Search

The Internet of Vehicles (IoV) is a powerful application of the Internet of Things (IoT) in the Intelligent Transportation System (ITS). It enables device connectivity, and interaction with the environment, and improves efficiency in utilizing sensor data. Leveraging the capabilities of vehicle sensors to provide virtual sensor service presents an opportunity to make the most of underutilized sensor resources and offer on-demand sensor services. However, challenges remain in ensuring spatio-temporal sensor availability due to the high mobility of vehicles and frequent changes in the IoV network topology. Furthermore, providing sensor services in the dynamic IoV-Cloud market, while balancing cost-effectiveness for consumers and profitability for service providers, poses a significant challenge. To address these challenges, we develop an IoV-Cloud architecture tailored for vehicle virtual sensor provisioning, integrating interactive functional layers and components for a comprehensive solution. This architecture supports vehicle sensor virtualization and management, facilitating the intelligent provisioning of on-demand, elastic, and scalable vehicle virtual sensors from existing physical sensors within mobile vehicles. To address vehicle mobility and enhance sensor availability, our design permits virtual sensors to maintain data provision even when switched to different physical sensors. Further optimizing sensor utilization, our system allows multiple virtual vehicle sensors to share a single physical sensor by employing a configuration mapping mechanism. At the heart of our strategy is a reinforcement learning model that dynamically selects the most suitable vehicle physical sensor for each time slot throughout the service period, considering both physical availability and cost-effectiveness for the Sensor Cloud Service Provider (SCSP). We simulate the proposed intelligent sensor selection model using both Q-learning and SARSA algorithms, demonstrating its effectiveness in intelligent and dynamic sensor provisioning.

Machine learning (ML) has transformed various sectors, including healthcare, by enabling the extraction of complex knowledge and predictions from vast datasets. However, the opacity of ML models, often referred to as “black boxes,” hinders their integration into medical practice. Explainable AI (XAI) has emerged as a crucial area for enhancing the transparency and understandability of ML model decisions, particularly in healthcare where reliability and accuracy are paramount. However, the reliability of the explanations provided by ML models remains a major challenge. This mainly concerns the difficulty of maintaining the validity and relevance of the new training and test data explanations. In this study, we propose a structured approach to enhance and evaluate the reliability of explanations provided by ML models in healthcare. We aim to improve the reliability of explainability by combining the XAI approaches with the k-fold technique. We then developed several metrics to assess the generalizability, concordance, and stability of the combined XAI and k-fold approach, which we applied to case studies on hypothyroidism and diabetes risk prediction using SHAP and LIME frameworks. Our findings reveal that the SHAP approach combined with k-fold exhibits superior generalizability, stability, and concordance compared to the combination of LIME with k-fold. SHAP and k-fold integration provide reliable explanations for hypothyroidism and diabetes predictions, providing strong concordance with the internal explainability of the random forest model, the best generalizability, and good stability. This structured approach can bolster practitioner’s confidence in ML models and facilitate their adoption in healthcare settings.

With the deployment of satellite constellations, Internet-of-Things (IoT) devices in remote areas have gained access to low-cost network connectivity. In this paper, we investigate the performance of IoT devices connecting in up-link through low Earth orbit (LEO) satellites to geosynchronous equatorial orbit (GEO) links. We model the dynamic LEO satellite constellation using the stochastic geometry method and provide an analysis of end-to-end availability with low-complexity and coverage performance estimates for the mentioned link. Based on the analytical expressions derived in this research, we make a sound investigation on the impact of constellation configuration, transmission power, and the relative positions of IoT devices and GEO satellites on end-to-end performance.

In this work, we consider multi-hop and mesh hybrid teraHertz/free-space optics (THz/FSO)-based backhaul networks for high data-rate communications. The results are presented for the cases with both out-band integrated access and backhaul (IAB) and non-IAB based communication setups. We consider different deployments of the THz and FSO networks and consider both switching and combining methods between the hybrid THz/FSO links. We study the impact of atmospheric turbulence, atmospheric attenuation, and the pointing error on the FSO communication. The THz communication suffers from small scale fading, path-loss, and the misalignment error. Finally, we evaluate the effects of atmospheric attenuation/path-loss, pointing/misalignment error, small-scale fading, atmospheric turbulence, number of antennas, number of user equipments, number of hops, and the threshold data-rates on the performance of considered systems. As we show, with different network deployments and switching/combining methods, the hybrid implementation of the THz/FSO links improves the network reliability significantly.

With an objective of ubiquitous connectivity around the world with enhanced spectral efficiency, intelligent reflecting surfaces (IRS) integrated satellite-terrestrial communications is a topic of research interest specially in infrastructure-deficient terrains. In line with this vision, this paper entails the performance analysis of satellite-terrestrial networks leveraging both aerial and terrestrial IRS nodes, with the support of high altitude platforms (HAPS) over diverse fading channels including shadowed Rician, Rician, and Nakagami-m fading channels. The merits of IRS in enhancing spectral efficiency is analyzed through closed-form expressions of outage probability and ergodic rate. Further, the average symbol error rate analysis for the higher-order quadrature amplitude modulation (QAM) schemes such as hexagonal QAM, rectangular QAM, cross QAM, and square QAM is performed. Practical constraints like antenna gains, path loss, and link fading are considered to characterize the satellite terrestrial links. Finally, a comparison between the HAPs based IRS node and terrestrial IRS nodes is performed and various insights are drawn under various fading scenarios and path loss conditions. Our results demonstrate that aerial IRS nodes offer superior performance in terms of outage probability, ergodic rate, and symbol error rate for higher-order QAM schemes. Additionally, the study reveals that the ergodic rate in aerial IRS systems scales with the number of IRS elements, while terrestrial IRS systems rely on the diversity of the satellite-HAP link.

The present paper tackles the dynamic job shop scheduling problem (DJSSP), aiming to schedule a new set of jobs while minimizing the completion time of all operations. The problem is an NP-hard combinatorial optimization problem. This contribution proposes an optimal scheduling method based on the evolutionary genetic algorithm approach. The difficulty of this problem is to comprehensively find the best direction of a candidate solution while maintaining the minimum total completion time known as the makespan and denoted as Cmax. To adapt the system to changes and perform the scheduling of a new job, a local search could be an appropriate solution to fix and repair the problem by guiding the search directions following the job’s arrival. Experiment-based statistical analysis shows that the proposed model has better convergence and accuracy than state-of-the-art algorithms.

