity of global searching; secondly, through dynamic monitoring of population, whenever the algorithm meets the preset condition, the new population individuals were generated using chaotic sequences, thus effectively improving convergence speed; thirdly, a Gaussian disturbance would be given on the global optimum of each generation, thus the algorithm could effectively jump out of local minima. Based on six complex test functions, the test results show that chaos-based dynamic population FA improves the capacity of global searching optimal solution, convergence speed and computational precision of solution.

The evolutionary mode of Differential Evolution (DE) was analyzed, and modified differentiation operator and selection operator with self-accelerated characteristic were proposed. Then the Self-Accelerated and Variable Neighbourhood searching of Differential Evolution (SAVNDE) algorithm was advanced using these new operators and variable neighbourhood search which improved the local search ability of algorithm. On the basis of the three evolution models, the simulation results on five classical benchmark functions show that SAVNDE has the same convergence rate of DE, and can achieve more optimization results in shorter time.

That the individuals search relevant objects from the environment may cause high time complexity during the crowd simulation. If the crowd should be simulated in real-time, the time complexity of the model needs reducing and the computing capability of the simulation platform needs enhancing. In this paper, the Biods model was studied as a typical case and a solution of how to parallelize and optimize the real-time huge crowd simulation based on Compute Unified Device Architecture (CUDA) was presented. Each individual was correspondent to a logical Graphic Processing Unit (GPU) thread. By discretizing simulation environment, the efficiency of searching the relevant individuals was improved. The individual information was organized into an array with the spatial locality by parallel radix sort in order to improve the utilization of the GPU memory bandwidth. The experiment verifies the solution presented here has improved number of simulation individuals up to about 7.3 times as CPU solution.

For solving combinational optimization problems, a Binary Harmony Search Algorithm (BHSA) based on three discrete operators of Harmony Search Algorithm （HSA）was proposed. Then, BHSA was used to solve the famous k-SAT problem and 0-1 knapsack problem. The numeral results of BHSA, Binary Particle Swarm Optimization （BPSO） and Genetic Algorithm (GA) show that the BHSA is feasible and highly efficient.

Owing to the problem that the motion can not be adjusted in the motion control method based on motion capture currently, the authors proposed a technique for adjusting motion based on time. Firstly, the time parameters were obtained by analyzing the space-time characteristics of the basic motions of character model, and then the real-time goal position of the character was calculated according to the controlled information and environment constraints. Subsequently, the parameters of joints with the space-time characteristic of the basic motions were calculated, so that the character could make new motions when it was necessary. Finally, the simulation results show that the character is able to adjust his motion when he turns around and climbs ladder with Unity by loading character model.

In this paper, an adaptive color image enhancement method was proposed: Firstly, color image was transformed from RGB to HSV color space and the H component was kept invariable, while the illumination component of brightness image could be estimated through Adaptive Bidimensional Empirical Mode Decomposition (ABEMD); Secondly, reflection component was figured out by the method of center/surround Retinex algorithm, and the illumination and reflection components were controlled through Gamma emendation and Weber's law and processed with weighted average method; Thirdly, the S component was adjusted adaptively based on characteristics of the whole image, and then image was transformed back to RGB color space. The method could be evaluated by subjective effects and objective image quality assessment, and the experiment results show that the proposed algorithm is better in mean value, square variation, entropy and resolution than MSR algorithm and Meylan's algorithm.