Tasos Dagiuklas

This paper investigates a uncrewed aerial vehicles (UAV)-assisted cell-free architecture for vehicular networks in road-constrained environments. Roads are modeled using a Poisson Line Process (PLP), with multi-layer roadside access points (APs) deployed via 1-D Poisson Point Process (PPP). Each user forms a localized cell-free cluster by associating with the nearest AP in each layer along its corresponding road. This forms a road-constrained cell-free architecture. To enhance coverage, UAV act as an aerial tier, extending access from 1-D road-constrained layouts (embedded in 2-D) to 3-D. We employ a Matérn Hard-Core (MHC) point process to model the spatial distribution of UAV base stations, ensuring a minimum safety distance between them. In order to enable tractable analysis of the aggregate signal from multiple APs, a distance-based power control scheme is introduced. Leveraging tools from stochastic geometry, we have studied the coverage probability. Furthermore, we analyze the impact of key system parameters on coverage performance, providing useful insights into the deployment and optimization of UAV-assisted cell-free vehicular networks.

Maximizing area spectral efficiency (ASE) is essential for improving the performance of uncrewed aerial vehicles (UAV) base stations (BSs) in future 6G networks. However, the high computational complexity of UAV deployment in realistic urban environments poses a significant challenge. This paper proposes an optimization framework for deploying UAV-BSs as aerial access points that directly serve ground user equipment (UE) over three-dimensional (3-D) terrains. To reduce complexity, the original ASE maximization problem is transformed into maximizing the line-of-sight (LoS) coverage between UAV and UE, based on their strong correlation. LoS coverage is estimated through a query mechanism without requiring full network information, UAV hovering points are identified via an Improved Snake Optimization (ISO) algorithm, and UAV trajectories are optimized using Dijkstra's algorithm combined with the Travelling Salesman Problem (TSP). Simulation results have shown that the proposed method attains near-optimal ASE, staying within $\sim 5\%$ of an ASE-targeted optimizer, while substantially reducing computational complexity and converging in minimum $\sim 50$ iterations. Compared with the Snake Optimizatio (SO) baseline, it delivers an additional maximum $\sim 6\%$ LoS coverage gain. Performance evaluation across four urban terrain scenarios confirms the robustness and adaptability of the proposed solution. While higher UAV altitudes increase LoS probability, the benefit is offset by the larger path loss due to longer links; by contrast, increasing the number of UAV hovering points expands LoS coverage and yields consistent ASE gains. Across benchmarks and terrains, the proposed method achieves higher LoS coverage and more stable performance, demonstrating its effectiveness for UAV-enabled network optimization.

The integration of terrestrial and non-terrestrial networks is essential for reliable, secure, and ubiquitous connectivity with QoS guarantees, and is a key enabler for supporting emerging applications like in-flight broadband connectivity and mission-critical operations, though several challenges remain. This paper compares three architectural options for providing in-flight broadband connectivity: a DU/CU functional split with the DU on the aircraft and the CU on the ground; a similar split enhanced with integrated access and backhauling to enable 3GPP-compliant flying ad-hoc networks; and a novel architecture in which aircraft act as mobile wireless access and backhaul nodes hosting MEC capabilities for low-latency services and local breakout, a flexible approach that requires sophisticated SON functions and optimised routing.

Federated Learning (FL) has emerged as a powerful paradigm, allowing multiple decentralized clients to collaboratively train a machine learning model without sharing their raw data. When combined with Multi-access Edge Computing (MEC), it enhances the utilization of computation and storage resources at the edge, enabling local data training on edge nodes. Such integration reduces latency and facilitates real-time processing and decision-making while ensuring data privacy. However, this decentralized approach introduces security and trust challenges, as models can be compromised through data poisoning attacks, such as label flipping attacks. The trustworthiness of these edge nodes and the integrity of their data are critical for performance and reliability of FL models. This paper introduces an adaptive zero trust framework that, by default, does not assume any edge node as trustworthy. It continuously validates edge data before each training round and checks its model to ensure that only reliable contributors are included in the global model aggregation. The results of the proposed framework reduce the impact of malicious nodes, maintaining the global model accuracy even in scenarios with high numbers of malicious edge nodes, showcasing its robustness and reliability.

