Vasileios Panagiotis Rekkas

Dr. Vasileios Panagiotis Rekkas

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 November 2021 in Electronics
Verified
Journal Article
Open access
PDF file
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
SSSotirios Sotiroudis
Sotirios Sotiroudis
Panagiotis SarigiannidisPanagiotis Sarigiannidis
Panagiotis Sarigiannidis
Shaohua WanShaohua Wan
Shaohua Wan
George K. KaragiannidisGeorge K. Karagiannidis
George K. Karagiannidis
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
Artificial Intelligence (AI) and especially Machine Learning (ML) can play a very important role in realizing and optimizing 6G network applications. In this paper, we present a brief summary of ML methods, as well as an up-to-date review of ML approaches in 6G wireless communication systems. These methods include supervised, unsupervised and reinforcement techniques. Additionally, we discuss open issues in the field of ML for 6G networks and wireless communications in general, as well as some potential future trends to motivate further research into this area.

24 October 2023 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
LILazaros Alexios Iliadis
Lazaros Alexios Iliadis
SSSotirios Sotiroudis
Sotirios Sotiroudis
Achilles D. BoursianisAchilles D. Boursianis
Achilles D. Boursianis
Panagiotis SarigiannidisPanagiotis Sarigiannidis
Panagiotis Sarigiannidis
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
Indoor communication and positioning are significant fields of applications for indoor Internet of Things (IoT) given the rapid growth of IoT in smart cities, smart grids, and smart industries. Visible light positioning (VLP) has become more and more attractive for researchers to provide indoor location-aware IoT services. Additionally, artificial intelligence (AI) has attracted considerable research effort to address the challenges in visible-light communication (VLC) systems. This is an emerging technology in next-generation wireless networks. However, despite the rapid progress, the use of AI in localization, navigation, and position estimation is still underexplored in VLC systems, and various research challenges are still open. This methodological review summarizes the research efforts regarding the use of AI in the field of VLP, to improve the position estimation accuracy in both two-dimensional (2D) and three-dimensional (3D) indoor IoT applications. This treatise also presents open issues and potential future directions for motivating further research in the field. Various databases were utilized in this paper: Scopus, Google Scholar, and IEEE Xplore; obtained 88 papers from 2017 to early 2023. Most (68%) of the AI articles in VLP systems are machine learning (ML) methods applied for localization and position estimation in VLC systems, while the other 32% of the research articles focussed on evolutionary algorithms. ML and evolutionary models may present limitations in terms of complexity and time-consuming nature but offer highly accurate, robust, reliable, and cost-effective results in terms of position estimation over conventional approaches.

7 August 2024 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
SSSotirios Sotiroudis
Sotirios Sotiroudis
LILazaros Alexios Iliadis
Lazaros Alexios Iliadis
SBSander Bastiaens
Sander Bastiaens
Wout JosephWout Joseph
Wout Joseph
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
Optical wireless communication (OWC) is emerging as a pivotal technology for next-generation broadcast networks, with visible light communication (VLC) poised to meet the escalating demands of advanced radio frequency systems. This study focuses on enhancing visible light positioning (VLP), recognized for its precision, simplicity, and cost-effectiveness, which are essential for accurate indoor localization and responsive location-based services. Central to our approach is the integration of advanced machine learning (ML) techniques, which fundamentally transform the accuracy and efficiency of 3D indoor positioning systems. We introduce an advanced VLP framework where ML is leveraged not merely as an adjunct but as the primary driver of innovation, significantly refining the processing of received signal strength (RSS) indicators. The methodology centers around a system comprising four light-emitting diodes (LEDs) arranged in a star geometry, optimized for precise spatial localization. We evaluate three distinct methodologies: a foundational star-shaped configuration for baseline position estimation, a repeated unit cell strategy to extend the four-LED configuration to a larger positioning area, and a sophisticated implementation employing Nyström kernel approximation. This integration of Nyström approximation into our ML framework drastically enhances the system’s predictive accuracy, achieving an exceptional average relative root mean square error (aRRMSE) of 2.1 cm in a simulated setup. The results demonstrate that ML, especially combined with the application of the Nyström kernel approximation, significantly elevates the precision and operational efficiency of traditional VLP systems, setting new benchmarks for accuracy in indoor 3D positioning technologies and fostering advancements towards more sophisticated and adaptable communication networks.

