For the problems that the performance of the nearest neighbor classification algorithm is greatly affected by the adopted similarity or distance measuring method， and it is difficult to select the optimal similarity or distance measuring method， with multi-similarity method adopted， a K-Nearest Neighbor algorithm with Ordered Pairs of Normalized real numbers （OPNs-KNN） was proposed. Firstly， the new mathematical theory of Ordered Pair of Normalized real numbers （OPN） was introduced in machine learning. And all the samples in the training and test sets were converted into OPNs by multiple similarity or distance measuring methods， so that different similarity information was included in each OPN. Then， the improved nearest neighbor algorithm was used to classify the OPNs， so that different similarity or distance measuring methods were able to be mixed and complemented to improve the classification performance. Experimental results show that compared with 6 improved nearest neighbor classification algorithms， such as distance-Weighted K-Nearest-Neighbor rule （WKNN） rule on Iris， seeds， and other datasets， OPNs-KNN has the classification accuracy improved by 0.29 to 15.28 percentage points， which proves that the performance of classification can be improved greatly by the proposed algorithm.

Achieving seal segmentation precisely， it is benefit to intelligent application of the Republican archives. Concerning the problems of serious printing invasion and excessive noise， a network for seal segmentation was proposed， namely U-Net for Seal （UNet-S）. Based on the encoder-decoder framework and skip connections of U-Net， this proposed network was improved from three aspects. Firstly， multi-scale residual module was employed to replace the original convolution layer of U-Net. In this way， the problems such as network degradation and gradient explosion were avoided， while multi-scale features were extracted effectively by UNet-S. Next improvement was using Depthwise Separable Convolution （DSConv） to replace the ordinary convolution in the multi-scale residual module， thereby greatly reducing the number of network parameters. Thirdly， Binary Cross Entropy Dice Loss （BCEDiceLoss） was used and weight factors were determined by experimental results to solve the data imbalance problem of archives of the Republic of China. Experimental results show that compared with U-Net， DeepLab v2 and other networks， the Dice Similarity Coefficient （DSC）， mean Intersection over Union （mIoU） and Mean Pixel Accuracy （MPA） of UNet-S have achieved the best results， which have increased by 17.38%， 32.68% and 0.6% at most， and the number of parameters have decreased by 76.64% at most. It can be seen that UNet-S has good segmentation effect in the dataset of Republican archives.

Most of the Multi-objective Optimization Problems （MOP） in real life are Dynamic Multi-objective Optimization Problems （DMOP）， and the objective function， constraint conditions and decision variables of such problems may change with time， which requires the algorithm to quickly adapt to the new environment after the environment changes， and guarantee the diversity of Pareto solution sets while converging to the new Pareto frontier quickly. To solve the problem， an Adaptive Prediction Dynamic Multi-objective Optimization Algorithm based on New Evaluation Index （NEI-APDMOA） was proposed. Firstly， a new evaluation index better than crowding was proposed in the process of population non-dominated sorting， and the convergence speed and population diversity were balanced in different stages， so as to make the convergence process of population more reasonable. Secondly， a factor that can judge the strength of environmental changes was proposed， thereby providing valuable information for the prediction stage and guiding the population to better adapt to environmental changes. Finally， three more reasonable prediction strategies were matched according to environmental change factor， so that the population was able to respond to environmental changes quickly. NEI-APDMOA， DNSGA-Ⅱ-A （Dynamic Non-dominated Sorting Genetic Algorithm-Ⅱ-A）， DNSGA-Ⅱ-B （Dynamic Non-dominated Sorting Genetic Algorithm-Ⅱ-B） and PPS （Population Prediction Strategy） algorithms were compared on nine standard dynamic test functions. Experimental results show that NEI-APDMOA achieves the best average Inverted Generational Distance （IGD） value， average SPacing （SP） value and average Generational Distance （GD） value on nine， four and eight test functions respectively， and can respond to environmental changes faster.

In order to solve the problems of low detection efficiency and poor detection precision caused by various surface defects and numerous small defects of section steel， a detection algorithm for surface defects of section steel， namely Steel-YOLOv3， was proposed on the basis of the deformable convolution and multi-scale dense feature pyramid. Firstly， the deformable convolution was used to replace the convolutional layers of part of the residual units in Darknet53 network， which strengthened the feature learning ability of feature extraction network for multi-type defects on the surface of section steel. Secondly， a multi-scale dense feature pyramid module was designed， which means that a shallower prediction scale was added to the 3 prediction scales of the original YOLOv3 algorithm and the multi-scale feature maps were connected across layers， thereby enhancing the ability to characterize dense small defects. Finally， according to the defect size distribution characteristics of section steel， the K-means dimension clustering method was used to optimize the scales of anchor boxes， and the anchor boxes were evenly distributed to 4 corresponding prediction scales. Experimental results show that Steel-YOLOv3 algorithm has a detection mean Average Precision （mAP） of 89.24%， which is improved by 3.51%， 26.46%， 12.63% and 5.71% compared with those of Faster Region-based Convolutional Neural Network （Faster R-CNN）， Single Shot multibox Detector （SSD）， YOLOv3 and YOLOv5 algorithms respectively. And the detection rate of tiny spalling defects is significantly improved by the proposed algorithm. Moreover， the proposed algorithm can detect 25.62 images per second， which means the requirement of real-time detection can be met and the algorithm can be applied to the online detection for the surface defects of section steel.

