With the development of mobile Internet technology， the scale of image data is getting larger and larger， and the large-scale image retrieval task has become an urgent problem. Due to the fast retrieval speed and very low storage consumption， the hashing algorithm has received extensive attention from researchers. Deep learning based hashing algorithms need a certain amount of high-quality training data to train the model to improve the retrieval performance. However， the existing hashing methods usually ignore the problem of imbalance of data categories in the dataset， which may reduce the retrieval performance. Aiming at this problem， a deep hashing retrieval algorithm based on meta-learning network was proposed， which can automatically learn the weighting function directly from the data. The weighting function is a Multi-Layer Perceptron （MLP） with only one hidden layer. Under the guidance of a small amount of unbiased meta data， the parameters of the weighting function were able to be optimized and updated simultaneously with the parameters during model training process. The updating equations of the meta-learning network parameters were able to be explained as： increasing the weights of samples which are consistent with the meta-learning data， and reducing the weights of samples which are not consistent with the meta-learning data. The impact of imbalanced data on image retrieval was able to be effectively reduced and the robustness of the model was able to be improved through the deep hashing retrieval algorithm based on meta-learning network. A large number of experiments were conducted on widely used benchmark datasets such as CIFAR-10. The results show that the mean Average Precision （mAP） of the hashing algorithm based on meta-learning network is the highest with large imbalanced rate；especially， under the condition of imbalanced ratio=200， the mAP of the proposed algorithm is 0.54 percentage points，30.93 percentage points and 48.43 percentage points higher than those of central similarity quantization algorithm， Asymmetric Deep Supervised Hashing （ADSH） algorithm and Fast Scalable Supervised Hashing （FSSH） algorithm.

This paper concerned the output tracking problem for a class of high-order stochastic nonlinear systems. Based on the backstepping control by adding a power integrator, an adaptive smooth state-feedback dynamic surface controller was proposed. The derivative of the designed adaption law was continuous by making use of the Sigmoid function. “Explosion of complexity” phenomenon in the adding a power integrator method design was eliminated by introducing a filter at each step of the recursive procedure and employing the dynamic surface control. The stability analysis was carried out by choosing an appropriate conol Lyapunov function. And its results show that the output can be regulated to the small neighborhood of the reference signal in probability. The results of a simulation example demonstrate the effectiveness of the proposed adaptive smooth state-feedback dynamic surface controller.

Concerning the safe problem of digital image information hiding, a scrambling algorithm based on bitwise layered Arnold transform was proposed. The secret image was stratified by bit-plane, taking into account the location and pixel gray transform, each bit-plane was scrambled for different times with Arnold transforma, and the pixel was cross transposed, and adjacent pixels were bitwise XOR to get a scrambling image. The experimental results show that the secret image histogram is more evenly distributed after stratification scrambling, its similarity with the white noise is around 0.962, and the scrambling image can be restored and extracted almost lossless, which improves the robustness. Compared with other scrambling algorithms, the proposed algorithm is more robust to resist attack, and improves the spatial information hiding security.

In order to deal with the problems of inefficient searching and low accuracy of Artificial Fish Swarm Algorithm （AFSA） for multimodal function optimization, an improved AFSA for multimodal function optimization was proposed. In the algorithm, the strategy of the survival of the fitter suppression was adopted, eliminating artificial fish which was situated in food with low concentration of similar artificial fish to select elite artificial fish swarm. Optimization for swarming behavior and following behavior contributed to artificial fish careful search in a new optimization trajectory to enhance its local search capacity. Modifying for preying behavior, artificial fish was avoided sinking flat position. In combination with Pattern Search Method (PSM), its local accuracy search capacity was enhanced. The simulation results indicate that the proposed algorithm has stronger global optimization and local optimization capabilities, and the search for each optimal solution accuracy has reached the ideal value, and it is able to be used for complex multimodal function optimization.