Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.

Non-orthogonal multiple access (NOMA) based wireless caching network (WCN) is considered as one of the most promising technologies for next-generation wireless communications since it can significantly improve the spectral efficiency. In this paper, we propose a quality of service (QoS)-oriented dynamic power allocation strategy for NOMA-WCN. In content stack phase, the base station sends multiple files to the content servers by allocating different powers according to the different QoS targets of files, for ensuring that all content servers can successfully decode the two most popular files. In content deliver phase, the content servers serve two users at the same time by allocating the minimum power to the far user according to the QoS requirement, and then all the remaining power is allocated to the near user. Hence, the proposed power allocation scheme is able to increase the hit probability and drop the outage probability compared with conventional method. Simulation results confirm that the proposed power allocation method can significantly improve the caching hit probability and reduce the user outage probability. It is also shown that this strategy can reduce the user delay time, improve the system efficiency and the capacity.

Decentralized edge computing techniques have been attracted strongly attentions in many applications of intelligent internet of things (IIoT). Among these applications, intelligent edge surveillance (LEDS) techniques play a very important role to recognize object feature information automatically from surveillance video by virtue of edge computing together with image processing and computer vision. Traditional centralized surveillance techniques recognize objects at the cost of high latency, high cost and also require high occupied storage. In this paper, we propose a deep learning-based LEDS technique for a specific IIoT application. First, we introduce depthwise separable convolutional to build a lightweight neural network to reduce its computational cost. Second, we combine edge computing with cloud computing to reduce network traffic. Third, we apply the proposed LEDS technique into the practical construction site for the validation of a specific IIoT application. The detection speed of our proposed lightweight neural network reaches 16 frames per second in edge devices. After cloud server fine detection, the precision of the detection reaches 89\%. In addition, the operating cost at the edge device is only one-tenth of that of the centralized server.