In machine learning， data quality has a far-reaching impact on the accuracy of system prediction. Due to the difficulty of obtaining information and the subjective and limited cognition of human， experts cannot accurately mark all samples. And some probability sampling methods proposed in resent years fail to avoid the problem of unreasonable and subjective sample division by human. To solve this problem， a label noise filtering method based on Dynamic Probability Sampling （DPS） was proposed， which fully considered the differences between samples of each dataset. By counting the frequency of built-in confidence distribution in each interval and analyzing the trend of information entropy of built-in confidence distribution in each interval， the reasonable threshold was determined. Fourteen datasets were selected from UCI classic datasets， and the proposed algorithm was compared with Random Forest （RF）， High Agreement Random Forest Filter （HARF）， Majority Vote Filter （MVF） and Local Probability Sampling （LPS） methods. Experimental results show that the proposed method shows high ability on both label noise recognition and classification generalization.

Traditional methods of generating digital camouflages cannot generate digital camouflages based on the background information in real time. In order to cope with this problem， a digital camouflage generation method based on cycle-consistent adversarial network was proposed. Firstly， the image features were extracted by using densely connected convolutional network， and the learned digital camouflage features were mapped into the background image. Secondly， the color retention loss was added to improve the quality of generated digital camouflages， ensuring that the generated digital camouflages were consistent with the surrounding background colors. Finally， a self-normalized neural network was added to the discriminator to improve the robustness of the model against noise. For the lack of objective evaluation criteria for digital camouflages， the edge detection algorithm and the Structural SIMilarity （SSIM） algorithm were used to evaluate the camouflage effects of the generated digital camouflages. Experimental results show that the SSIM score of the digital camouflage generated by the proposed method on the self-made datasets is reduced by more than 30% compared with the existing algorithms， verifying the effectiveness of the proposed method in the digital camouflage generation task.

Tumor in brain Magnetic Resonance Imaging (MRI) images is often difficult to be segmented accurately due to noise, gray inhomogeneity, complex structrue, fuzzy and discontinuous boundaries. For the purpose of getting precise segmentation with less position bias, a new method based on Fuzzy C-Means (FCM) clustering and morphological multi-scale modification was proposed. Firstly, a control parameter was introduced to distinguish noise points, edge points and regional interior points in neighborhood, and the function relationship between pixels and the sizes of structure elements was established by combining with spatial information. Then, different pixels were modified with different-sized structure elements using morphological closing operation. Thus most local minimums caused by irregular details and noises were removed, while region contours positions corresponding to the target area were largely unchanged. Finally, FCM clustering algorithm was employed to implement segmentation on the basis of multi-scale modified image, which avoids the local optimization, misclassification and region contours position bias, while remaining accurate positioning of contour area. Compared with the standard FCM, Kernel FCM (KFCM), Genetic FCM (GFCM), Fuzzy Local Information C-Means (FLICM) and expert hand sketch, the experimental results show that the suggested method can achieve more accurate segmentation result, owing to its lower over-segmentation and under-segmentation, as well as higher similarity index compared with the standard segmentation.

In order to reduce the time complexity of biological networks alignment, an implementation for large scale biological networks alignment based on Scalable Protein Interaction Network Alignment (SPINAL) in Message Passing Interface (MPI) program was proposed. Based on MPI, the SPINAL algorithm combined with parallelization method was applied into this approach. Instead of serial algorithm, parallel sorting algorithm was used in multi-core environment. Load balancing strategy was chosen to assign tasks reasonably. In the processing of large scale biological networks alignment, the experiment shows that, compared with the algorithm without parallelization and load balancing strategy, this proposed algorithm can reduce the runtime and improve computation efficiency effectively.

A general construction method of optimal frequency hopping sequence sets with no-hit zone was proposed in this paper, which included several known constructions as special cases. The general method was obtained by performing the column permutation on the signal matrix. In the proposed construction, the length, the number of the sequences and the length of the no-hit zone could be changed flexibly. Furthermore, the available concrete construction methods were abundant. Some properties of the frequency hopping sequence sets were influenced by the concrete construction methods and the parameters. The parameters of frequency hopping sequence sets obtained by this method reach the theoretical bound; hence they are classes of optimal frequency hopping sequence sets with no-hit zone.

