As a promising machine learning tool to handle the accurate pattern recognition from complex raw data, deep learning (DL) is becoming a powerful method to add intelligence to wireless networks with large-scale topology and complex radio conditions. DL uses many neural network layers to achieve a brain-like acute feature extraction from high-dimensional raw data. It can be used to find the network dynamics (such as hotspots, interference distribution, congestion points, traffic bottlenecks, spectrum availability, etc.) based on the analysis of a large amount of network parameters (such as delay, loss rate, link SNR, etc.). Therefore, DL can analyze extremely complex wireless networks with many nodes and dynamic link quality. This article performs a comprehensive survey of the applications of DL algorithms for different network layers, including physical layer modulation/coding, data link layer access control/resource allocation, and routing layer path search and traffic balancing. The use of DL to enhance other network functions, such as network security, sensing data compression, etc., is also discussed. Moreover, the challenging unsolved research issues in this field are discussed in detail, which represent the future research trends of DL-based wireless networks. This article can help the readers to deeply understand the state-of-the-art of the DL-based wireless network designs, and select interesting unsolved issues to pursue in their research.

In this research, we target the communication-oriented UAV placement issue in a typical Manned-and-UnManned (MUM) airborne network. The MUM network consists of man-operated, communication-powerful aircraft in the higher height level and high-density unmanned air vehicles (UAVs) in the lower height level. While the aircraft network is relatively stable, the UAVs can form different swarm network topologies. Some UAVs are selected as gateway nodes to aggregate the received UAV data and send to a close aircraft. Assume a source UAV has data to be sent to a close gateway node via a routing path which may have broken links. Our goal is to guide the positioning of one or multiple relay UAVs to make up for the broken wireless links under the dynamic swarm topology. The placement of the relay node is determined by both traffic quality-of-service (QoS) requirements and the link conditions. We propose to build a new queueing model, called multi-hop priority queue, to analyze the achievable QoS performance through multi-hop queue-to-queue accumulation modeling. To handle dynamic swarm topology and time-varying link conditions, we propose to build Deep Q-learning (DQN) to determine the optimal link between any 2 UAV nodes, and then use optimization algorithm to locally fine-tune the position of the UAV node to optimize the overall network performance. The DQN-based UAV link selection is computed in the powerful aircraft which maintains the graphs of the swarm topology as well as the interference of each link. The optimization is implemented at the UAV. Our simulation results validate the throughput efficiency of our DQN-based UAV positioning schemes.

Human pose estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains, such as human–computer interaction, sports analysis, and human tracking via images and videos. Recently, deep learning-based approaches have shown state-of-the-art performance in HPE-based applications. Although deep learning-based approaches have achieved remarkable performance in HPE, a comprehensive review of deep learning-based HPE methods remains lacking in literature. In this article, we provide an up-to-date and in-depth overview of the deep learning approaches in vision-based HPE. We summarize these methods of 2-D and 3-D HPE, and their applications, discuss the challenges and the research trends through bibliometrics, and provide insightful recommendations for future research. This article provides a meaningful overview as introductory material for beginners to deep learning-based HPE, as well as supplementary material for advanced researchers.

A Review on Cloud Computing: Design Challenges in Architecture and Security

5G-based millimeter Waves (mmWave) systems have the prospective of enabling >1Gbps communications in the Intelligent Transportation Systems (ITS). ITS relies on vehicle-to-everything (V2X) communications to share information among vehicles. However, the V2X Communications via existing technologies such as DSRC, 3G, 4G and LTE, are not able to achieve such a high data rate. Although 5G-based mmWave can support ultra-low-delay V2X transmissions, it comes with beam alignment difficulties as well as the routing stability issues due to rapid mobility of vehicles. The dynamic vehicle traffic causes frequent beam misalignment which tends to degrade the quality-of-service (QoS) performance. In this paper, we first propose a 3D-based position detection scheme for beam alignment/selection purpose. Then a group-based routing algorithm is performed to select a secure path for achieving trustworthy data transmissions. The road traffic is automatically segmented to divide the vehicles into different groups, and each group head is selected and members are added. Group members are authenticated by the group head via elliptic curve algorithms. Huffman coding is performed to compress the data and encrypt the binary files. This proposed novel intelligent beam control and secure stable routing scheme have been verified in simulations to demonstrate much better performance than existing schemes.

The smart-house technology aims to increase home automation and security with reduced energy consumption. A smart house consists of various intelligent sensors and actuators operating on different platforms with conflicting objectives. This paper proposes a multi-agent system (MAS) design framework to achieve smart house automation. The novelties of this work include the developments of (1) belief, desire and intention (BDI) agent behavior models; (2) a regulation policy-based multi-agent collaboration mechanism; and (3) a set of metrics for MAS performance evaluation. Simulations of case studies are performed using the Java Agent Development Environment (JADE) to demonstrate the advantages of the proposed method.