The Internet of Things (IoT) revolutionizes connectivity, as IoT devices grow exponentially, vulnerabilities emerge, ranging from data breaches to device hijacking. Thus there is the critical need for robust security measures, including encryption protocols and authentication mechanisms, to safeguard against cyber threats. Despite advancements in the authentication mechanism, still IoT security remains an ongoing concern. Because most of the authentications are vulnerable to diverse security attacks and other resource intensive. Thus protecting user data in this increasingly interconnected IoT-enabled world requires a secure and lightweight authentication mechanism. In this direction, in this paper, we propose a physically secure authentication framework for the IoT (PSAF-IoT). PSAF-IoT utilizes a combination of physical unclonable functions, secure hash algorithm, and elliptic curve cryptography to establish robust security measures. It guarantees the creation of a secure channel (session key) following user authentication at the gateway node, allowing the user to use the established secure channel for future communication. The secure channel establishment procedure is validated for security by employing formal methods such as the random oracle model and Scyther-based simulations. Additionally, PSAF-IoT undergoes informal validation to demonstrate resilience against node capture, replay attacks, impersonation, and other common security threats. Notably, PSAF-IoT demonstrates efficiency in terms of execution time, energy consumption, and communication costs, as evidenced by comparative analyses with related authentication frameworks, all while enhancing information security functionalities.

With the development of fifth-generation (5G) networks, the number of user equipments (UE) increases dramatically. However, the potential health risks from electromagnetic fields (EMF) tend to be a public concern. Generally, EMF exposure-related analysis mainly considers the passive exposure from base stations (BSs) and active exposure that results from the user’s personal devices while communicating. However, the passive radiation that is generated by nearby devices of other users is typically ignored. In fact, with the increase in the density of UE, their passive exposure to human bodies can no longer be ignored. In this work, we propose a stochastic geometry framework to analyze the EMF exposure from active and passive radiation sources. In particular, considering a typical user, we account for their exposure to EMF from BSs, their own UE, and other UE. We derive the distribution of the Exposure index (EI) and the coverage probability for two typical models for spatial distributions of UE, i.e., i) a Poisson point process (PPP); ii) a Matern cluster process. Also, we show the trade-off between the EMF exposure and the coverage probability. Our numerical results suggest that the passive exposure from other users is non-negligible compared to the exposure from BSs when user density is 102 times higher than BS density, and non-negligible compared to active exposure from the user’s own UE when user density is 105 times the BS density.

The use of visible light communication (VLC) to support wireless coverage has been receiving increasing interest, due to factors that include its operation in a large unregulated spectrum and immunity against electromagnetic interference. On the other hand, the sensitivity of VLC network performance to the line-of-sight (LOS) link quality affects the system reliability. The emergence of reconfigurable intelligent surfaces (RISs) in optical domain opens the door for minimizing the impacts of the LOS link degradation on VLC networks, given the possibilities they provide for enhancing the non-LOS channel gain. In this paper, we propose optimizing the RIS-assisted VLC systems by controlling the RIS elements to maximize the network sum-rate while maintaining fairness in the user achievable throughput. Two types of RIS elements are considered, where the addressed non-convex optimization problems are handled using the genetic algorithm and the particle swarm optimization techniques, presenting improvement in network performance in terms of sum rate, fairness, and link outage ratio. In addition, we investigate the RIS-assisted VLC system performance in cases of handling mobile users, highlighting the trade-off between the variation in the optimization rate and the network performance.

Terrain information is a crucial factor affecting the performance of unmanned aerial vehicle (UAV) networks. As a tutorial, this article provides a unique perspective on the completeness of terrain information, summarizing and enhancing the research on terrain-based UAV deployment. In the presence of complete terrain information, two highly discussed topics are UAV-aided map construction and dynamic trajectory design based on maps. We propose a case study illustrating the mutually reinforcing relationship between them. When terrain information is incomplete, and only terrain-related feature parameters are available, we discuss how existing models map terrain features to blockage probabilities. By introducing the application of this model with stochastic geometry, a case study is proposed to analyze the accuracy of the model. When no terrain information is available, UAVs gather terrain information during the real-time networking process and determine the next position by collected information. This real-time search method is currently limited to relay communication. In the case study, we extend it to a multi-user scenario and summarize three trade-offs of the method. Finally, we conduct a qualitative analysis to assess the impact of three factors that have been overlooked in terrain-based UAV deployment.

The concept of the smart city relies on connectivity and is expected to revolutionize urban living and create sustainable cities. However, while smart cities continue to evolve, small towns, suburbs, and villages lack basic communication infrastructure. This phenomenon exacerbates inequality and perpetuates a growing digital divide. Hence, it is imperative to also concentrate on these communities by designing strategies to extend essential services to them and drive the development of smart communities. High-altitude platform stations (HAPS) are a key enabling technology for such a concept. They fly in the stratosphere and offer extensive connectivity coverage, are cost-effective, and powered by solar energy and hydrogen. To demonstrate the potential of HAPS in enabling smart communities, the world’s first-ever fifth-generation (5G) trial using HAPS was conducted. The experiment showed that HAPS provided high data rates and ubiquitous 5G coverage from the stratosphere in different scenarios. The main requirements of smart communities, such as ensuring equity and inclusion, intelligent transportation systems, and a blue economy were successfully addressed. We also highlight the main benefits of HAPS in enabling smart communities, as well as the involvement of communities in the co-design of such solutions. Finally, additional applications are presented, along with the main key enabling technologies.

This article considers an interference-based radio-frequency energy harvesting (RF-EH)-empowered wireless dual-hop amplify-and-forward relaying system in which an ambient interferer is beneficially utilized as the solely free power source for EH and detrimentally considered as the dominant factor that corrupts its receivers. Three EH modes are considered and analyzed separately. In mode I, energy is harvested only by the source; in mode II, energy is harvested only by the relay; and in mode III, energy is harvested concurrently by both the source and relay. Under these modes, exact and approximate analytical expressions are derived for the system's outage probability, which are directly used to determine the system's delay-limited throughput as a performance figure of merit. Thorough numerical and simulation results are presented to verify the analytical work and to demonstrate the system's throughput performance under different system and channel parameters. For example, results reveal that for given channel conditions, increasing the interferer's power reduces the throughput in case of modes I and II, and has no effect on it in case of mode III. Also, for given interferer's power, improving the channel conditions between the interferer and a harvesting node, improves the throughput, while improving them between the interferer and a receiving node, degrades the throughput.

