Bayesian Learning-Assisted Compressive Sensing Improves Multi-Target Parameter Estimation in 5G-NR Inspired ISAC
IEEE Open Journal of Vehicular Technology · 2026 · 7 · 1576-1586
DOI: 10.1109/ojvt.2026.3697606 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Vehicular Technology, 2026. Verfasst von Prabhanshu Yadav und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IIT Jodhpur's Research, Science and Engineering Research Board, Telecom Technology Development Fund.
Abstract (Originalsprache)
Integrated sensing and communication (ISAC) has emerged as a key technology for 6G communication systems, enabling both spectrum and hardware sharing between radar and communication systems. In this paper, we present a 5G New Radio (5G-NR) inspired ISAC system that enhances sensing accuracy and robustness by smartly combining various standard reference symbol outputs in a multi-target scenario. Toward this, we first formulate a novel multiple measurement vector (MMV)-based sparse signal recovery (SSR)-aided compressive sensing (CS) problem, which employs multiple subcarriers and symbols in the time-frequency grid of 5G-NR for improved velocity and range profile estimation. Next we propose an MMV Bayesian learning (BL) algorithm, which leverages the simultaneous-sparse structure of velocity/range profiles for enhanced profile estimation from compressed pilot outputs. Our analysis is supported by extensive simulation results confirming that the proposed technique outperforms the existing state-of-the-art algorithms, in the most critical low signal-to-noise ratio (SNR) regime.
Förderung
- IIT Jodhpur's Research
- Science and Engineering Research Board
- Telecom Technology Development Fund
- DST and UKRI-EPSRC
- India-U.K. Joint opportunity in Telecommunications Research
- Engineering and Physical Sciences Research Council
- Platform for Driving Ultimate Connectivity
- PerCom
Zitieren
APA
Yadav, P., Singh, K. K., Srivastava, S., & Hanzo, L. (2026). Bayesian Learning-Assisted Compressive Sensing Improves Multi-Target Parameter Estimation in 5G-NR Inspired ISAC. IEEE Open Journal of Vehicular Technology, 7, 1576-1586. https://doi.org/10.1109/ojvt.2026.3697606
Vancouver
Yadav P, Singh KK, Srivastava S, Hanzo L. Bayesian Learning-Assisted Compressive Sensing Improves Multi-Target Parameter Estimation in 5G-NR Inspired ISAC. IEEE Open Journal of Vehicular Technology. 2026;7:1576-1586. doi:10.1109/ojvt.2026.3697606
BibTeX
@article{Yadav2026,
author = {Yadav, Prabhanshu and Singh, Kunal Kumar and Srivastava, Suraj and Hanzo, Lajos},
title = {Bayesian Learning-Assisted Compressive Sensing Improves Multi-Target Parameter Estimation in 5G-NR Inspired ISAC},
journal = {IEEE Open Journal of Vehicular Technology},
year = {2026},
volume = {7},
pages = {1576--1586},
doi = {10.1109/ojvt.2026.3697606}
}
EUVIMED