Uncrewed Aerial Vehicles (UAVs) are increasingly used in civilian and industrial applications, making secure low-altitude operations crucial. In dense mmWave environments, accurately classifying low-altitude UAVs as either inside authorized or restricted airspaces remains challenging, requiring models that handle complex propagation and signal variability. This paper proposes a deep learning model, referred to as CoBA, which stands for integrated Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention which leverages Fifth Generation (5G) millimeter-wave (mmWave) radio measurements to classify UAV operations in authorized and restricted airspaces at low altitude. The proposed CoBA model integrates convolutional, bidirectional recurrent, and attention layers to capture both spatial and temporal patterns in UAV radio measurements. To validate the model, a dedicated dataset is collected using the 5G mmWave network at TalTech, with controlled low altitude UAV flights in authorized and restricted scenarios. The model is evaluated against conventional ML models and a fingerprinting-based benchmark. Experimental results show that CoBA achieves superior accuracy, significantly outperforming all baseline models and demonstrating its potential for reliable and regulated UAV airspace monitoring.

This study examines the impact of User Equipment (UE)-to-Next Generation Node Base (gNB) synchronization on Time of Flight (ToF)-based localization in 5th generation (5 G) networks. First, a method for measuring the UE-to-gNB overall ToF delay is introduced, leveraging the Timing Advance (TA) command and Sounding Reference Signals (SRSs). The impact of key synchronization factors, such as clock drift and reception/transmission (RX/TX) timing delays, on ToF measurements and positioning accuracy is thoroughly analyzed. To quantify the effect of these localization impairments on 3GPP-compliant devices, an experimental campaign was conducted using the OpenAirInterface (OAI) platform. Field data were collected to assess errors in UE-to-gNB distance estimation. The results show that after estimating and compensating for RX/TX timing delays, the distance error remains within 3.8 m in 95% of cases in a line-of-sight (LoS) urban scenario.

As the deployment of fifth generation (5G) mobile wireless networks continues to gain momentum, researchers are already focusing on the challenges and opportunities of the next sixth generation (6G). To meet the ever-increasing demand for higher data rates and support the development of new services, 6G is expected to exploit millimeter wave (mmWave) frequencies. However, the complex propagation characteristics at mmWave require beamforming technology, which introduces significant complexity in the communication system. Herein, we propose a real-time testbed platform to evaluate beamforming and other communication solutions designed for multiple-input multiple-output (MIMO) mmWave-based 6G networks. This platform serves as an enabler for 6G technologies evaluation under realistic propagation conditions, accelerating the development and deployment of robust and efficient 6G networks. To demonstrate the capabilities of our platform, we have implemented a smart relay with real-time beam control and tracking. The platform is able to perform an exhaustive search of 64 reception beams in less than 256 μs. Additionally, the platform can maintain the optimal beam even in mobility scenarios using a gradient-based tracking system that achieves a low overhead of less than 5%, with an update rate of 100 Hz.

Integrated sensing and communication (ISAC) systems are recognized as one of the key ingredients of the sixth generation (6G) network. A challenging topic in ISAC is the design of a single waveform combining both communication and sensing functionalities on the same time-frequency-space resources, allowing tuning the performance of both with partial or full hardware sharing. This paper proposes a dual-domain waveform design approach that superposes onto the frequency-time (FT) domain both the legacy orthogonal frequency division multiplexing (OFDM) signal and a sensing one, purposely designed in the delay-Doppler domain. With a proper power downscaling of the sensing signal w.r.t. OFDM, it is possible to exceed regulatory bandwidth limitations proper of legacy multicarrier systems to increase the sensing performance while leaving communication substantially unaffected. Numerical and experimental results prove the effectiveness of the dual-domain waveform, notwithstanding a power abatement of at least 30 dB of the signal used for sensing compared to the one used for communication. The dual-domain ISAC waveform outperforms both OFDM and orthogonal time-frequency-space (OTFS) in terms of Cramér-Rao bound on delay estimation (up to 20 dB), thanks to its superior resolution, with a negligible penalty on the achievable rate.

Recently, Unmanned Aerial Vehicles (UAVs) have been deployed in various logistics and surveillance applications. Sixth-Generation (6G) cellular networks can further enhance communications to provide ubiquitous coverage, low-latency control, and seamless connectivity among the UAVs. However, achieving constant and end-to-end 3D coverage for user devices is demanding. UAV s have limited battery capacity; thus, energy consumption should be efficiently managed. Optimizing the UAV trajectories improves network performance by diminishing Base Station (BS) load or covering areas with limited radio access. Hence, we propose a Swarm Clustering and Double-Deep-Q-Network (SC-DDQN) framework for efficient communication in aerial networks. The framework constitutes a novel SC- Particle Swarm Optimization (SC-PSO) to improve intra-UAV communication and an Intelligent Trajectory Optimization (ITO) sub-component to optimize Air-to-Ground (A2G) trajectories. The results show that the proposed SC-DDQN framework achieves 40 % faster clustering and a 1.2 % failure probability of reaching a destination compared to the conventional systems, thus providing optimal clustering and trajectory for UAV communications.