In this paper, we investigate the performance of multiple-input multiple-output (MIMO) free-space optical (FSO) communication systems, encompassing both slant path (downlink and uplink) and horizontal links. The FSO links span ground-to-high altitude platform system (HAPS), HAPS-to-ground, and HAPS-to-HAPS configurations. To model the atmospheric turbulence-induced fading, pointing error impairments, and angle-of-arrival (AOA) fluctuations, we employ the Gamma-Gamma distribution, Hoyt distribution, and Rayleigh distribution, respectively. We then derive the probability density function (PDF) of the end-to-end signal-to-noise ratio (SNR) under the combined effect of turbulence, AOA fluctuations, attenuation due to absorption and scattering, and generalized pointing error impairments. Capitalizing on this PDF expression, we present novel results for fundamental performance metrics, including outage probability, average bit-error rate (BER) of on-off keying (OOK) modulation scheme, and ergodic capacity expressed in terms of the Meijer's G function. Additionally, we provide highly accurate asymptotic results for the outage probability and the average BER at high SNR, obtained in terms of simpler functions. Furthermore, we demonstrate that the integration of MIMO configurations in either the transmitter, receiver, or both significantly enhances the performance of FSO communication links. To validate our analytical results, computer-based Monte-Carlo simulations are conducted, affirming the reliability of our findings.

Since the discovery of vortex beams by Allen et al., there has been a growing interest in exploring the applications of orbital angular momentum (OAM) in communication. Among all these researches, especially radio frequency (RF) wireless communication based on OAM should be one of the most promising research topics since the frequency resource is increasingly scarce and OAM can provide us with a new degree of freedom besides frequency, time, and space. In the context of wireless communication, millimeter wave and terahertz communication have gained extensive attention to harness spectrum resources. However, due to the short wavelength at these frequencies, line of sight (LOS) channels dominate. OAM, even in LOS channels, offers an additional degree of freedom compared to conventional multiple input multiple output systems. Yet, there are strict requirements for free-space OAM, one of which is the strict alignment between antenna arrays. To the best of our knowledge, there has not been any work about the capacity analysis of OAM communication under random misalignment. In this article, we obtain accurate closed-form intensity for a given misalignment value for both indoor and outdoor situations. Moreover, based on these intensity formulas, we analyze the average capacity under 2-D Gaussian random misalignment numerically and validate its accuracy by simulation. Besides, we illustrate that the Gauss-Laguerre quadrature can be used to reduce the computation complexity in the real environment. Moreover, we analyze the relationship between the average capacity and system parameters such as the array radii, signal-to-noise ratio, and misalignment distribution standard deviation for both indoor and outdoor situations. At last, we verify our work is also effective for the concentric circular array. This work could be a reference to the implementation of a practical RF OAM communication system.

We hereby present a novel interference mitigation strategy specifically designed to enhance the quality of service that a typical terrestrial user equipment (UE) would experience after the occurrence of a calamity. In particular, we devise a novel stochastic geometry framework where the functioning ground base stations are modeled as an inhomogeneous Poisson point process, and promote proper silencing as an effective solution to improve both coverage and reliability (which is usually overlooked in emergency scenarios); in particular, the latter is evaluated by means of the signal-to-interference-plus-noise ratio (SINR) meta distribution performance metric. The derived downlink performances assume Rayleigh fading conditions for all wireless links. The numerical results show insightful trends in terms of both average coverage probability (which is optimized by choosing the best area for applying the silencing strategy) and SINR meta distribution, depending on: distance of the UE from the disaster epicenter (henceforth intended as the center of the area where the BS can be damaged), disaster radius (also referring to the latter area), and quality of resilience of the terrestrial network. The aim of this paper is therefore to prove the effectiveness of proper silencing in emergency scenarios, at least from the coverage and reliability perspectives.

Given the necessity of connecting the unconnected, covering blind spots has emerged as a critical task in the next-generation wireless communication network. A direct solution involves obtaining a coverage manifold that visually showcases network coverage performance at each position. Our goal is to devise different methods that minimize the absolute error between the estimated coverage manifold and the actual coverage manifold (referred to as accuracy), while simultaneously maximizing the reduction in computational complexity (measured by computational latency). Simulation is a common method for acquiring coverage manifolds. Although accurate, it is computationally expensive, making it challenging to extend to large-scale networks. In this paper, we expedite traditional simulation methods by introducing a statistical model termed line-of-sight probability-based accelerated simulation. Stochastic geometry is suitable for evaluating the performance of large-scale networks, albeit in a coarse-grained manner. Therefore, we propose a second method wherein a model training approach is applied to the stochastic geometry framework to enhance accuracy and reduce complexity. Additionally, we propose a machine learning-based method that ensures both low complexity and high accuracy, albeit with a significant demand for the size and quality of the dataset. Furthermore, we describe the relationships between these three methods, compare their complexity and accuracy as performance verification, and discuss their application scenarios.

Aerial base stations can be realized using unmanned aerial vehicles (UAVs)-mounted access points, which offer flexible and rapid network access in scenarios where terrestrial cellular networks are challenged by high traffic loads or insufficient coverage. Visible light communication (VLC) is an emerging technology that can be integrated with UAVs to offer simultaneous communication and illumination services while having low interference, high energy efficiency, and high data rates. To achieve an efficient operation of VLC-enabled UAVs, the power consumption of the UAVs due to their mobility should be considered, as it constitutes a significant portion of the total power consumption of the UAVs, especially when compared to that of the communication needs. This paper proposes a framework to optimize the trajectories of VLC-enabled UAVs, considering a multi-objective optimization problem that jointly maximizes the sum-rate and rate fairness of the users and minimizes the power consumption of the UAVs using particle swarm optimization (PSO) algorithm. The results show that the proposed optimization can effectively improve the performance of the system under various user mobility scenarios and UAV deployment altitudes.

This paper derives approximate outage probability (OP) expressions for uplink cell-free massive multiple-input-multiple-output (CF-mMIMO) systems with and without pilot contamination. The system’s access points (APs) are considered to have imperfect channel state information (CSI). The signal-to-interference-plus-noise ratio (SINR) of the CF-mMIMO system is approximated via a Log-normal distribution using a two-step moment matching method. OP and ergodic rate expressions are derived with the help of the approximated Log-normal distribution. For the no-pilot contamination scenario, an exact expression is first derived using conditional expectations in terms of a multi-fold integral. Then, a novel dimension reduction method is used to approximate it by the sum of single-variable integrations. Both the approximations derived for the CF-mMIMO systems are also useful for single-cell collocated massive MIMO (mMIMO) systems and lead to closed-form expression. The derived expressions closely match the simulated numerical values for OP and ergodic rate.

