With the emergence of many computation-intensive applications, mobile devices cannot meet user requirements such as delay and energy consumption due to their limited computing capabilities. Mobile Edge Computing (MEC) offloads user task computing to the MEC server through a wireless channel to significantly reduce the response delay and energy consumption of tasks. Concerning the problem of multi-user task offloading, a Multi-User Task Offloading strategy based on Stable Allocation (MUTOSA) was proposed to minimize energy consumption while ensuring the user delay requirement. Firstly, based on the comprehensive consideration of delay and energy consumption, the problem of multi-user task offloading in the independent task scenario was modeled. Then, based on the idea of delayed reception in the stable allocation of game theory, an adjustment strategy was proposed. Finally, the problem of multi-user task unloading was solved through continuous iteration. Experimental results show that, compared with the benchmark strategy and heuristic strategy, the proposed strategy can meet the delay requirements of more users, increase user satisfaction by about 10% on average, and reduce the total energy consumption of user devices by about 50%. It shows that the proposed strategy can effectively reduce energy consumption with ensuring the user delay requirement, and can effectively improve the user experience for delay-sensitive applications.

In the framework of traditional knowledge distillation， the teacher network transfers all of its own knowledge to the student network， and there are almost no researches on the transfer of partial knowledge or specific knowledge. Considering that the industrial field has the characteristics of single scene and small number of classifications， the evaluation of recognition performance of neural network models in specific categories need to be focused on. Based on the attention feature transfer distillation algorithm， three specific knowledge learning algorithms were proposed to improve the classification performance of student networks in specific categories. Firstly， the training dataset was filtered for specific classes to exclude other non-specific classes of training data. On this basis， other non-specific classes were treated as background and the background knowledge was suppressed in the distillation process， so as to further reduce the impact of other irrelevant knowledge on specific classes of knowledge. Finally， the network structure was changed， that is the background knowledge was suppressed only at the high-level of the network， and the learning of basic graphic features was retained at the bottom of the network. Experimental results show that the student network trained by a specific knowledge learning algorithm can be as good as or even has better classification performance than a teacher network whose parameter scale is six times of that of the student network in specific category classification.

The histopathological image is the gold standard for identifying breast cancer, so that the automatic and accurate classification of breast cancer histopathological images is of great clinical application. In order to improve the classification accuracy of breast cancer histopathology images and thus meet the needs of clinical applications, a high-precision breast classification method that incorporates spatial and channel features was proposed. In the method, the histopathological images were processed by using color normalization and the dataset was expanded by using data enhancement, and the spatial feature information and channel feature information of the histopathological images were fused based on the Convolutional Neural Network (CNN) models DenseNet and Squeeze-and-Excitation Network (SENet). Three different BCSCNet (Breast Classification fusing Spatial and Channel features Network) models, BCSCNetⅠ, BCSCNetⅡ and BCSCNetⅢ, were designed according to the insertion position and the number of Squeeze-and-Excitation (SE) modules. The experiments were carried out on the breast cancer histopathology image dataset (BreaKHis), and through experimental comparison, it was firstly verified that color normalization and data enhancement of the images were able to improve the classification accuracy of breast canner, and then among the three designed breast canner classification models, the one with the highest precision was found to be BCSCNetⅢ. Experimental results showed that BCSCNetⅢ had the accuracy of binary classification ranged from 99.05% to 99.89%, which was improved by 0.42 percentage points compared with Breast cancer Histopathology image Classification Network (BHCNet); and the accuracy of multi-class classification ranged from 93.06% to 95.72%, which was improved by 2.41 percentage points compared with BHCNet. It proves that BCSCNet can accurately classify breast cancer histopathological images and provide reliable theoretical support for computer-aided breast cancer diagnosis.

A new feature selection algorithm using forest optimization algorithm was proposed, which aimed at solving the problems of the traditional feature selection using forest optimization algorithm in the stages of initialization, candidate forest generation and updating. In the algorithm, Pearson correlation coefficient and L₁ regularization method were used to replace the random initialization strategy in the initialization stage, the methods of separating good and bad trees and fulfilling the difference were used to solve the problems of incompletion of good and bad trees in the candidate forest generation stage, and trees having the same precision but different dimension with the optimal tree were added to the forest in the updating stage. In the experiments, with the same experimental data and experimental parameters, the proposed algorithm and the traditional feature selection using forest optimization algorithm were used to test the small, medium and large dimension data respectively. The experimental results show that the proposed algorithm is better than the traditional feature selection using forest optimization algorithm in the classification performance and dimension reduction ability on two medium and two large dimension data. The experimental results prove the effectiveness of the proposed algorithm in solving feature selection problems.

