Fine-tuning a pre-trained GNN-based precoder on real D-MIMO CSI data from the Techtile testbed yields a 15.7% gain in multi-user scenarios and near-MRT performance in single-user cases with under 0.7 bits/channel use degradation on unseen positions.
Callebaut et al.,Usrp b210 based synchronization measure- ments, GitHub repository, techtile-by-dramco/NI-B210-Sync, Ac- cessed: 2025-09-08
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Testbed Evaluation of AI-based Precoding in Distributed MIMO Systems
Fine-tuning a pre-trained GNN-based precoder on real D-MIMO CSI data from the Techtile testbed yields a 15.7% gain in multi-user scenarios and near-MRT performance in single-user cases with under 0.7 bits/channel use degradation on unseen positions.