Many rural and remote areas around the world still lack access to the Internet due to the high deployment and maintenance costs, the lack of infrastructure, and the low income compared to urban regions. Therefore, cost-effective wireless backhaul links are required to connect these areas to the Internet core network. A wireless non-line-of-sight (NLOS) backhaul via diffraction in rural areas is a promising low-cost solution alternative to the traditional LOS backhaul. A reliable and cost-effective NLOS backhaul can be achieved if accurate propagation modelling and performance evaluation are performed before deployment. In this work, we first examine the accuracy of various terrain-based propagation models in predicting diffraction in different rural sites at unlicensed 5.8 GHz band. Although the classic irregular terrain model (ITM) is widely implemented in many radio frequency (RF) design software, we find that it overestimates the actual diffraction loss over small diffraction angles with an average error of −24 dB and RMSE value of 23 dB. However, a less complex rounded-obstacle diffraction model shows very high prediction accuracy compared to measured data with a negligible average error of −0.01 dB and RMSE value of 2.7 dB. Further, we evaluate the feasibility of an end-to-end NLOS backhaul link via simulation based on the IEEE 802.11ac standard using the practical characteristics of commercial RF equipment. The link performance is evaluated via end-to-end simulation in terms of the achieved throughput and the packet error rate (PER) over various antenna heights, modulation, and coding (MCS) schemes, and channel bandwidths. The results show that an NLOS backhaul at a distance of 11 km is viable with a throughput of 100–175 Mbps and PER of 0-0.1.

An unmanned aerial vehicle-mounted base station (UAV-BS), also known as an aerial base station (ABS), is a viable technology for the next 6G wireless networks due to its adaptability and affordability. Furthermore, the concept of tethered UAVs (TUAVs), can be used to circumvent the limited network operating time of UAV-BS networks. TUAVs are UAVs powered by a ground energy source via a tether that restrain their mobility while providing unlimited power. In this work, we propose a system where ABSs are deployed in user hotspots to offload the traffic and assist terrestrial base stations (TBSs). We will analyze three different scenarios and compare them in terms of coverage performance and energy efficiency. For a more realistic system, we offer a system model that considers the dynamic spatial distribution of users. First of all, we start by determining the optimal locations of TUAVs that minimize the average pathloss for each scenario. Next, using tools from stochastic geometry and an approach of dividing the space into concentric rings and slices to quantify the locations and orientations of ground stations (GSs), we analyze both coverage and energy performance for each scenario. We verify our findings using Monte-Carlo simulations and draw multiple useful insights. For instance, we show that deploying a TUAV with attachment and detachment capability for each pair of clusters outperforms deploying a normal TUAV for each cluster in terms of energy efficiency but not in terms of coverage performance.

Reconfigurable intelligent surface (RIS) technology and its integration into existing wireless networks have recently attracted much interest. While an important use case of said technology consists in mounting RISs onto unmanned aerial vehicles (UAVs) to support the terrestrial infrastructure in post-disaster scenarios, the current literature lacks an analytical framework that captures the networks' topological aspects. Therefore, our study borrows stochastic geometry tools to estimate both the average and local coverage probability of a wireless network aided by an aerial RIS (ARIS); in particular, the surviving terrestrial base stations (TBSs) are modeled by means of an inhomogeneous Poisson point process, while the UAV is assumed to hover above the disaster epicenter. Our framework captures important aspects such as the TBSs' altitude, the fact that they may be in either line-of-sight or non-line-of-sight condition with a given node, and the Nakagami-m fading conditions of wireless links. By leveraging said aspects we accurately evaluate three possible scenarios, where TBSs are either: (i) not aided, (ii) aided by an ARIS, or (iii) aided by an aerial base station (ABS). Our selected numerical results reflect various situations, depending on parameters such as the environment's urbanization level, disaster radius, and the UAV's altitude.

The high altitude platform (HAP) network has been regarded as a cost-efficient solution for providing network access to rural or remote areas. Apart from network connectivity, rural areas are predicted to have demands for diverse real-time intelligent communication services, such as smart agriculture and digital forestry. The effectiveness of real-time decision-making applications depends on the timely updating of sensing data measurements used in generating decisions. As a performance metric capable of quantifying the freshness of transmitted information, the age of information (AoI) can evaluate the freshness-aware performance of the process of updating sensory data. However, unlike urban areas, the available communication resources in rural areas may not allow for maintaining dedicated infrastructures for different types of services, e.g., conventional non-freshness-aware services and freshness-aware real-time services, thereby requiring the proper resource allocation among different services. In this article, we first introduce the anticipated services and discuss the advances of rural networks. Next, a case study on the efficient resource allocation across heterogeneous services characterized by AoI and data rate in HAP networks is presented. We also explore the potential of employing the free-space optical (FSO) backhaul framework to enhance the performance of multi-layer HAP networks. To strike a balance between the AoI and data rate, we develop both static and deep reinforcement learning (DRL)-based dynamic resource allocation schemes to allocate the communication resources provided by HAP networks. The simulation results show that the proposed dynamic DRL-based method outperforms the heuristic algorithm and can surpass the performance ceiling achieved by the proposed static allocation scheme. In particular, our presented method can improve performance by nearly 2.5 times more than the ant colony optimization (ACO) method in terms of weighted sum performance improvements. Some insights on system design and promising future research directions are also given.

