Unmanned aerial vehicles (UAVs) will be an integral part of the next generation wireless communication networks. Their adoption in various communication-based applications is expected to improve coverage and spectral efficiency, as compared to traditional ground-based solutions. However, this new degree of freedom that will be included in the network will also add new challenges. In this context, the machine-learning (ML) framework is expected to provide solutions for the various problems that have already been identified when UAVs are used for communication purposes. In this article, we provide a detailed survey of all relevant research works, in which ML techniques have been used on UAV-based communications for improving various design and functional aspects such as channel modeling, resource management, positioning, and security.

Unmanned aerial vehicle (UAV)-enabled communications have been proposed as a critical part of the beyond fifthgeneration (5G) cellular networks. This type of communications is frequently characterized by line-of-sight (LoS) and dynamic propagation conditions. However, in various scenarios, the presence of large obstacles in the LoS path is unavoidable, resulting in shadowed fading environments. In this paper, a new channel model is proposed, in which the effects of mobility and shadowing are simultaneously considered. In particular, the performance of a UAV-based communication system operating in a shadowed double-scattering channel is analyzed. The new channel model is generic, since it models various fading/shadowing conditions, while it is in terms of easy-to-evaluate mathematical functions. Moreover, a low complexity UAV selection policy is proposed, which exploits shadowing-related information. The proposed scheme offers a reduction of the signal processing complexity, without any important degradation on the performance, as compared to alternatives approaches. In this context, a new analytical framework has been developed for investigating the performance of the new strategy. Finally, the main outcomes of this paper are also validated by empirical data, collected in an air-to-ground measurement campaign.

In this paper we introduce a new perspective to the implementation of wireless MIMO transmission systems with increased bandwidth efficiency. Unlike traditional spatial multiplexing techniques in MIMO systems, where additional information can be sent through the wireless channel by feeding uncorrelated antenna elements with diverse bitstreams, we use the idea of mapping diverse bitstreams onto orthogonal bases defined in the beamspace domain of the transmitting array far-field region. Using this approach we show that we can increase the capacity of wireless communication systems using compact parasitic antenna architectures and a single RF front end at the transmitter, thus paving the way for integrating MIMO systems in cost and size sensitive wireless devices such as mobile terminals and mobile personal digital assistants.

In this paper, we study a hybrid satellite-terrestrial spectrum sharing system (HSTSSS) in which multiple terrestrial secondary networks cooperate with a primary satellite network for dynamic spectrum access. For complexity-aware HSTSSS design, we propose an amplify-and-forward-based overlay spectrum sharing protocol using partial and opportunistic secondary network selection schemes. The secondary network selection aims to minimize the outage probability of the primary satellite system and, thereby, to explore spectrum sharing opportunities. With the overlay approach, the selected secondary network allocates part of its power to relay the satellite signal and utilizes the remaining power to transmit its own signal. Considering Shadowed-Rician fading for satellite links, and Nakagami- ${m}$ as well as Rician fading for terrestrial links, we derive closed-form expressions for the outage probability of both primary and secondary networks, and examine their achievable diversity orders. Numerical and simulation results validate our analysis and highlight the performance gains of the proposed schemes for an HSTSSS with and without a direct satellite primary communication link.

This paper presents a three-dimensional (3-D) propagation model for path-loss prediction in a typical urban site, based on geometrical optics (GO) and uniform theory of diffraction (UTD), The model takes into account numerous rays that undergo reflections from ground and wall surfaces and diffraction from corners or rooftops of buildings. The exact location of reflection and diffraction points is essential in order to calculate the polarization components of the reflected and diffracted fields and their trajectories, This is accomplished by local rag-fixed coordinate systems in combination with appropriate dyadic reflection and diffraction coefficients. Finally, a vector addition of the received fields is carried out to obtain the total received field strength and, subsequently, the path loss along a predetermined route. The model computes the contributions of various categories of rays, as selected, in a flexible manner, Several results-path loss versus distance and power-delay profile-are given, and comparisons with measured data are presented

High-altitude platforms (HAPs) are one of the most promising alternative infrastructures for realizing next-generation high-data-rate wireless networks. This paper investigates the application of multiple-input-multiple-output (MIMO) techniques to HAP-based systems and proposes a 3-D geometry-based single-bounce reference model for Ricean fading channels. From this model, the space-time correlation function is derived for a 3-D nonisotropic scattering environment. The statistical properties of the reference model are analytically studied in terms of various parameters such as the elevation angle of the platform, the array configuration, the Doppler spread, and the distribution of the scatterers. Using the theoretical expressions, one can easily numerically evaluate the HAP antenna interelement spacing required to achieve uncorrelated responses in the HAP-MIMO channel matrix. The proposed model provides guidelines for the system design and performance analysis of HAP-MIMO communication systems with line-of-sight (LoS) and non-line-of-sight (NLoS) connections at the L and S frequency bands.