According to the gray distribution characteristics of microaneurysms, a new microaneurysm detection algorithm was proposed. First, by multi-scale matched filtering, candidate microaneurysm lesions were picked out as seed points. And region growing technology was applied to segment the lesion areas. Then the features of the lesion areas were extracted. Finally the Adaboost neural network ensemble was designed to distinguish the real microaneurysm from all of the candidate lesions. The proposed method was tested on public ROC database. The experimental results show that the average detection accuracy is 40.92%, which is better than that of previous doublering filtering and morphological methods.

Energy efficiency is an important metric in wireless Ad Hoc networks. Until now, there is no universally accepted definition of energy efficiency, and the related results are asymptotic or qualitative, which has limited its applicability. By regarding a bit as a physical particle with one unit of mass, the authors assumed that a bit in transmission possessed a certain amount of kinetic information energy. As a result, the energy efficiency of wireless transmission was defined as the ratio of information energy to physical energy. A quantitative analysis on energy efficiency in wireless transmission was carried out and meaningful results were obtained. It is concluded that the energy efficiency changes non-monotonously with the transmission power, and there is an optimal transmission power, with which the maximum energy efficiency will be acquired. The optimal transmission power was given to help the protocol design. Based on the theoretical results, a practical solution for transmission power control was proposed, and an extensive experimental study of it was given on the CC2420 radio. The results show the effectiveness of the proposed transmission power control scheme.

In view of the limitation of the traditional Transmission Control Protocol (TCP) used in the heterogeneous network, a network cognitive model based on fuzzy comprehensive evaluation was proposed. This model, by building the membership functions and different dynamic weight distribution under the different network environment, distinguished the wireless error loss from congestion loss according to fuzzy comprehensive evaluation. The simulation results show: compared with the traditional TCP, under different network conditions, the model can more accurately distinguish the wireless error loss from congestion loss, and improve the TCP throughput and network performance.

The conventional light radiation intensity estimation of K-Nearest Neighbor (K-NN) algorithm can only be improved by increasing the density of photons. The authors replaced the K-NN algorithm with Variable Kernel (VK) method which inherited the properties of smoothing kernel, and estimated the light radiation intensity for different surface point adaptively by calculating the ratio of the assigned radius of each photon to the distance between the photon and the surface point. The experimental results show that the VK algorithm is faster than K-NN algorithm and it can improve image quality without shooting a great number of photos.

In the Case-Based Reasoning (CBR) case retrieving and matching, different cases are usually composed by different features. But most of the traditional CBR engines adopt fixed feature weights mode, which makes matching rate of whole system very low. To solve this problem, this paper proposed a CBR engine model with variable feature weights and brought interactive mode into feature weights calculating module. It calculated subjective weight based on group decisionmaking theory and proposed an adjustment method which used differences between a single expert and his group. It used similarity rough set theory to calculate objective weight in order to make results calculating more objective and accurate. At last, it designed composite weights adjustment algorithm which calculated the distance between the subjective weight and objective weight, considered the deviation degree of those two weights, then deduced weights adjustment coefficient, and get the final weight adjustment results. The calculation example and simulation analysis of network attack cases validate the effectiveness of the proposed method and prove this method has much better performance in different performance indexes.

Current three-dimensional reconstruction algorithms of the computer vision field have limitations that they need to deploy and calibrate the cameras around the scene, or they need a structure light. Furthermore, these algorithms are not robust enough to every object. A new kind of four camera array reconstruction algorithms which properly combined the image registration algorithm and the camera array method was proposed to solve the robustness and limitation problems. It does not need calibration or structure light support. The experiments based on complex indoor sense with shadows demonstrate that this method is able to do dense point cloud reconstruction robustly and can overcome the shortcomings of current reconstruction algorithms.

An improved algorithm for image restoration was proposed based on Primal-Dual Hybrid Gradient Descent (PDHGD) method. The preferences have a great impact on convergence rate of the known algorithm. The form was changed by introducing new variable, and the elements of the dual vector of the primal-dual hybrid model were separated, and then step-size was replaced by using parameter matrices. The numerical experiments show that the improved algorithm has advantage on choosing parameters compared to the known algorithm, and the iterative number and CPU' time nearly declined by 50%, and at the same time, the improved algorithm has exactly the same effect on image restoration.

The existing Enterprise Service Bus （ESB） products can hardly fulfill enterprises' changeable requirements of business processes due to their absence or inadequacy of manageability, flexibility and openness. Importing work flow technology, an innovative ESB design scheme was proposed with component model as its basis, service chain as the design, deployment and management unit of ESB applications, and event-driven asynchronous messaging as the communication mechanism. Our work has been applied in the NPUESB system. Results prove that the design can not only effectively realize enterprise application integration, but also efficiently implement and manage ESB applications and deal with changeable enterprise business processes, meanwhile possessing good openness and scalability properties.