In this paper, we present a simulation-based study for the coexistence of an International Mobile Telecommunication (IMT) system with a Digital Terrestrial Television Broadcasting (DTTB) system. The study considers the coexistence of the two systems in the sub-700 MHz band and presents interference analysis results for locations in the Kingdom of Saudi Arabia (KSA). The study includes different terrains in which each of the two systems is deployed, e.g., mountains, sea, desert, etc. Using an advanced terrain-aware simulation software (HTZ from Advanced Topographic and Digital Imaging (ATDI), the coexistence problem is studied in these cases which represent some of the most common types of terrains. The goal is to quantify the level of interference in each of the case studies and compare it with the protection ratio in terms of either the carrier-to-interference-plus noise $C/(I+N)$ or interference-to-noise $(I/N)$ ratios, depending on the simulation parameters and following the standard approach used in such studies. These two measures help in providing the proper recommendations on the coexistence of the IMT and DTTB systems. This study is structured into two main parts. The first part focuses on studying the interference induced by IMT base station (BS) and IMT user equipment (UE) on the DTTB receiver in the sub−700 MHz band (from 614 to 694 MHz) which corresponds to the 5G N71 band, whereas the second part considers the interference induced by DTTB system on IMT BS and IMT UE. The investigation has revealed that in most of those situations, separation distances (exclusion zones) are found to be relatively within a reasonable range from the border compared with the size of the whole network. This indicates that IMT network could be deployed in many locations close to the DTTB network with tolerable effect. The most challenging case is the effect of DTTB system on the up-link (UL) of IMT network, which necessitates the use of additional mitigation techniques to reduce the interference.

The deployment of 5G networks is approaching a mature phase in many countries across the world. However, little efforts have been done so far to scientifically compare ElectroMagnetic Field (EMF) exposure and traffic levels before and after the activation of 5G service over the territory. The goal of this work is to provide a sound comparative assessment of exposure and traffic, by performing repeated measurements before and after 5G provisioning service. Our solution is based on an EMF meter and a spectrum analyzer that is remotely controlled by a measurement algorithm. In this way, we dissect the contribution of each pre-5G and 5G band radiating over the territory. In addition, we employ a traffic chain to precisely characterize the achieved throughput levels. Results, derived from a set of measurements performed on a commercial deployment, reveal that the provisioning of 5G service over mid-band frequencies has a limited impact on the exposure. In parallel, the measured traffic is more than doubled when 5G is activated over mid-bands, reaching levels above 200 [Mbps]. On the other hand, the provisioning of 5G over sub-GHz bands does not introduce a substantial increase in the traffic levels. Eventually, we demonstrate that EMF exposure is impacted by the raw-land reconfiguration to host the 5G panels, which introduces changes in the sight conditions and in the power received from the main lobes.

The provisioning of 5G technology does not only involve mobile terminals, but also new services such as Fixed Wireless Access (FWA). The aim of this study is to examine the ElectroMagnetic Field (EMF) and throughput performance of a FWA deployment utilizing Standalone technology operating at 3.5 GHz. To address the unique characteristics of 5G FWA signals, an innovative framework has been designed based on the measurement of 5G FWA spectrum using four independent chains and an additional traffic generation chain to saturate the radio link capacity at the measurement location. Methodologies for evaluating 5G FWA exposure under conservative conditions, such as measurements of exposure during active traffic generation and maximum power extrapolations, are also introduced. Results from real measurements taken at a baseball stadium show that 5G FWA exposure is consistently low, typically below 0.4 [V/m], with an upper bound of 0.59 [V/m], while the achieved throughput is up to 250 [Mbps]. Additionally, the measured 5G exposure levels are a small fraction compared to those emitted by other technologies such as 4G. Furthermore, the values estimated by simulation from the output power counters of the base station are found to be in close agreement with the measured exposure levels.

We analyze the outage probability of integrated ground-air-space free-space optical (FSO) communication links for different atmospheric turbulence channel models. The performance of ground to high altitude platforms (HAPS), HAPS to geostationay Earth orbit (GEO) satellite, HAPS to HAPS and ground to GEO satellite is investigated for various link configurations (downlink, horizontal, and uplink) and parameters such as zenith angle, channel state, horizontal and vertical deviations, altitude, beam waist, receiver aperture diameter, wind speed, and visibility. The atmospheric attenuation (the effects of fog, cloud and volcanic activities), atmospheric turbulence, angle of arrival (AOA) fluctuations and pointing error are included in the considered model. Closed-form expressions for the probability density function (PDF) and cumulative distribution function (CDF) are obtained for Lognormal, Gamma and exponentiated Weibull distributed channel models. The benefit of using HAPS is shown by comparison of outage probabilities for direct ground to GEO satellite and HAPS assisted ground to GEO satellite links.

An array of detectors is widely used in deep space optical communications for both fine beam tracking and symbol detection. In this paper, we have analyzed and compared the performance of different combining schemes—such as equal gain combiner (EGC), selection combiner (SC) and the maximal ratio combiner (MRC)—that are used to fuse the outputs from the elements of such arrays. The three combining schemes are compared in terms of error rate performance and computational complexity. Additionally, for the limiting case of continuous arrays of circular configuration, the optimization of two important parameters—the spot size and the array size—is also discussed in order to achieve the best error rate performance.

Networked Tethered Flying Platforms (NTFPs) have gained growing interest in recent years due to their versatility and cost-efficiency. These aerial platforms are linked to ground stations via tethers that supply them with continuous power and data. The main advantages of NTFPs include endurance, broad coverage, and robust backhaul capacity, allowing them to carry various types of applications. This survey provides a comprehensive overview of NTFPs from a general and wireless communication perspective. We start with a general overview of this solution by reviewing all the existing types of NTFPs, including their components, characteristics, applications, advantages, and regulations. We also describe several case studies in various fields. Then, we investigate the role of NTFPs in wireless communications and their integration in Non-Terrestrial Networks (NTNs) alongside free-flying platforms and satellites in Sixth Generation (6G) cellular technology. We present NTFPs system models and emerging works on NTFPs performance. We show how 6G key technologies will be integrated into NTFPs and discuss how NTFPs will enable 6G use cases. The related channel models to NTFPs deployment are also covered. For completeness, we provide an economic analysis of the use of NTFPs. Finally, we discuss the challenges and open problems.

The number of disasters has increased over the past decade where these calamities significantly affect the functionality of communication networks. In the context of 6G, airborne and spaceborne networks offer hope in disaster recovery to serve the underserved and to be resilient in calamities. Therefore, our paper reviews the state-of-the-art literature on post-disaster wireless communication networks and provides insights for the future establishment of such networks. In particular, we first give an overview of the works investigating the general procedures and strategies for facing any large-scale disaster. Then, we present technological solutions for post-disaster communications, such as the recovery of the terrestrial infrastructure, installing aerial networks, and using spaceborne networks. Afterwards, we shed light on the technological aspects of post-disaster networks, primarily the physical and networking issues. We present the literature on channel modeling, coverage and capacity, radio resource management, localization, and energy efficiency in the physical layer part, and discuss the integrated space-air-ground architectures, routing, delay-tolerant/software-defined networks, and edge computing in the networking layer part. This paper also includes interesting simulation results which can provide practical guidelines about the deployment of ad hoc network architectures in emergency scenarios. Finally, we present several promising research directions, namely backhauling, cache-enabled and intelligent reflective surface-enabled networks, placement optimization of aerial base stations (ABSs), and the mobility-related aspects that come into play when deploying aerial networks, such as planning their trajectories and the consequent handovers (HOs).

