arXiv subjects

Shafi Ullah Khan

Publications and source records attributed to Shafi Ullah Khan.

3 recordsLinked to original sources

arXiv2026

PERFECT: Personalized Federated Learning for CBRS Radar Detection

The Citizens Broadband Radio Service (CBRS) band is pivotal for expanding next-generation wireless services, but its success hinges on robustly protecting incumbent users, such as naval radar systems, from interference. This task is delegated to a network of Environmental Sensing Capability (ESC) sensors, which must detect faint radar signals amidst heavy co-channel interference from commercial LTE and 5G users. Traditional centralized detection models raise significant data privacy concerns and are ill-suited for the Non-Independent and Identically Distributed (non-IID) nature of data from geographically dispersed sensors. To overcome these limitations, we propose a novel Federated Learning (FL) framework PERFECT that leverages ESC level personalization for robust and efficient radar detection. PERFECT preserves privacy by training models locally on ESC sensors. Furthermore, our framework is the first to effectively handle non-IID scenarios through model personalization where different ESCs observe distinct radar types. We demonstrate through extensive simulations that PERFECT achieves the mandated 99% recall for radar detection, matching centralized performance while significantly enhancing privacy, efficiency, and scalability for dynamic spectrum sharing.

cs.NI↗

arXiv2025

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

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.

cs.NI↗

arXiv2025

Waves of Imagination: Unconditional Spectrogram Generation using Diffusion Architectures

The growing demand for effective spectrum management and interference mitigation in shared bands, such as the Citizens Broadband Radio Service (CBRS), requires robust radar detection algorithms to protect the military transmission from interference due to commercial wireless transmission. These algorithms, in turn, depend on large, diverse, and carefully labeled spectrogram datasets. However, collecting and annotating real-world radio frequency (RF) spectrogram data remains a significant challenge, as radar signals are rare, and their occurrences are infrequent. This challenge makes the creation of balanced datasets difficult, limiting the performance and generalizability of AI models in this domain. To address this critical issue, we propose a diffusion-based generative model for synthesizing realistic and diverse spectrograms of five distinct categories that integrate LTE, 5G, and radar signals within the CBRS band. We conduct a structural and statistical fidelity analysis of the generated spectrograms using widely accepted evaluation metrics Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR), to quantify their divergence from the training data. Furthermore, we demonstrate that pre-training on the generated spectrograms significantly improves training efficiency on a real-world radar detection task by enabling $51.5\%$ faster convergence.

cs.NI↗