Aiming at the difficulty of unsupervised feature learning on defect vibration data of train running part, a method based on Compressed Sensing and Deep Wavelet Neural Network (CS-DWNN) was proposed. Firstly, the collected vibration data of train running part were compressed and sampled by Gauss random matrix. Secondly, a DWNN based on improved Wavelet Auto-Encoder (WAE) was constructed, and the compressed data were directly input into the network for automatic feature extraction layer by layer. Finally, the multi-layer features learned by DWNN were used to train multiple Deep Support Vector Machines (DSVMs) and Deep Forest (DF) classifiers respectively, and the recognition results were integrated. In this method DWNN was employed to automatically mine hidden fault information from compressed data, which was less affected by prior knowledge and subjective influence, and complicated artificial feature extraction process was avoided. The experimental results show that the CS-DWNN method achieves an average diagnostic accuracy of 99.16%, and can effectively identify three common faults in train running part. The fault recognition ability of the proposed method is superior to traditional methods such as Artificial Neural Network (ANN), Support Vector Machine (SVM) and deep learning models such as Deep Belief Network (DBN), Stack De-noised Auto-Encoder (SDAE).

Classical regression algorithms for data set analysis of multiple models have the defects of long calculating time and low detecting accuracy of models. Therefore, a heuristic robust regression analysis method was proposed. This method mimicked the clustering principle of immune system. The B cell network was taken as classifier of data set and memory of model set. Conformity between data and model was used as the classification criteria, which improved the accuracy of the data classification. The extraction process of model set was divided into a parallel iterative trial including clustering, regressing and clustering again, by which the solution of model set was gradually approximated to. The simulation results show that the proposed algorithm needs obviously less calculating time and it has higher detecting accuracy of models than classical ones. According to the results of the eight-model data set analysis in this paper, among the classical algorithms, the best algorithm is the successive extraction algorithm based on Random Sample Consensus (RANSAC). Its mean model detecting accuracy is 90.37% and the calculating time is 53.3947s. The detecting accuracy of those classical algorithms which calculating time is below 0.5s is bellow 1%. By the contrary, the proposed algorithm needs only 0.5094s and its detecting accuracy is 98.25%.

Concerning the uncertainty of pure time delay system with disturbance such as steel temperature control, an evolutionary computation way based on immune feedback control was applied to Smith predictor. The way was based on the autoregressive moving average model and rolling horizon optimization by using immune clone selection, which avoided solving the Diophantine equations. It can adjust time-delay automatically and conduct a feed-forward compensation to optimize feedback error. The simulation result shows the effectiveness of the method, and shows it has a very good adaptability for interference and system modeling error. The application to steel temperature control has illustrated its excellent control effect.

Aim to balance the problem of global optimal and local optimal in multi-modal function, an improved quantum genetic algorithm with immune operator is introduced. It carries both the quality of celerity of common quantum genetic algorithm and the quality of global searching of immune clone algorithm. It not only overcomes the flaw of the common quantum genetic algorithm which relapses into local optimum result but also avoids the flaw of the common immune clone algorithm which computes slowly. With the experiment of the global optimization of the multimodal function, the result indicates that this algorithm can settle the problem of searching the global optimization result in given range with faster speed and better result ,and it also shows us that it gets more robust stability compared to the common genetic algorithm and the common quantum genetic algorithm.

The data scheduling algorithm in data-driven overlay network is identified as one of the most influential factors affecting system performance of P2P streaming media. Considering the fact that the current algorithm fails to make use of the data blocks and nodes efficiently, which leads to low-quality streaming media services, a new method for data scheduling algorithm was proposed in this study based on both priority of data blocks and capacity of nodes. This algorithm could get priority value according to the scarcity and urgency of blocks. It also could get the capacity of the nodes according to uplink-bandwidths, time-online and relative distance of the nodes. With the utilization of this algorithm, higher priority blocks and higher capacity nodes were requested, and the waiting time to play was decreased. The simulations in the OPNET network indicate that the algorithm can efficiently reduce start-up delay of streaming media playing system and the server load.

In background subtraction, it is challenging to detect foreground objects in the presence of complex background motions including waving trees, rippling water, illumination changes, etc. In order to solve this problem, a codebook-based object detection algorithm is proposed in the paper. Given that in actual scene the change of background reflects on brightness, color space is transformed from RGB space to YUV space for video sequences. Then the algorithm establishes a Box model which makes the codewords representation and training period more compact than the standard codebook. Besides, A local updated method, namely through frame difference to detect the region of variation, is incorporated into layered codebook to update the background real-timely, thus achieving more accurate foreground detection. Comparative results indicate that the algorithm can handle scenes containing moving backgrounds or illumination variations, and it achieves robust object detection for different types of video.