In the past decade, improving upper limb prostheses control methods with pattern recognition (PR) has been the focus of an extended amount of research. However, several challenges associated with the processing of the Electromyogram (EMG) signals still need to be tackled to enable widespread and clinical implementation of upper limb prostheses with PR. As a result, alternative modalities functioning as promising control signals have been proposed as source of control input rather than the surface EMG, such as Acoustic myography (AMG) and Force myography. In this paper, eight high sensitivity array microphones were utilized to acquire the AMG signals, with 8 custom-built 3D printed microphone housing developed for the purpose of this research. Twenty subjects were recruited for data collection in this paper with the hardware design developed specifically by our research team, making our database the largest open-access dataset in the AMG literature. We proposed a novel feature extraction (FE) method based on the Wavelet Scattering Transform (WST) to tackle the challenge of extracting the relevant information from AMG to classify 14 hand and finger movement classes. The WST is a translation-invariant non-linear signal representation that has a strong theoretical support as it maintains stability to time-warping deformations, while preserving a high degree of discriminability. The performance results showed that WST outperformed all state-of-the-art FE methods with an accuracy of 88% on average across 20 subjects when classified with Quadratic Discriminant Analysis (QDA) classifier for a large dataset of AMG signals. These results suggest that the AMG signals can be utilized as a reliable source of control, especially when the windows sizes and number of channels are carefully selected. The AMG dataset is available from the link https://drive.google.com/drive/folders/1r0rBnrNG5c8qegffKUhAYYHQUT8cGVHD?usp=sharing.

This paper proposes a new time-domain multi-tone distortion (TD-MTD) model suitable for accurately predicting the non-linear behavior of packaged high power radio frequency (RF) transistors over a range of discrete non-uniformly distributed frequencies. This proposed TD-MTD model uses a single expression rather than multiple distinct frequency specific behavioral models to describe the underlying behavior of the high power RF transistor at multiple fundamental frequencies. Furthermore its extraction is carried out using a time-domain representation of the travelling waves that can be acquired using a generic vector load-pull characterization system and without imposing additional requirements. The proposed model is extracted as an artificial neural network (ANN) and is implemented as a Netlist to serve in a harmonic balance simulator based power amplifier design process. The proposed model is validated in two phases. First, its ability to reproduce the large-signal behavior of a high power RF LDMOS transistor was demonstrated in simulation. Then, the TD-MTD model was used to validate the design of a high power two-way asymmetric Doherty power amplifier and the simulated output-power-dependent power efficiency, AM/AM, AM/PM and input return loss characteristics were compared to those obtained in measurement. The excellent agreement between the simulation and measurement results confirms the usefulness of the proposed model despite the simplicity of its extraction routine and measurement data.

Unlike its intercept, a linear classifier's weight vector cannot be tuned by a simple grid search. Hence, this paper proposes weight vector tuning of a generic binary linear classifier through the parameterization of a decomposition of the discriminant by a scalar which controls the trade-off between conflicting informative and noisy terms. By varying this parameter, the original weight vector is modified in a meaningful way. Applying this method to a number of linear classifiers under a variety of data dimensionality and sample size settings reveals that the classification performance loss due to non-optimal native hyperparameters can be compensated for by weight vector tuning. This yields computational savings as the proposed tuning method reduces to tuning a scalar compared to tuning the native hyperparameter, which may involve repeated weight vector generation along with its burden of optimization, dimensionality reduction, etc., depending on the classifier. It is also found that weight vector tuning significantly improves the performance of Linear Discriminant Analysis (LDA) under high estimation noise. Proceeding from this second finding, an asymptotic study of the misclassification probability of the parameterized LDA classifier in the growth regime where the data dimensionality and sample size are comparable is conducted. Using random matrix theory, the misclassification probability is shown to converge to a quantity that is a function of the true statistics of the data. Additionally, an estimator of the misclassification probability is derived. Finally, computationally efficient tuning of the parameter using this estimator is demonstrated on real data.

This work investigates the performance of a laser-powered unmanned aerial vehicle (UAV) based hybrid wireless network consisting of a UAV-mounted base station (UAV-BS), cellular user, a low-power IoT user, and a secondary IoT network consisting of a group of multiple IoT devices. Communication among these devices takes place in two different phases. In the first phase of transmission, UAV-BS fulfills its power requirements by harvesting power from a distributed laser charging-based laser power transfer and uses non-orthogonal multiple access (NOMA) signaling to transmit the information to both the users. Further, in the second phase of transmission, the IoT user harvests power using power-splitting (PS) protocol and uses it to communicate with the selected IoT device, selected using a signal to interference-plus-noise ratio based selection strategy from the secondary IoT network, while the cellular user transmits uplink information to UAV-BS. We discuss the effect of non-linear energy harvesting on the performance of secondary IoT network and UAV-BS. Next, we analyze the performance of the proposed system by deriving the closed-form expressions of the outage probabilities, throughput, and ergodic capacity of both the users, the secondary IoT network, and UAV-BS. Furthermore, we find the optimal values of power coefficient and target rates that maximize the throughput of the IoT user while attaining a desired throughput for the cellular user. We also demonstrate that a judicious choice of the power allocation coefficient is essential in order to maximize the sum throughput of the system and hence the energy efficiency. Simulation results verify the accuracy of derived expressions and validate the effectiveness of proposed algorithms.

The prospects of utilizing single-carrier (SC) and multi-carrier (MC) waveforms in future terahertz (THz)-band communication systems remain unresolved. On the one hand, the limited multi-path components at high frequencies result in frequency-flat channels that favor low-complexity wideband SC systems. On the other hand, frequency-dependent molecular absorption and transceiver characteristics and the existence of multi-path components in indoor sub-THz systems can still result in frequency-selective channels, favoring off-the-shelf MC schemes such as orthogonal frequency-division multiplexing (OFDM). Variations of SC/MC designs result in different THz spectrum utilization, but spectral efficiency is not the primary concern with substantial available bandwidths; baseband complexity, power efficiency, and hardware impairment constraints are predominant. This paper presents a comprehensive study of SC/MC waveforms for THz communications, utilizing an accurate wideband THz channel model and highlighting the various performance and complexity trade-offs of the candidate schemes. Simulations demonstrate that discrete-Fourier-transform spread orthogonal time-frequency space (DFT-s-OTFS) achieves a lower peakto- average power ratio (PAPR) than OFDM and OTFS and enhances immunity to THz impairments and Doppler spreads, but at an increased complexity cost. Moreover, DFT-s-OFDM is a promising candidate that increases robustness to THz impairments and phase noise (PHN) at a low PAPR and overall complexity.

