Physics-Aware Generative Adversarial Networks for Radar-Based Human Activity Recognition
IEEE Transactions on Aerospace and Electronic Systems · 2023-06 · 59 (3) · 2994-3008
DOI: 10.1109/taes.2022.3221023 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2023-06. Verfasst von Mohammed Mahbubur Rahman und 2 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: NSF, Air Force Office of Scientific Research, University of Alabama Institutional Review Board.
Abstract (Originalsprache)
Generative adversarial networks (GANs) have recently been proposed for the synthesis of RF micro-Doppler signatures to address the issue of low sample support and enable the training of deeper neural networks (DNNs) for enhanced RF signal classification. But GANs suffer from systemic kinematic inconsistencies that decrease performance when GAN-synthesized data is used for training DNNs in human activity recognition. As a solution to this problem, this article proposes the design of a multibranch GAN (MBGAN), which integrates domain knowledge into its architecture, and physics-aware metrics based on correlation and curve-matching in the loss function. The quality of the synthetic samples generated is evaluated via image quality metrics, the ability to synthesize data that reflects human physical properties and generalize to broader subject profiles, and the achieved classification accuracy. Our experimental results show the proposed approach generates synthetic data for training that more accurately matches target kinematics, resulting in an increase of 9% in classification accuracy when classifying 14 different ambulatory human activities.
Förderung
- NSF
- Air Force Office of Scientific Research
- University of Alabama Institutional Review Board
Zitieren
APA
Rahman, M. M., Gurbuz, S. Z., & Amin, M. G. (2023). Physics-Aware Generative Adversarial Networks for Radar-Based Human Activity Recognition. IEEE Transactions on Aerospace and Electronic Systems, 59(3), 2994-3008. https://doi.org/10.1109/taes.2022.3221023
Vancouver
Rahman MM, Gurbuz SZ, Amin MG. Physics-Aware Generative Adversarial Networks for Radar-Based Human Activity Recognition. IEEE Transactions on Aerospace and Electronic Systems. 2023;59(3):2994-3008. doi:10.1109/taes.2022.3221023
BibTeX
@article{Rahman2023,
author = {Rahman, Mohammed Mahbubur and Gurbuz, Sevgi Z. and Amin, Moeness G.},
title = {Physics-Aware Generative Adversarial Networks for Radar-Based Human Activity Recognition},
journal = {IEEE Transactions on Aerospace and Electronic Systems},
year = {2023},
volume = {59},
number = {3},
pages = {2994--3008},
doi = {10.1109/taes.2022.3221023}
}
EUVIMED