Tharmalingam Ratnarajah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tharmalingam Ratnarajah has a total of 167 co-authors. Here are the top co-authors by number of shared publications:
- Navneet Garg
Institute for Digital Communications, The University of Edinburgh, Edinburgh, U.K.
26 shared publications - Mathini Sellathurai
School of Engineering and Physical Sciences, Institute of Sensors Signals and Systems, Heriot-Watt University, Edinburgh, U.K.
22 shared publications - Sudip Biswas
Indian Institute of Information Technology Guwahati
11 shared publications - Christos Masouros
University College London
10 shared publications - Anastasios Papazafeiropoulos
Communications and Intelligent Systems Research Group, University of Hertfordshire, Hatfield AL10 9AB, UK
9 shared publications - Haifeng Luo
Institute for Digital Communications, School of Engineering, The University of Edinburgh, Edinburgh, U.K.
9 shared publications
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (5) , 13-15
Fluid Antenna System for Future Wireless Networks
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (5) , 13-15
Fluid Antenna System for Future Wireless Networks
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Magazine
- Vol. PP (25763180) , 1-8
Multi-Source Semantic Communication and Denoising for Non-Terrestrial Networks: Fundamentals, Framework, and Challenges
6G non-terrestrial networks (NTNs) will strengthen global Earth observation (EO) by linking low Earth orbit (LEO) satellite constellations, high altitude platforms (HAPs), and unmanned aerial vehicles (UAVs). However, long paths, intermittent links, and tight spectrum make traditional bit-centric pipelines brittle and bandwidth-heavy. Traditional semantic communication (SC) approaches also fall short because they rely on a single-source processing and degrade severely under low signal-to-noise ratio (SNR), multi-hop, and noisy orbital conditions. Therefore, we present a unified multi-source SC with an intelligent denoising framework that transmits meaning rather than raw symbols, fuses complementary features from multiple satellites, and restores semantics in the presence of noise. We first discuss the fundamentals of the unified multi-source SC with an intelligent denoising framework. Then, we explain our proposed framework in detail. Our framework couples the multi-hop inter-satellite delivery of compact semantic features with transformer-based denoising to maintain fidelity at low SNR and receiver-side image merging and large language model (LLM)-assisted semantic refinement to assemble overlapping segments into a coherent EO product aligned with a shared knowledge base. As a proof of concept, we present a case study on EO image delivery over LEO satellite, which shows improved robustness and bandwidth efficiency relative to conventional SC without denoising and traditional communications, with higher peak SNR (PSNR) and multi-scale structural similarity index (MS-SSIM), and reduced loss across SNR regimes. Finally, we provide several open challenges and conclude the paper.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Magazine
- Vol. PP (25763180) , 1-8
Multi-Source Semantic Communication and Denoising for Non-Terrestrial Networks: Fundamentals, Framework, and Challenges
6G non-terrestrial networks (NTNs) will strengthen global Earth observation (EO) by linking low Earth orbit (LEO) satellite constellations, high altitude platforms (HAPs), and unmanned aerial vehicles (UAVs). However, long paths, intermittent links, and tight spectrum make traditional bit-centric pipelines brittle and bandwidth-heavy. Traditional semantic communication (SC) approaches also fall short because they rely on a single-source processing and degrade severely under low signal-to-noise ratio (SNR), multi-hop, and noisy orbital conditions. Therefore, we present a unified multi-source SC with an intelligent denoising framework that transmits meaning rather than raw symbols, fuses complementary features from multiple satellites, and restores semantics in the presence of noise. We first discuss the fundamentals of the unified multi-source SC with an intelligent denoising framework. Then, we explain our proposed framework in detail. Our framework couples the multi-hop inter-satellite delivery of compact semantic features with transformer-based denoising to maintain fidelity at low SNR and receiver-side image merging and large language model (LLM)-assisted semantic refinement to assemble overlapping segments into a coherent EO product aligned with a shared knowledge base. As a proof of concept, we present a case study on EO image delivery over LEO satellite, which shows improved robustness and bandwidth efficiency relative to conventional SC without denoising and traditional communications, with higher peak SNR (PSNR) and multi-scale structural similarity index (MS-SSIM), and reduced loss across SNR regimes. Finally, we provide several open challenges and conclude the paper.
- Open Access
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48212-48221
NOMA-Enabled UAV Trajectory Optimization Using Deep Reinforcement Learning for Efficient IoT Data Collection
Non-orthogonal multiple access (NOMA) is a promising technology for future networks because it can allow many sensors to connect and share the same resources at the same time. This provides a spectrally efficient method in situations where spectrum is limited but number of sensors are enormous. In this paper, we extend NOMA to unmanned aerial vehicles (UAVs) to solve their limited flight time issue while collecting data from sensors that are distributed randomly across an open field. The objective of this study is to design an efficient UAV trajectory planning scheme that maximizes the total collected sensor data within the available flight time. To achieve this, We model the UAV trajectory optimization as a Markov Decision Process and employ a Deep Q-Network (DQN) to adaptively select UAV movements. A novel reward function is designed to simultaneously guide the UAV toward sensor locations, avoid unnecessary detours, and enhance data collection efficiency under uplink NOMA. Simulation results demonstrate that the proposed NOMA-enabled DQN framework achieves up to 93.5% average data collection, offering an improvement of approximately 19% compared to the traditional TDMA-based approach, while requiring no retraining when the sensor distribution varies.