This letter investigates the jamming attack in the physical broadcast channel (PBCH) of the fifth generation (5G) new radio (NR) that conveys critical information of the cell called master information block (MIB). Since smart attack on PBCH is simply possible using the information of synchronization signal block (SSB) that is unencrypted during the initial access, this channel is one of the most effective choices from a jammer’s point of view. In this study, we propose a hypothesis test to detect the presence of a jamming attack in the PBCH block and, furthermore, we estimate the principal direction of the attacked PBCH demodulation reference signal (PBCH DMRS) that significantly deviates under that attack. These achievements are also presented in the form of semi-definite programming (SDP) relaxation. PBCH DMRS is located at 25% of the PBCH block and is vital for PBCH extraction to initiate a radio connection between user and an appropriate cell. Simulation results evaluate the proposed method in various aspects and prove its superiority over the recent competing methods.

The primary aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been developed by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system’s performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide a standardized evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low-light environments, image compression, and object occlusions.

Indoor positioning is a core enabler for various 5G identity and context-aware applications requiring precise and real-time simultaneous localisation and mapping (SLAM). In this work, we propose a K-nearest neighbours and deep neural network (K-DNN) algorithm to improve 3D indoor positioning. Our implementation uses a novel data-augmentation concept for the received signal strength (RSS)-based fingerprint technique to produce a 3D fused hybrid. In the offline phase, a machine learning (ML) approach is used to train a model on a radiomap dataset that is collected during the offline phase. The proposed algorithm is implemented on the constructed hybrid multi-layered radiomap to improve the 3D localisation accuracy. In our implementation, the proposed approach is based on the fusion of the prominent 5G IoT signals of Bluetooth Low Energy (BLE) and the ubiquitous WLAN. As a result, we achieved a 91% classification accuracy in 1D and a submeter accuracy in 2D.

6G networks can support global, ubiquitous and seamless connectivity through the convergence of terrestrial and non-terrestrial networks (NTNs). Unlike terrestrial scenarios, NTNs pose unique challenges including propagation characteristics, latency and mobility, owing to the operations in spaceborne and airborne platforms. To overcome all these technical hurdles, this survey paper presents the use of artificial intelligence (AI) techniques in learning and adapting to the complex NTN environments. We begin by providing an overview of NTNs in the context of 6G, highlighting the potential security and privacy issues. Next, we review the existing AI methods adopted for 6G NTN optimization, starting from machine learning (ML), through deep learning (DL) to deep reinforcement learning (DRL). All these AI techniques have paved the way towards more intelligent network planning, resource allocation (RA), and interference management. Furthermore, we discuss the challenges and opportunities in AI-powered NTN for 6G networks. Finally, we conclude by providing insights and recommendations on the key enabling technologies for future AI-powered 6G NTNs.

The developments on next generation IoT sensing devices, with the advances on their low power computational capabilities and high speed networking has led to the introduction of the edge computing paradigm. Within an edge cloud environment, services may generate and consume data locally, without involving cloud computing infrastructures. Aiming to tackle the low computational resources of the IoT nodes, Virtual-Function-Chain has been proposed as an intelligent distribution model for exploiting the maximum of the computational power at the edge, thus enabling the support of demanding services. An intelligent migration model with the capacity to support Virtual-Function-Chains is introduced in this work. According to this model, migration at the edge can support individual features of a Virtual-Function-Chain. First, auto-healing can be implemented with cold migrations, if a Virtual Function fails unexpectedly. Second, a Quality of Service monitoring model can trigger live migrations, aiming to avoid edge devices overload. The evaluation studies of the proposed model revealed that it has the capacity to increase the robustness of an edge-based service on low-powered IoT devices. Finally, comparison with similar frameworks, like Kubernetes, showed that the migration model can effectively react on edge network fluctuations.