The rolling-out of 5G networks is recently including 5G Base Stations (BSs) operating on millimeter-Wave (mm-Wave) frequencies. The goal of this work is to shed light on the exposure assessment from commercial 5G mm-Wave 5G BSs, by focusing on the impact of downlink traffic on the exposure levels. To this aim, we adopt an innovative measurement framework, based on hardware and software components, able to satisfy the challenging measurement requirements of mm-Wave frequencies. In addition, we design a completely softwarized algorithm, called M-WAVE, in order to measure the mm-Wave exposure with a programmable spectrum analyzer. Results, obtained from a commercial 5G scenario, reveal that the exposure from the mm-Wave BS is directly proportional to the amount of traffic injected on the wireless link. However, the electric field is always lower than 0.08 V/m, while the downlink traffic is even larger than 800 Mbps.

Future non-terrestrial networks aim to achieve a throughput of Terabits/s. Therefore, free-space optical (FSO) communications have been adopted as a candidate solution due to their ability to achieve an extremely high data rate. Nonetheless, FSO communications are sensitive to the adverse effects of beam scintillation, beam-wander-induced pointing errors, free-space loss, and weather conditions. Space-air-ground (SAG) FSO transmission and hybrid single-hop (SH) FSO/radio frequency (RF) transmission are promising solutions to improve the performance of FSO links and can be integrated into a satellite communication (Satcom) system. In this work, we carry out a thorough capacity analysis of the resulting integrated SAG-FSO/SH-FSO/RF Satcom system, where Gamma-Gamma and Rician distributions are used to characterize FSO and RF links, respectively. The exact analytical expressions are derived and validated by Monte-Carlo simulations. We also obtain asymptotic expressions for the ergodic capacity in the high signal-to-noise ratio region. The numerical results highlight the significant potential of the integrated SAG-FSO/SH-FSO/RF Satcom system over existing solutions. We also show that the integrated Satcom system with intensity modulation and direct detection can achieve a capacity gain over that with a heterodyne detection technique over all satellite zenith angles.

The rolling-out of 5G antennas over the territory is a fundamental step to provide 5G connectivity. However, little efforts have been done so far on the exposure assessment from 5G cellular towers over young people and “sensitive” buildings, like schools and medical centers. To face such issues, we provide a sound methodology for the numerical evaluation of 5G (and pre-5G) downlink exposure over children, teenagers, schools and medical centers. We then apply the proposed methodology over two real scenarios. Results reveal that the exposure from 5G cellular towers will increase in the forthcoming years, in parallel with the growth of the 5G adoption levels. However, the exposure levels are well below the maximum ones defined by international regulations. Moreover, the exposure over children and teenagers is similar to the one of the whole population, while the exposure over schools and medical centers can be lower than the one of the whole set of buildings. Finally, the exposure from 5G is strongly lower than the pre-5G one when the building attenuation is introduced and a maturity adoption level for 5G is assumed.

The heterogeneity of optical wireless networks (OWNs) has expanded over decades in terms of services, node densities, mobility requirements, bandwidth needs, responsiveness, and physical device profile. Consequently, incorporating dynamic reconfigurability into future OWNs can satisfy their diverse realm of objectives. Towards this end, we provide our vision for the potential gains of integrating tunable optical elements in OWNs reflected in energy consumption reduction, coverage customization, data transfer rate boosting, highly accommodating multiple access schemes, enhancing physical layer security, supporting simultaneous services, and interference reduction. Finally, we speculate a roadmap for future research directions in tunable optics aided OWNs and the associated challenges with their deployment and operation.

This paper presents a secrecy performance analysis of a parallel free-space optical/millimeter-wave (mm-wave) communication system with a selection-combining receiver over a unified Fisher-Snedecor $\mathcal{F}$-distribution channel. The $\mathcal{F}$-distribution model, with the proper parameters, may be used to describe both the mm-wave and optical channels. The security performance is specifically evaluated by deriving closed-form expressions for the average secrecy capacity, secrecy outage probability, and strictly positive secrecy capacity. We examine the three following distinct security scenarios: 1) An FSO-link eavesdropping attack, 2) mm-wave-link eavesdropping attacks, and 3) eavesdropping attacks on FSO and mm-wave links at the same time. Furthermore, to better understand the influence of various system and channel parameters, asymptotic analysis is performed at high signal-to-noise ratio values. Our developed analytical expressions provide an efficient tool for examining the influence of various system and channel parameters on the secrecy performance, including the atmospheric turbulence severity, pointing errors of the FSO link, fading severity, the shadowing parameters, as well as the number of diversity branches of the mm-wave links. Monte-Carlo simulations are used to verify the correctness of the numerical findings.

The LoRaWAN standard comes from the low-power wide area network (LPWAN) technology suitable for developing Internet of Things (IoT) systems that are poised to disrupt the semiconductor industry. Even as a widespread technology used for diverse applications, security issues of long-range (LoRa) networks and devices remain a major challenge. Although the LoRa Alliance enhanced the security and the network architecture of LoRaWAN from version 1.0 to version 1.1, the last version still faces some drawbacks such as vulnerability to attacks. Some works have assessed LoRaWAN (v1.0 and v1.1) security risks and vulnerabilities. Moreover, all these specifications must coexist with each other, which makes compatibility an important factor in ensuring the sustainability of this technology. For this reason, we study the vulnerability of the LoRaWAN protocol in the context of compatibility. Hence, we consider four compatibility scenarios and possible cyber-attacks when connecting devices from the two mentioned versions. In this paper, we analyze the LoRaWAN architectures and then discuss the basic security concepts related to the compatibility scenarios between homogeneous or heterogeneous systems integrating the two LoRaWAN versions. After that, we investigate and identify the potential security risks and network vulnerabilities in LoRaWAN technology. We establish a catalog of vulnerabilities for LoRaWAN on a methodological framework. The catalog contains five vulnerabilities related to LoRaWAN v1.0.x and v1.1 and seven vulnerabilities related to LoRaWAN v1.0.x. Then, we check if these vulnerabilities could be applied to the compatibility scenarios. We observe that the majority of vulnerabilities mitigated in LoRaWAN v1.1 remain present in compatibility scenarios.