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48212-48221
Open AccessNOMA-Enabled UAV Trajectory Optimization Using Deep Reinforcement Learning for Efficient IoT Data Collection
Non-orthogonal multiple access (NOMA) is a promising technology for future networks because it can allow many sensors to connect and share the same resources at the same time. This provides a spectrally efficient method in situations where spectrum is limited but number of sensors are enormous. In this paper, we extend NOMA to unmanned aerial vehicles (UAVs) to solve their limited flight time issue while collecting data from sensors that are distributed randomly across an open field. The objective of this study is to design an efficient UAV trajectory planning scheme that maximizes the total collected sensor data within the available flight time. To achieve this, We model the UAV trajectory optimization as a Markov Decision Process and employ a Deep Q-Network (DQN) to adaptively select UAV movements. A novel reward function is designed to simultaneously guide the UAV toward sensor locations, avoid unnecessary detours, and enhance data collection efficiency under uplink NOMA. Simulation results demonstrate that the proposed NOMA-enabled DQN framework achieves up to 93.5% average data collection, offering an improvement of approximately 19% compared to the traditional TDMA-based approach, while requiring no retraining when the sensor distribution varies.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 16372-16386
Scalable Nonconvex Optimization for Dual-Function Radar–Communication Beamforming
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 16372-16386
Scalable Nonconvex Optimization for Dual-Function Radar–Communication Beamforming
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 30, 3678-3682
Graph Over the Grid: A Spatial K -Nearest Neighbor Approach to Modulation Recognition in OTFS
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 30, 3678-3682
Graph Over the Grid: A Spatial K -Nearest Neighbor Approach to Modulation Recognition in OTFS
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4807-4811
A Lorentzian Dispersion Model for Stacked Intelligent Metasurfaces
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4807-4811
A Lorentzian Dispersion Model for Stacked Intelligent Metasurfaces
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 13142-13156
A Robust Design for Power Minimization in Uplink BackCom Assisted Hybrid NOMA With Bounded Channel Error Sets
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 13142-13156
A Robust Design for Power Minimization in Uplink BackCom Assisted Hybrid NOMA With Bounded Channel Error Sets
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25, 18669-18684
Federated Dropout: Convergence Analysis and Resource Allocation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25, 18669-18684
Federated Dropout: Convergence Analysis and Resource Allocation
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 28, 3710-3750
Quantum Machine Learning for 6G Space–Air–Ground Integrated Networks: A Comprehensive Tutorial and Survey
Space-air-ground integrated networks (SAGINs) are emerging as a fundamental architecture for 6G systems to enable massive connectivity, novel applications, extreme data rates, ultra-low latency, and multi-dimensional networking. The complex nature of SAGINs has driven researchers to explore classical machine learning (CML) as a powerful tool for modeling and optimizing these multi-layer networks. Although CML offers many benefits, it will suffer from exponential complexity for SAGIN design, mainly due to high-dimensional data and problem spaces. Therefore, the NP-hard problems are challenging for CML to enable SAGINs efficiently. To address this critical challenge, we present a comprehensive survey examining the integration of quantum ML (QML) with SAGINs. We systematically evaluate quantum-enhanced SAGIN technologies through detailed performance metrics and create a new classification system for hybrid network architectures. We thoroughly examine key integration strategies and analyze major technical challenges, which include how quantum states degrade in space, how to distribute resources optimally, and how to develop security protocols. We show how QML can solve the growing complexity of 6G networks by improving network capacity, intelligence, and security. The research also creates a comprehensive framework for quantum-enhanced SAGINs that researchers and industry professionals can use as a guide when developing next-generation communication systems. Our findings examine the transformative potential of QML in reshaping global communications infrastructure, which presents a structured approach to navigating the intricate challenges of advanced networking technologies and also provides a critical pathway for addressing the exponentially growing computational demands of future communication ecosystems.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 28, 3710-3750
Quantum Machine Learning for 6G Space–Air–Ground Integrated Networks: A Comprehensive Tutorial and Survey
Space-air-ground integrated networks (SAGINs) are emerging as a fundamental architecture for 6G systems to enable massive connectivity, novel applications, extreme data rates, ultra-low latency, and multi-dimensional networking. The complex nature of SAGINs has driven researchers to explore classical machine learning (CML) as a powerful tool for modeling and optimizing these multi-layer networks. Although CML offers many benefits, it will suffer from exponential complexity for SAGIN design, mainly due to high-dimensional data and problem spaces. Therefore, the NP-hard problems are challenging for CML to enable SAGINs efficiently. To address this critical challenge, we present a comprehensive survey examining the integration of quantum ML (QML) with SAGINs. We systematically evaluate quantum-enhanced SAGIN technologies through detailed performance metrics and create a new classification system for hybrid network architectures. We thoroughly examine key integration strategies and analyze major technical challenges, which include how quantum states degrade in space, how to distribute resources optimally, and how to develop security protocols. We show how QML can solve the growing complexity of 6G networks by improving network capacity, intelligence, and security. The research also creates a comprehensive framework for quantum-enhanced SAGINs that researchers and industry professionals can use as a guide when developing next-generation communication systems. Our findings examine the transformative potential of QML in reshaping global communications infrastructure, which presents a structured approach to navigating the intricate challenges of advanced networking technologies and also provides a critical pathway for addressing the exponentially growing computational demands of future communication ecosystems.