Spectral fingerprint recognition of mobile signals via Rydberg atomic sensors
Abstract
Rydberg-atom sensors have emerged as a promising quantum technology for broadband radio-frequency detection owing to their intrinsic calibration, wide frequency coverage, and high sensitivity. However, their potential for intelligent identification of real-world wireless signals remains largely unexplored. Here, we demonstrate a quantum-enabled framework for mobile signal classification based on Rydberg electromagnetically induced transparency spectroscopy and deep learning. Three types of wireless emissions, including cellular voice call, Wi-Fi, and 5G signals from three commercial smartphone brands, are measured to construct a spectral-fingerprint dataset. A convolutional neural network trained on this dataset achieves an initial baseline classification accuracy of 93.44\%. To compensate for spectral drifts induced by temporal and environmental variations, a progressive fine-tuning strategy is employed to continuously adapt the pretrained model, enabling robust classification across diverse deployment scenarios. Furthermore, continuous real-time monitoring is demonstrated under dynamically varying wireless conditions, including cellular voice call, Wi-Fi, and their coexistence. The proposed system achieves an overall frame-level recognition accuracy of 87.67\% over a 60-s measurement. These results establish a pathway toward intelligent quantum radio-frequency sensing and highlight the potential of Rydberg-atom platforms for real-time wireless signal awareness and spectrum monitoring.
Related
- Characteristics of VHF and UHF band detection using Stark shifting in Rydberg-atom sensors
- A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint Recognition
- Profiling a Rydberg-Atom Electric Field Sensor for Off-Resonant Detection of Sub-100 MHz RF Signals
- Motion-state recognition of satellite active components based on high-frequency photometric signals
- Modelling Fourier filtering wavefront sensors for power spectral density-based methods: The AOPERA tool
BibTeX
@misc{yin2026spectral,
title = {{Spectral fingerprint recognition of mobile signals via Rydberg atomic sensors}},
author = {Yi-Ming Yin and Ming-Yao Cui and Ling-Yu Du and Jin-Hang Fang and Luan-Yi Wei and Bang Liu and Li-Hua Zhang and Kai Wang and Kai-Bin Huang and Dong-Sheng Ding},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35301},
eprint = {2610.35301},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35301},
}
RIS
TY - UNPB
TI - Spectral fingerprint recognition of mobile signals via Rydberg atomic sensors
AU - Yi-Ming Yin
AU - Ming-Yao Cui
AU - Ling-Yu Du
AU - Jin-Hang Fang
AU - Luan-Yi Wei
AU - Bang Liu
AU - Li-Hua Zhang
AU - Kai Wang
AU - Kai-Bin Huang
AU - Dong-Sheng Ding
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35301
UR - https://arxiv.org/abs/2610.35301
AB - Rydberg-atom sensors have emerged as a promising quantum technology for broadband radio-frequency detection owing to their intrinsic calibration, wide frequency coverage, and high sensitivity. However, their potential for intelligent identification of real-world wireless signals remains largely unexplored. Here, we demonstrate a quantum-enabled framework for mobile signal classification based on Rydberg electromagnetically induced transparency spectroscopy and deep learning. Three types of wireless emissions, including cellular voice call, Wi-Fi, and 5G signals from three commercial smartphone brands, are measured to construct a spectral-fingerprint dataset. A convolutional neural network trained on this dataset achieves an initial baseline classification accuracy of 93.44\%. To compensate for spectral drifts induced by temporal and environmental variations, a progressive fine-tuning strategy is employed to continuously adapt the pretrained model, enabling robust classification across diverse deployment scenarios. Furthermore, continuous real-time monitoring is demonstrated under dynamically varying wireless conditions, including cellular voice call, Wi-Fi, and their coexistence. The proposed system achieves an overall frame-level recognition accuracy of 87.67\% over a 60-s measurement. These results establish a pathway toward intelligent quantum radio-frequency sensing and highlight the potential of Rydberg-atom platforms for real-time wireless signal awareness and spectrum monitoring.
ER -