Solar energy is widely used for electricity generation, heating systems, and indoor environment daytime illumination. Indeed, large amounts of sunlight energy remain insufficiently used. In this work, we aim at employing sunlight energy for data transmission as a green option for wireless communications. Being emitted by an uncontrollable source, taming the sunlight is a challenging task that requires appropriate technologies to manipulate incident light. Liquid crystal devices are switchable glass technologies that have adequate response time and contrast characteristics for such an application. In this regard, we design a novel dual-cell liquid crystal shutter (DLS) by stacking two liquid crystal cells that operate in opposite manners, and we build our sunlight modulator with an array of DLSs. Then, we adopt time division multiplexing and polarization-based modulation to boost the data rate and eliminate the flickering effect. In addition, we provide mathematical modeling of the system and study its performance in terms of communication and energy consumption. Finally, we introduce some numerical results to examine the impact of multiple parameters on the system's performance and compare it with the state-of-the-art, which showed that our system features higher data rates and extended link ranges.

In this paper, we study the problem of topology optimization and routing in integrated access and backhaul (IAB) networks, as one of the promising techniques for evolving 5G networks. We study the problem from different perspectives. We develop efficient genetic algorithm-based schemes for both IAB node placement and non-IAB backhaul link distribution, and evaluate the effect of routing on bypassing temporal blockages. Here, concentrating on millimeter wave-based communications, we study the service coverage probability, defined as the probability of the event that the user equipments’ (UEs) minimum rate requirements are satisfied. Moreover, we study the effect of different parameters such as the antenna gain, blockage, and tree foliage on the system performance. Finally, we summarize the recent Rel-16 as well as the upcoming Rel-17 3GPP discussions on routing in IAB networks, and discuss the main challenges for enabling mesh-based IAB networks. As we show, with a proper network topology, IAB is an attractive approach to enable the network densification required by 5G and beyond.

This paper investigates the asymptotic behavior of the soft-margin and hard-margin support vector machine (SVM) classifiers for simultaneously high-dimensional and numerous data (large $n$ and large $p$ with $n/p\to \delta$) drawn from a Gaussian mixture distribution. Sharp predictions of the classification error rate of the hard-margin and soft-margin SVM are provided, as well as asymptotic limits of as such important parameters as the margin and the bias. As a further outcome, the analysis allows for the identification of the maximum number of training samples that the hard-margin SVM is able to separate. The precise nature of our results allows for an accurate performance comparison of the hard-margin and soft-margin SVM as well as a better understanding of the involved parameters (such as the number of measurements and the margin parameter) on the classification performance. Our analysis, confirmed by a set of numerical experiments, builds upon the convex Gaussian min-max Theorem, and extends its scope to new problems never studied before by this framework.

The Increasing number of smart devices in different forms and capabilities combined with the worldwide adoption of advanced multimedia applications are contributing to the significant growth of the mobile data traffic. The fifth generation (5G) and beyond-5G wireless networks aim at providing wireless connectivity with very high data rates, low latency, high reliability, and scalability, and will support the emerging Internet-of-Things (IoT) applications and services with massively interconnected devices [items 1), 2) in the Appendix].

First-order Marcum Q -function is observed in various problem formulations. However, it is not an easy-to-handle function. For this reason, in this article, we first present a semi-linear approximation of the Marcum Q -function. Our proposed approximation is useful because it simplifies, e.g., various integral calculations including Marcum Q -function as well as different operations such as parameter optimization. Then, as an example of interest, we apply our proposed approximation approach to the performance analysis of predictor antenna (PA) systems. Here, the PA system is referred to as a system with two sets of antennas on the roof of a vehicle. Then, the PA positioned in the front of the vehicle can be used to improve the channel state estimation for data transmission of the receive antenna that is aligned behind the PA. Considering spatial mismatch due to the mobility, we derive closed-form expressions for the instantaneous and average throughput as well as the throughput-optimized rate allocation. As we show, our proposed approximation scheme enables us to analyze PA systems with high accuracy. Moreover, our results show that rate adaptation can improve the performance of PA systems with different levels of spatial mismatch.

We propose two types of intelligent reflecting systems based on programmable metasurfaces and mirrors to focus the incident optical power towards a visible light communication receiver. We derive the required phase gradients for the metasurface array reflector and the required orientations of each mirror in the mirrors array reflector to achieve power focusing. Based on which, we derive the irradiance expressions for the two systems in the detector plane to characterize their performance in terms of aiming and focusing capabilities. We show analytically that the number of reflecting elements along with the relative source - reflector dimensions determine the system power focusing capability. Moreover, we quantify analytically the received power gain compared with reflector-free systems. In addition, we introduce a new simple metric to assess the relative reflectors' performance for a given source, detector, reflector layout. Finally, we verify the analytical findings regarding absolute and relative reflectors' performance via numerical simulations.

Deep learning (DL) has seen great success in the computer vision (CV) field, and related techniques have been used in security, healthcare, remote sensing, and many other areas. As a parallel development, visual data has become universal in daily life, easily generated by ubiquitous low-cost cameras. Therefore, exploring DL-based CV may yield useful information about objects, such as their number, locations, distribution, motion, etc. Intuitively, DL-based CV can also facilitate and improve the designs of wireless communications, especially in dynamic network scenarios. However, so far, such work is rare in the literature. The primary purpose of this article, then, is to introduce ideas about applying DL-based CV in wireless communications to bring some novel degrees of freedom to both theoretical research and engineering applications. To illustrate how DL-based CV can be applied in wireless communications, an example of using a DL-based CV with a millimeter-wave (mmWave) system is given to realize optimal mmWave multiple-input and multiple-output (MIMO) beamforming in mobile scenarios. In this example, we propose a framework to predict future beam indices from previously observed beam indices and images of street views using ResNet, 3-dimensional ResNext, and a long short-term memory network. The experimental results show that our frameworks achieve much higher accuracy than the baseline method, and that visual data can significantly improve the performance of the MIMO beamforming system. Finally, we discuss the opportunities and challenges of applying DL-based CV in wireless communications.