Site-Specific Finetuning of Neural Receivers with Real-World 5G NR Measurements

2026-03-10

AI Summary

This work addresses the lack of scenario-specific fine-tuning and validation of wireless neural receivers using real-world data. Leveraging the over-the-air testbed at ETH Zurich, the study presents the first site-specific fine-tuning and transfer learning of a neural receiver across three realistic 5G NR physical uplink shared channel (PUSCH) scenarios: laboratory, office, and high-mobility outdoor environments. Experimental results demonstrate consistent and significant bit error rate reductions across diverse user equipment hardware and deployment conditions. The observed performance gains align with prior findings based on synthetic data, while also confirming the model’s generalization capability across both deployment scenarios and hardware platforms. These findings provide empirical evidence supporting the practical deployment of neural receivers in real-world wireless systems.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: State Estimation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Finetuning wireless receivers to a specific deployment scenario can yield significant error-rate performance improvements without increasing processing complexity. However, site-specific finetuning has so far only been demonstrated on synthetic channel data and lacks real-world benchmarks. In this work, we empirically study site-specific finetuning of neural receivers using real-world 5G NR physical uplink shared channel (PUSCH) data collected with an over-the-air testbed at ETH Zurich across three scenarios: (i) a small laboratory, (ii) a large office floor, and (iii) a high-mobility outdoor environment. Our results confirm substantial error-rate performance improvements from site-specific finetuning, consistent with earlier findings based on synthetic channel data. Moreover, we demonstrate that these improvements generalize across different user-equipment hardware and deployment scenarios.

Problem

• site-specific finetuning
• neural receivers
• real-world 5G NR measurements
• error-rate performance
• deployment scenarios

Innovation

• site-specific finetuning
• neural receivers
• 5G NR
• real-world measurements
• PUSCH