EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Calibrated Multi-Dimensional Evaluation Framework for Diffusion-Based Radio Frequency Signal Generation

Qian Li iD, Xin Xiang, Yuan Liang iD, Hu Mao

Sensors · 23.07.2026 · 26 (15) · 4694

DOI: 10.3390/s26154694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.07.2026. Verfasst von Qian Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Aviation Engineering School, Air Force Engineering University, No. 1 Baling Road, Baqiao District, Xi'an 710000, China. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Evaluation of generative models for RF (Radio Frequency) signals remains largely ad hoc, with existing approaches relying on uncalibrated metrics imported from computer vision without systematic justification or baseline establishment. We present a multi-dimensional, distribution-level evaluation framework comprising ten metrics across six layers, calibrated against real-real baselines. A real-real baseline is computed by splitting authentic signals into two independent subsets and measuring the same metric between them; the resulting value sets the achievable ceiling for that metric, against which generated-vs-real scores are normalized. The framework is grounded in four design principles: distribution-level aggregation, real-real baseline normalization, signal-to-noise ratio (SNR)-modulation stratification, and multi-dimensional coverage. Application of the framework reveals two previously unreported phenomena. First, linear Short-Time Fourier Transform preprocessing creates a gradient imbalance between frequency-domain and time-domain loss components that causes catastrophic generation failure for analog amplitude modulation; logarithmic compression resolves this. Second, the widely adopted noise-prediction training objective exhibits systematic gradient suppression for amplitude-modulated signals due to SNR-dependent implicit loss weighting; switching to signal-prediction substantially improves temporal structure fidelity for amplitude-modulated signals, with only modest trade-offs for digital communication signals. The framework and calibration methodology establish reproducible standards for comparative assessment of RF generative models.

Schlagwörter

Stichwörter der Autor:innen

autocorrelation functiondiffusion modelsevaluation frameworkradio frequency signal generationsensor systemsshort-time Fourier transformtraining objective parameterization

Autor:innen und Institutionen

  • Aviation Engineering School, Air Force Engineering University, No. 1 Baling Road, Baqiao District, Xi'an 710000, China.

ORCID-Profile: Qian Li, Yuan Liang

Zitieren

APA

Li, Q., Xiang, X., Liang, Y., & Mao, H. (2026). A Calibrated Multi-Dimensional Evaluation Framework for Diffusion-Based Radio Frequency Signal Generation. Sensors, 26(15), 4694. https://doi.org/10.3390/s26154694

Vancouver

Li Q, Xiang X, Liang Y, Mao H. A Calibrated Multi-Dimensional Evaluation Framework for Diffusion-Based Radio Frequency Signal Generation. Sensors. 2026;26(15):4694. doi:10.3390/s26154694

BibTeX
@article{Li2026,
  author = {Li, Qian and Xiang, Xin and Liang, Yuan and Mao, Hu},
  title = {A Calibrated Multi-Dimensional Evaluation Framework for Diffusion-Based Radio Frequency Signal Generation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4694},
  doi = {10.3390/s26154694}
}
Kostenlos starten →