Recently, communication in cellular networks assisted by Unmanned Aerial Vehicles (UAVs) has attracted considerable attention, as it provides wireless connectivity to devices in areas with poor coverage. With a single UAV deployed, it is difficult to achieve Line-of-Sight (LoS) probability and network availability targets for critical Ultra-Reliable Low-Latency Communication (URLLC) applications while meeting cost and system complexity requirements. To harness the advantages of UAVs in these situations, an alternative solution is to deploy a multi-UAV system, exploiting inter-connectivity to maintain uninterrupted communication with a ground transmitter. The idea is to deploy a fixed UAV on the side of a building rooftop, which acts as a relay between the ground transmitter and the flying UAV base station, thus increasing the LoS probability. Notably, a two-hop amplify-and-forward relay can provide significant improvements in the channel capacity, channel gain, and thus overall quality of service. In our study, simulations were carried out in four general environments as specified by ITU-R, namely Suburban, Urban, Dense Urban, and High Rise Urban, based on data collected in Los Angeles, USA. Numerical results demonstrate that two-hop communication via a relay UAV increases LoS probability in all environments, thus improving system reliability and feasibility.

Unmanned Aerial Vehicles (UAVs) can be used as low altitude platforms in several applications. In this paper, we propose their use to localize a ground Radio Frequency (RF) emitter by collecting measures of the Received Signal Strength Indicator (RSSI) at different positions. The main contribution of the work consists in the definition of an experimental setup for the simultaneous measures of RSSI and receiver position. The RSSI is measured by an actual transceiver, the Adalm Pluto Software Defined Radio (SDR) development board, programmed with the open-source software GNU Radio. The position is provided by GPS and Inertial Measuring Unit (IMU) sensors on the drone. The measures are acquired in the 865MHz Short Range Device (SRD) and 2.4 GHz Industrial Scientific Medical (ISM) unlicensed frequency bands. Since the ISM measures can be affected by interference generated by different sources (e.g. Wi-Fi access points and UAV controller), the SRD band is exploited for collecting the RSSI measures with less interference. A maximum likelihood (ML) algorithm is applied to the collected data for estimating the transmitter location. For the considered setup we show that the mean absolute localization error is around 4m without interference and 5m with interference. A threshold-based technique is proposed to improve the accuracy in presence of interference.

The high mobility of Unmanned Aerial Vehicles (UAVs) and their capability to rapidly deploy Aerial Base Stations (ABS) in areas where the terrestrial network becomes unavailable is a key enabler for Public Safety Networks. In our work we introduce a model in order to identify Line of Sight (LoS) and Non-Line of Sight (NLoS) conditions for User Equipments (UEs) that attempt a connection to an ABS through the Physical Random Access Channel (PRACH) based on Convolutional Neural Networks (CNNs). Our method limits the number of antennas employed with respect to other methods that were developed for traditional approaches, while achieving higher than 80% accuracy for SNR of -20 dB. Finally, we study the impact of UAV’s height on the accuracy of our method and we compare it with typical computationally efficient methods based on the delay spread with and without the aid of beamforming.

Wireless Sensor Network (WSN) technologies provide advantages that allow them to replace traditional wired systems in an ever growing number of applications. This paper describes the design of a WSN for mission critical applications such as the case of avionics, in which data collected from the sensors can be delivered to a cloud application through multiple independent gateways, thereby increasing data availability in presence of failures. Since the same data might be distributed along multiple paths, system-wide synchronization must be provided in order to guarantee data consistency. A heartbeat protocol is introduced along each path in order to guarantee timely detection of any single failure. We present a solution that can be implemented using open source software and commercial off-the-shelf hardware, which makes this approach viable for networks with a large number of heterogeneous sensors. Results reported in this paper show some sample measurements as well as the performance evaluation for our heartbeat algorithm in terms of latency between a failure and a full recovery of the system.

In mission critical wireless sensor networks (WSNs) accurate timestamping of the occurrence of events measured by the sensor nodes is often required together with a high degree of reliability. While precise timestamping requires synchronization of the sensor nodes, reliability is obtained by adding redundancy in all potential single point of failure nodes. In this paper, we focus on a ZigBee-based WSN using two personal area network (PAN) coordinators with different PAN identifiers (IDs) and, for this configuration, we propose a solution where if the primary PAN coordinator goes down, connections are transferred to the other by changing the PAN ID of the nodes. Our proposed solution provides significant gains in terms of recovery speed and timing synchronization accuracy in comparison to a solution that is proposed in the literature.