activity
20242026
collaborators

6 papers

eess.SP2026

Comprehensive Review of Deep Unfolding Techniques for Next-Generation Wireless Communication Systems

Sukanya Deka, Kuntal Deka, Nhan Thanh Nguyen +3

The application of machine learning in wireless communications has been extensively explored, with deep unfolding emerging as a powerful model-based technique. Deep unfolding enhan…

cs.IT2025

End-to-end Learning of Probabilistic and Geometric Constellation Shaping with Iterative Receivers

Harindu Jayarathne, Dileepa Marasinghe, Nandana Rajatheva +1

An end-to-end learning method for constellation shaping with a shaping-encoder assisted transceiver architecture is presented. The shaping encoder, which produces shaping bits with…

eess.SP2025

Max-Min Fairness for Stacked Intelligent Metasurface-Assisted Multi-User MISO Systems

Nipuni Ginige, Prathapasinghe Dharmawansa, Arthur Sousa de Sena +3

Stacked intelligent metasurface (SIM) is an emerging technology that uses multiple reconfigurable surface layers to enable flexible wave-based beamforming. In this paper, we focus…

cs.LG2025

A CNN-based End-to-End Learning for RIS-assisted Communication System

Nipuni Ginige, Nandana Rajatheva, Matti Latva-aho

Reconfigurable intelligent surface (RIS) is an emerging technology that is used to improve the system performance in beyond 5G systems. In this letter, we propose a novel convoluti…

cs.NI2025

Towards Specialized Wireless Networks Using an ML-Driven Radio Interface

Kamil Szczech, Maksymilian Wojnar, Katarzyna Kosek-Szott +8

Future wireless networks will need to support diverse applications (such as extended reality), scenarios (such as fully automated industries), and technological advances (such as t…

eess.SP2024

Efficient Channel Prediction for Beyond Diagonal RIS-Assisted MIMO Systems with Channel Aging

Nipuni Ginige, Arthur Sousa de Sena, Nurul Huda Mahmood +2

Novel reconfigurable intelligent surface (RIS) architectures, known as beyond diagonal RISs (BD-RISs), have been proposed to enhance reflection efficiency and expand RIS capabiliti…