Pushing the Boundaries in CBRS Band: Robust Radar Detection within High 5G Interference

2025-10-11

AI Summary

To address severe interference from 5G communications to military radar systems in the Citizens Broadband Radio Service (CBRS) band, this work proposes a robust machine learning–based radar detection and waveform classification method. The approach jointly exploits raw IQ samples and spectrogram features within a deep neural network architecture to enable reliable radar signal detection and six-class radar waveform identification under high-interference conditions. Key contributions include reducing the required signal-to-interference-plus-noise ratio (SINR) threshold for reliable radar detection from the FCC-mandated 20 dB to −5 dB—surpassing the prior 12 dB performance bottleneck while maintaining 99% detection accuracy. Evaluated on both synthetic and real-world measurements, the method achieves 99% radar detection accuracy and 93% waveform classification accuracy. This advancement significantly enhances spectrum-sharing feasibility and provides a validated technical pathway for dynamic coexistence between 5G and radar systems in the CBRS band.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Spectrum sharing is a critical strategy for meeting escalating user demands via commercial wireless services, yet its effective regulation and technological enablement, particularly concerning coexistence with incumbent systems, remain significant challenges. Federal organizations have established regulatory frameworks to manage shared commercial use alongside mission-critical operations, such as military communications. This paper investigates the potential of machine learning (ML)-based approaches to enhance spectrum sharing capabilities within the Citizens Broadband Radio Service (CBRS) band, specifically focusing on the coexistence of commercial signals (e.g., 5G) and military radar systems. We demonstrate that ML techniques can potentially extend the Federal Communications Commission (FCC)-recommended signal-to-interference-plus-noise ratio (SINR) boundaries by improving radar detection and waveform identification in high-interference environments. Through rigorous evaluation using both synthetic and real-world signals, our findings indicate that proposed ML models, utilizing In-phase/Quadrature (IQ) data and spectrograms, can achieve the FCC-recommended $99%$ radar detection accuracy even when subjected to high interference from 5G signals upto -5dB SINR, exceeding the required limits of $20$ SINR. Our experimental studies distinguish this work from the state-of-the-art by significantly extending the SINR limit for $99%$ radar detection accuracy from approximately $12$ dB down to $-5$ dB. Subsequent to detection, we further apply ML to analyze and identify radar waveforms. The proposed models also demonstrate the capability to classify six distinct radar waveform types with $93%$ accuracy.

Problem

• Enhancing radar detection in CBRS band with 5G interference
• Improving spectrum sharing between commercial and military systems
• Extending SINR limits for radar detection using ML

Innovation

• Machine learning enhances radar detection in CBRS
• ML extends SINR boundaries for radar identification
• Models use IQ data and spectrograms for classification