With the widespread use of mobile devices and emerging mobile applications， the exponential growth of traffic in mobile networks has caused problems such as network congestion， large delay， and poor user experience that cannot satisfy the needs of mobile users. Edge caching technology can greatly relieve the transmission pressure of wireless networks through the reuse of hot contents in the network. At the same time， it has become one of the key technologies in 5G/Beyond 5G Mobile Edge Computing （MEC） to reduce the network delay of user requests and thus improve the network experience of users. Focusing on mobile edge caching technology， firstly， the application scenarios， main characteristics， execution process， and evaluation indicators of mobile edge caching were introduced. Secondly， the edge caching strategies with energy efficiency， delay， hit ratio， and revenue maximization as optimization goals were analyzed and compared， and their key research points were summarized. Thirdly， the deployment of the MEC servers supporting 5G was described， based on this， the green mobility-aware caching strategy in 5G network and the caching strategy in 5G heterogeneous cellular network were analyzed. Finally， the research challenges and future development directions of edge caching strategies were discussed from the aspects of security， mobility-aware caching， edge caching based on reinforcement learning and federated learning and edge caching for Beyond 5G/6G networks.

In order to solve the problem that the traditional deep learning based remote sensing image classification algorithms cannot effectively fuse multiple deep learning features and their classifiers have poor performance, an improved high-resolution remote sensing image classification algorithm based on deep learning was proposed. Firstly, a seven-layer convolutional neural network was designed and constructed. Secondly, the high-resolution remote sensing images were input into the network to train it, and the last two fully connected layer outputs were taken as two different high-level features for the remote sensing images. Thirdly, Principal Component Analysis (PCA) was applied to the output of the fifth pooling layer in the network, and the obtained dimensionality reduction result was taken as the third high-level features for the remote sensing images. Fourthly, the above three kinds of features were concatenated to get an effective deep learning based remote sensing image feature. Finally, a logical regression based classifier was designed for remote sensing image classification. Compared with the traditional deep learning algorithms, the accuracy of the proposed algorithm was increased. The experimental results show that the proposed algorithm performs excellent in terms of classification accuracy, misclassification rate and Kappa coefficient, and achieves good classification results.

Aiming at the poor recognition accuracy and robustness of the human targets caused by the serious interference on the targets under infrared imaging conditions, an infrared human target recognition method based on multi-feature dimensionality reduction and transfer learning was proposed. Firstly, in order to solve the problem of incomplete information during the extraction of a single feature by the traditional infrared human target feature extraction method, different kinds of heterogeneous features were extracted to fully exploit the characteristics of infrared human targets. Secondly, to provide the efficient and compact feature description for subsequent recognition, a principal component analysis method was utilized to reduce the dimensionality of the fused heterogeneous features. Finally, to solve the problems such as poor generalization performance, caused by the lack of tagged human target samples in infrared images as well as the distributional and semantic deviations between the training samples and testing samples, an effective infrared human target classifier based on transfer learning was presented, which was able to greatly improve the generalization performance and the target recognition accuracy. The experimental results show that the recognition accuracy of the method on infrared human target data set reaches more than 94%, which is better and more stable than that of the methods with a single feature such as Histogram of Oriented Gradients (HOG), Intensity Self Similarity (ISS) for feature representation or the methods learned with traditional non-transfer classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors ( KNN). Therefore, the performance of infrared human target recognition is improved in real complex scenes by the method.

To solve the problems of local or global sparse representation based image saliency detection methods, such as incomplete object extracted, unsmooth boundary and residual noise, an image saliency detection algorithm based on adaptive fusion of local sparse representation and global sparse representation was proposed. Firstly, the original image was divided into a set of image blocks, and these blocks were used to substitute the image pixels, which may decrease the computational complexity. Secondly, the blocked image was represented via local sparse representation. Specifically, for each image block, an overcomplete dictionary was generated by using its surrounding image blocks, and based on such dictionary the image block was sparsely reconstructed. As a result, an initial local saliency map which may effectively extract the edges of the salient objects could be gotten. Thirdly, the blocked image was represented by global sparse representation. The procedures were similar to the above steps. The difference was that, for each image block, the overcomplete dictionary was constructed by using the image blocks from the four margins of the input image. According to this, an initial global saliency map which could effectively detect the inner areas of the salient objects was obtained. Finally, the initial local and global saliency maps were adaptively fused together to compute the final saliency map. Experimental results demonstrate that compared with several classical saliency detection methods, the proposed algorithm significantly improves the precision, recall and F-measure.

In recommendation systems, recommendation results are affected by the matter that rating data is characterized by large volume, high dimensionality, extreme sparsity, and the limitation of traditional similarity measuring methods in finding the nearest neighbors, including huge calculation and inaccurate results. Aiming at the poor recommendation quality, this paper presented a new collaborative filtering recommendation algorithm based on Exact Euclidean Locality-Sensitive Hashing (E2LSH). Firstly, E2LSH algorithm was utilized to lower dimensionality and construct index for large rating data. Based on the index, the nearest neighbor users of target user could be obtained with great efficiency. Then, a weighted strategy was applied to predict the user ratings to perform collaborative filtering recommendation. The experimental results on typical dataset show that the proposed method can overcome the bottleneck of high dimensionality and sparsity to some degree, with high running efficiency and good recommendation performance.

Concerning the impact on network performance of the mobile nodes and the constantly changing data transmission rate, the authors proposed a new backoff scheme for IEEE802.15.4, which used Probability Judgment based on Network Load and Exponentially Weighted Moving Average (PJNL_EWMA) method. According to a realtime monitoring of current network status by probability judgment of network load, this method dynamically adjusted backoff exponent by EWMA when Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) began. Compared with the IEEE802.15.4 standard protocol and MBS (Memorized Backoff Scheme)+EWMA algorithm, the simulation experiments on NS2 platform show that the PJNL_EWMA algorithm not only improves the throughput of the network, but also reduces the packet loss rate and the collision ratio, significantly improving the network performance.