23 September 2025 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
SSSotirios Sotiroudis
Sotirios Sotiroudis
Zaharias ZaharisZaharias Zaharis
Zaharias Zaharis
GKGeorgios P. Koudouridis
Georgios P. Koudouridis
Panagiotis SarigiannidisPanagiotis Sarigiannidis
Panagiotis Sarigiannidis
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
The exponential increase in wireless device usage, combined with a burgeoning demand for bandwidth-intensive applications, underscores the need for significant enhancements in network infrastructure, particularly within the realms of fifth-generation (5G) and beyond 5G (B5G) technologies. These enhancements must effectively address comprehensive network coverage, minimize latency, and improve overall efficiency. Consequently, this requires the deployment of advanced methodologies aimed at optimizing network performance, which poses complex challenges for network managers and operators. The adoption of machine learning (ML) techniques offers a formidable framework for predictive analytics in this domain, to effectively and efficiently improve network performance. This research paper explores the application of various boosting ML methodologies, with a focus on the creation of radio environmental maps (REMs). We use a new boosting method, namely the Gaussian Process Boosting (GPBoost) that has not yet been applied to an electromagnetics problem. Moreover, we solve a multi-output problem and present a model that can be used to predict both reference signal received power (RSRP) and reference signal received quality (RSRQ). This analytical approach enables accurate forecasting of critical network metrics that are crucial to evaluate network quality and operational efficiency. This study uses measurement data from the literature conducted on both 4G and 5G networks. The initial findings indicate that these methodologies considerably improve the accuracy of the predicted network performance metrics.

27 September 2023
Verified
Conference Paper
Closed access
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
SSSotirios Sotiroudis
Sotirios Sotiroudis
PSPanagiotis Sarigiannids
Panagiotis Sarigiannids
Kostas PsannisKostas Psannis
Kostas Psannis
George K. KaragiannidisGeorge K. Karagiannidis
George K. Karagiannidis
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
Millimeter-wave (mm-wave) and terahertz (THz) communication systems can satisfy the high data rate requirements in 5G, 6G, and beyond networks, but still rely on the use of extensive antenna arrays to guarantee sufficient received signal strength. Many antennas incur high beam training overhead; thus, the narrow beams require adjustment to support highly mobile applications. Deep learning (DL) vision-aided solutions can potentially forecast the optimal beams, leveraging raw RGB images captured at the base station. Image filtering techniques have been widely used in computer vision (CV) to modify and enhance the quality of an image, based on specific rules. This work applies different filters to RGB images for accurate mm-wave/THz beam prediction and feature extraction based on pre-trained convolutional neural networks (CNNs). The assessment of the developed framework is conducted on an actual dataset captured by an unmanned aerial vehicle (UAV) operating in the millimeter-wave (mm-wave) frequency range. The dataset comprises RGB images taken at the base station. Ensemble filtering techniques are also studied, enhancing the beam prediction accuracy of two state-of-the-art (SOTA) DL models.

2 March 2026 in Technologies
Verified
Journal Article
Open access
PDF file
VRVasileios Panagiotis Rekkas
Vasileios Panagiotis Rekkas
Leandro dos Santos CoelhoLeandro dos Santos Coelho
Leandro dos Santos Coelho
Viviana Cocco MarianiViviana Cocco Mariani
Viviana Cocco Mariani
APAdamantini Peratikou
Adamantini Peratikou
Sotirios K.  GoudosSotirios K. Goudos
Sotirios K. Goudos
Accurate estimation of wireless propagation characteristics is essential for guiding the design and deployment of fifth-generation (5G) communication systems. As network demand increases and 5G infrastructure is introduced in progressive phases, reliable path loss (PL) prediction models are required to refine deployment strategies and improve network efficiency. Conventional propagation models frequently display limited flexibility when applied to diverse environmental conditions and often entail considerable computational expense, reducing their practicality for large-scale 5G planning. Recent developments in data-centric artificial intelligence (AI) have enabled more adaptive and analytically powerful approaches to propagation modeling, resulting in notable gains in PL prediction accuracyThis study employs a comprehensive dataset produced using the NYUSIM channel simulator, integrating a wide spectrum of atmospheric parameters and seasonal variations within South Asian urban microcell environments, complemented by broad empirical observations. The core objective is to construct, optimize, and evaluate four machine learning (ML) models capable of accurately predicting PL at high-frequency bands critical to 5G performance. A fully automated hyperparameter tuning pipeline, based on the Optuna framework, is applied to twelve regression algorithms, including advanced ensemble methods, regularized linear techniques, and classical baseline models. Performance assessment emphasizes predictive reliability, stability, and cross-model generalization. Furthermore, statistical analysis utilizing bootstrap confidence intervals and paired t-tests indicates that all ML methods perform equivalently (p > 0.4), while SHapley Additive exPlanations (SHAP) analysis across all models supports a consistent feature importance distribution, supporting the statistical analysis results. To showcase the superiority of the ML approaches, a comparison with conventional free-space PL modeling methods is presented, with the AI methodology demonstrating robust performance across seasonal variations and a 95.3% improvement.