Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation

Zekun Zhang; Penghui Xu; Guohao Zhang; Li Ta Hsu

doi:10.1109/ITSC57777.2023.10422660

Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation

Zekun Zhang
, Penghui Xu
, Guohao Zhang
, Li Ta Hsu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

2 Citations (Scopus)

Abstract

Accurate and reliable GNSS solutions are essential for the development of intelligent transportation systems. However, GNSS signals can be easily blocked by buildings in urban areas, resulting in the sole reception of the reflected signal with large errors, namely non-line-of-sight (NLOS) receptions. Thus, it is necessary to classify the visible satellite measurements from NLOS receptions before conducting positioning. This paper aims to design a Transformer-based deep learning network to utilize the spatial correlations between satellites for their visibility classification. The proposed method achieves about 89 percent classification accuracy in validation and test data. By exploring the spatial correlation between satellites in the attention matrix of Transformer, we reveal the mechanism of deep learning network on satellite visibility classification.

Original language	English
Title of host publication	2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5969-5975
Number of pages	7
ISBN (Electronic)	9798350399462
DOIs	https://doi.org/10.1109/ITSC57777.2023.10422660
Publication status	Published - Sept 2023
Event	26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023 - Bilbao, Spain Duration: 24 Sept 2023 → 28 Sept 2023

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
ISSN (Print)	2153-0009
ISSN (Electronic)	2153-0017

Conference

Conference	26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023
Country/Territory	Spain
City	Bilbao
Period	24/09/23 → 28/09/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Attention Mechanism
Deep Learning
GNSS
NLOS
Transformer

ASJC Scopus subject areas

Automotive Engineering
Mechanical Engineering
Computer Science Applications

More information

10.1109/ITSC57777.2023.10422660

Cite this

Zhang, Z., Xu, P., Zhang, G., & Hsu, L. T. (2023). Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660 (pp. 5969-5975). (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC57777.2023.10422660

Zhang, Zekun ; Xu, Penghui ; Zhang, Guohao et al. / Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation. 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 5969-5975 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

@inproceedings{24d7e6645fb34feb9e0a8c17cd1a2791,

title = "Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation",

abstract = "Accurate and reliable GNSS solutions are essential for the development of intelligent transportation systems. However, GNSS signals can be easily blocked by buildings in urban areas, resulting in the sole reception of the reflected signal with large errors, namely non-line-of-sight (NLOS) receptions. Thus, it is necessary to classify the visible satellite measurements from NLOS receptions before conducting positioning. This paper aims to design a Transformer-based deep learning network to utilize the spatial correlations between satellites for their visibility classification. The proposed method achieves about 89 percent classification accuracy in validation and test data. By exploring the spatial correlation between satellites in the attention matrix of Transformer, we reveal the mechanism of deep learning network on satellite visibility classification.",

keywords = "Attention Mechanism, Deep Learning, GNSS, NLOS, Transformer",

author = "Zekun Zhang and Penghui Xu and Guohao Zhang and Hsu, \{Li Ta\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023 ; Conference date: 24-09-2023 Through 28-09-2023",

year = "2023",

month = sep,

doi = "10.1109/ITSC57777.2023.10422660",

language = "English",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5969--5975",

booktitle = "2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660",

}

Zhang, Z, Xu, P, Zhang, G & Hsu, LT 2023, Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation. in 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Institute of Electrical and Electronics Engineers Inc., pp. 5969-5975, 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023, Bilbao, Spain, 24/09/23. https://doi.org/10.1109/ITSC57777.2023.10422660

Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation. / Zhang, Zekun; Xu, Penghui; Zhang, Guohao et al.
2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660. Institute of Electrical and Electronics Engineers Inc., 2023. p. 5969-5975 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation

AU - Zhang, Zekun

AU - Xu, Penghui

AU - Zhang, Guohao

AU - Hsu, Li Ta

PY - 2023/9

Y1 - 2023/9

N2 - Accurate and reliable GNSS solutions are essential for the development of intelligent transportation systems. However, GNSS signals can be easily blocked by buildings in urban areas, resulting in the sole reception of the reflected signal with large errors, namely non-line-of-sight (NLOS) receptions. Thus, it is necessary to classify the visible satellite measurements from NLOS receptions before conducting positioning. This paper aims to design a Transformer-based deep learning network to utilize the spatial correlations between satellites for their visibility classification. The proposed method achieves about 89 percent classification accuracy in validation and test data. By exploring the spatial correlation between satellites in the attention matrix of Transformer, we reveal the mechanism of deep learning network on satellite visibility classification.

AB - Accurate and reliable GNSS solutions are essential for the development of intelligent transportation systems. However, GNSS signals can be easily blocked by buildings in urban areas, resulting in the sole reception of the reflected signal with large errors, namely non-line-of-sight (NLOS) receptions. Thus, it is necessary to classify the visible satellite measurements from NLOS receptions before conducting positioning. This paper aims to design a Transformer-based deep learning network to utilize the spatial correlations between satellites for their visibility classification. The proposed method achieves about 89 percent classification accuracy in validation and test data. By exploring the spatial correlation between satellites in the attention matrix of Transformer, we reveal the mechanism of deep learning network on satellite visibility classification.

KW - Attention Mechanism

KW - Deep Learning

KW - GNSS

KW - NLOS

KW - Transformer

UR - https://www.scopus.com/pages/publications/85186501552

U2 - 10.1109/ITSC57777.2023.10422660

DO - 10.1109/ITSC57777.2023.10422660

M3 - Conference article published in proceeding or book

AN - SCOPUS:85186501552

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 5969

EP - 5975

BT - 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023

Y2 - 24 September 2023 through 28 September 2023

ER -

Zhang Z, Xu P, Zhang G , Hsu LT. Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 https://doi.org/10.1109/ITSC57777.2023.10422660. Institute of Electrical and Electronics Engineers Inc. 2023. p. 5969-5975. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC57777.2023.10422660

Intelligent GNSS Satellite Visibility Classification in Urban Areas: A Deep Learning Approach with Interpretation

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this