There are very few paired high and low resolution images in the real world. The traditional single image Super-Resolution （SR） methods typically use pairs of high-resolution and low-resolution images to train models， but these methods use the way of synthetizing dataset to obtain training set， which only consider bilinear downsampling as image degradation process. However， the image degradation process in the real word is complex and diverse， and traditional image super-resolution methods have poor reconstruction performance when facing real unknown degraded images. Aiming at those problems， a single image super-resolution method was proposed for real complex scenes. Firstly， high- and low-resolution images were captured by the camera with different focal lengths， and these images were registered as image pairs to form a dataset CSR（Camera Super-Resolution dataset） of various scenes. Secondly， to simulate the image degradation process in the real world as much as possible， the image degradation model was improved by the parameter randomization of degradation factors and the nonlinear combination degradation. Besides， the dataset of high- and low-resolution image pairs and the image degradation model were combined to synthetize training set. Finally， as the degradation factors were considered in the dataset， residual shrinkage network and U-Net were embedded into the benchmark model to reduce the redundant information caused by degradation factors in the feature space as much as possible. Experimental results indicate that compared with the BSRGAN （Blind Super-Resolution Generative Adversarial Network） method， under complex degradation conditions， the proposed method improves the PSNR by 0.7 dB and 0.14 dB， and improves SSIM by 0.001 and 0.031 respectively on the RealSR and CSR test sets. The proposed method has better objective indicators and visual effect than the existing methods on complex degradation datasets.

In the face of adversarial example attack， deep neural networks are vulnerable. These adversarial examples result in the misclassification of deep neural networks by adding human-imperceptible perturbations on the original images， which brings a security threat to deep neural networks. Therefore， before the deployment of deep neural networks， the adversarial attack is an important method to evaluate the robustness of models. However， under the black-box setting， the attack success rates of adversarial examples need to be improved， that is， the transferability of adversarial examples need to be increased. To address this issue， an adversarial example method based on image flipping transform， namely FT-MI-FGSM （Flipping Transformation Momentum Iterative Fast Gradient Sign Method）， was proposed. Firstly， from the perspective of data augmentation， in each iteration of the adversarial example generation process， the original input image was flipped randomly. Then， the gradient of the transformed images was calculated. Finally， the adversarial examples were generated based on this gradient， so as to alleviate the overfitting in the process of adversarial example generation and to improve the transferability of adversarial examples. In addition， the method of attacking ensemble models was used to further enhance the transferability of adversarial examples. Extensive experiments on ImageNet dataset demonstrated the effectiveness of the proposed algorithm. Compared with I-FGSM （Iterative Fast Gradient Sign Method） and MI-FGSM （Momentum I-FGSM）， the average black-box attack success rate of FT-MI-FGSM on the adversarially training networks is improved by 26.0 and 8.4 percentage points under the attacking ensemble model setting， respectively.

The memory data will change after occurring the attack behaviors， and benchmark measurement used by the traditional integrity measurement system has the problems of low detection rate and lack of flexibility. Aiming at the above problems， a memory combined feature classification method based on multiple Back Propagation （BP） neural networks was proposed. Firstly， the feature value of the memory data was extracted by Measuring Object Extraction Algorithm （MOEA）. Then， the model was trained by different BP neural networks. Finally， a BP neural network was used to collect the obtained data and calculate the safety status score of the operating system. Experimental results show that compared with the traditional integrity measurement system using benchmark measurement， the proposed method has much higher accuracy and universality， and the proposed method has a detection accuracy of 98.25%， which is higher than those of Convolutional Neural Network （CNN）， K-Nearest Neighbor （KNN） algorithm and single BP neural network， verifying the proposed method can detect attack behaviors more accurately. The proposed method has the model training time about 1/3 of the traditional single BP neural network， and also has the model training speed improved compared with similar models.

In order to improve the ability of Artificial Bee Colony (ABC) algorithm at exploitation, a new Chaos Artificial Bee Colony (CH-ABC) algorithm was proposed for continuous function optimization problems. A new chaotic local search operator was embedded in the framework of the new algorithm. The new operator, whose search radius shrinks with the evolution generation, can do the local search around the best food source. The simulation results show that: compared with those of ABC algorithm, the solution quality and the convergence speed of the new algorithm are better for Rosenbrock and the convergence speed of the new algorithm is better for Griewank and Rastrigin.

A new localization algorithm based on reputation mechanism was proposed to improve the robustness of the node positioning system in Wireless Sensor Network (WSN). This algorithm introduced a monitoring mechanism and reputation model to filter out malicious beacon nodes giving the false location information, used Beta distribution to update and integrate the reputation of the beacon nodes. Through the cluster head node, the proposed algorithm collected and judged which beacon nodes were reliable, increased the malicious beacon nodes detection rates while the positioning error was reduced. Finally, the simulation and detailed analysis prove its efficiency and robustness. The algorithm is efficient in self-positioning of sensor nodes in distributed WSN, and the localization accuracy and security are greatly improved.

To overcome the deficiency in sharing and reusing design knowledge in manufacturing industry, a strategy based on functional ontology was proposed for design knowledge-sharing. The existing product structure can be mapped to its product functions by using functional ontology, and the design principles can be represented by functional decomposition tree. First, the basic framework of functional ontology was introduced. Then, the role of the functional decomposition tree to product design was analyzed. Finally, a knowledge-sharing platform for household appliances was designed and developed based on functional ontology. It was used to verify the proposed strategy. The experimental results show that the proposed strategy can effectively realize information retrieval, sharing and reuse of design knowledge in manufacturing industry. It can also shorten product development cycles.