Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification

Global Navigation Satellite System (GNSS) positioning in urban environments remains challenging due to signal obstructions and reflections caused by tall buildings, trees, and overpasses. Non-Line-of-Sight (NLOS) propagation leads to significant positioning errors, making accurate classification of...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Nie, H. Yang
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1117/2025/isprs-archives-XLVIII-G-2025-1117-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850073984333250560
author S. Nie
H. Yang
author_facet S. Nie
H. Yang
author_sort S. Nie
collection DOAJ
description Global Navigation Satellite System (GNSS) positioning in urban environments remains challenging due to signal obstructions and reflections caused by tall buildings, trees, and overpasses. Non-Line-of-Sight (NLOS) propagation leads to significant positioning errors, making accurate classification of Line-of-Sight (LOS) and NLOS signals essential for robust GNSS performance. Machine learning (ML) techniques have been widely explored for NLOS/LOS classification, yet their effectiveness is constrained by data imbalance, as acquiring labeled NLOS data is more challenging than LOS data. This imbalance reduces model generalization, leading to biased predictions. To address this challenge, we propose an Attention-GAN framework for synthetic GNSS data generation, coupled with a transformer-based encoder to enhance feature extraction. The proposed Attention-GAN incorporates Multi-Head Self-Attention (MHA) in both its generator and discriminator to improve the quality of generated data. Using the UrbanNav dataset, we validate our approach by training various ML classifiers on augmented data and comparing their performance against conventional methods. Experimental results demonstrate that our approach effectively mitigates data imbalance, improves classification accuracy, and enhances GNSS positioning robustness in complex urban environments.
format Article
id doaj-art-0b855299ce9d4298963dfee75ec71c22
institution DOAJ
issn 1682-1750
2194-9034
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-0b855299ce9d4298963dfee75ec71c222025-08-20T02:46:40ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-20251117112210.5194/isprs-archives-XLVIII-G-2025-1117-2025Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS ClassificationS. Nie0H. Yang1Department of Geomatics Engineering, University of Calgary, Calgary, AB, CanadaDepartment of Geomatics Engineering, University of Calgary, Calgary, AB, CanadaGlobal Navigation Satellite System (GNSS) positioning in urban environments remains challenging due to signal obstructions and reflections caused by tall buildings, trees, and overpasses. Non-Line-of-Sight (NLOS) propagation leads to significant positioning errors, making accurate classification of Line-of-Sight (LOS) and NLOS signals essential for robust GNSS performance. Machine learning (ML) techniques have been widely explored for NLOS/LOS classification, yet their effectiveness is constrained by data imbalance, as acquiring labeled NLOS data is more challenging than LOS data. This imbalance reduces model generalization, leading to biased predictions. To address this challenge, we propose an Attention-GAN framework for synthetic GNSS data generation, coupled with a transformer-based encoder to enhance feature extraction. The proposed Attention-GAN incorporates Multi-Head Self-Attention (MHA) in both its generator and discriminator to improve the quality of generated data. Using the UrbanNav dataset, we validate our approach by training various ML classifiers on augmented data and comparing their performance against conventional methods. Experimental results demonstrate that our approach effectively mitigates data imbalance, improves classification accuracy, and enhances GNSS positioning robustness in complex urban environments.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1117/2025/isprs-archives-XLVIII-G-2025-1117-2025.pdf
spellingShingle S. Nie
H. Yang
Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
title_full Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
title_fullStr Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
title_full_unstemmed Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
title_short Attention-GANs: An Advanced GNSS Data Augmentation Method for Improved NLOS/LOS Classification
title_sort attention gans an advanced gnss data augmentation method for improved nlos los classification
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1117/2025/isprs-archives-XLVIII-G-2025-1117-2025.pdf
work_keys_str_mv AT snie attentiongansanadvancedgnssdataaugmentationmethodforimprovednloslosclassification
AT hyang attentiongansanadvancedgnssdataaugmentationmethodforimprovednloslosclassification