Skip to content
New
Recent Research Updates || Accepted at GLOBECOM 2026: RIS-Aided Near-Field mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting || Accepted at IMAS 2026: A Machine Learning-Assisted Beamformer Controller for Channel-Driven Analogue Beamforming || Accepted at UCMMT 2026: Experimental Validation of Localisation in RIS-Assisted mmWave Networks || Published at AP-S/URSI 2026: Near Field-Aware UE Localization in RIS-Aided Wireless Networks Through ML-Regressor
Tarek Hassan
Research portfolio

Building intelligent wireless futures

My work brings machine learning, reconfigurable electromagnetic environments, and rigorous evaluation together for next-generation communication and sensing systems.

17
Published works
3
Accepted in 2026
6G
Current frontier

Focus areas

Research themes

View publications

Intelligent wireless systems

Learning-driven methods for adaptive, resilient communication networks.

ML/DL6GResource management

RIS-assisted localization

Near-field-aware localization and beam management in reconfigurable environments.

RISmmWaveBeam sweeping

Communication & sensing

Designing electromagnetic environments where communication and sensing work together.

ISACBeamformingLocalization

Edge intelligence

QoS- and fairness-aware computation offloading for edge-enabled networks.

MECDRLQoS

Evolution

Research journey

A progression from 5G resource management to intelligent, RIS-assisted 6G systems.

Current researchFeb 2025 – Present

Intelligent AI Electromagnetic Environment for Communication and Sensing within 6G

Queen's University Belfast (QUB)

Developing learning-enabled RIS architectures for localization, beam management, and integrated sensing in 6G environments.

  • RIS-assisted ML beam sweeping and user localization.
  • Intelligent electromagnetic-environment design for communication and sensing.
  • Simulation- and experiment-led evaluation of performance and robustness.
Master's researchSep 2021 – Dec 2024

Machine Learning Driven Mobile Edge Computing for Connectivity and QoS in Next Generation Networks

Rajshahi University of Engineering & Technology (RUET)

Explored machine-learning-based decisions for efficient and equitable mobile-edge computing networks.

  • ML-driven computation-offloading strategies in MEC networks.
  • QoS and fairness-aware decision-making under network constraints.
  • Comparative study of KNN, order-preserving, and DRL optimization methods.
Undergraduate researchJan 2016 – Mar 2021

Radio Resource Management in 5G Heterogeneous Networks

Rajshahi University of Engineering & Technology (RUET)

Established a foundation in resource allocation, scheduling, and channel modelling for 5G/mmWave systems.

  • Resource allocation and MAC scheduling in 5G/mmWave settings.
  • Spatial consistency, blockage, and outdoor-to-indoor channel-model considerations.
  • Performance evaluation of scheduling and transport-layer behaviour.