Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning

Global Positioning System (GPS) has been used in many aerial and terrestrial high precision positioning applications. Multipath affects positioning and navigation performance. This paper proposes a convolutional neural network based carrier-phase multipath detection method. The method is based on th...

Full description

Bibliographic Details
Main Authors: Quan, Yiming, Lau, Lawrence, Roberts, Gethin Wyn, Meng, Xiaolin, Zhang, Chao
Format: Article
Language:English
Published: MDPI 2018
Subjects:
Online Access:https://eprints.nottingham.ac.uk/55854/
_version_ 1848799228142288896
author Quan, Yiming
Lau, Lawrence
Roberts, Gethin Wyn
Meng, Xiaolin
Zhang, Chao
author_facet Quan, Yiming
Lau, Lawrence
Roberts, Gethin Wyn
Meng, Xiaolin
Zhang, Chao
author_sort Quan, Yiming
building Nottingham Research Data Repository
collection Online Access
description Global Positioning System (GPS) has been used in many aerial and terrestrial high precision positioning applications. Multipath affects positioning and navigation performance. This paper proposes a convolutional neural network based carrier-phase multipath detection method. The method is based on the fact that the features of multipath characteristics in multipath contaminated data can be learned and identified by a convolutional neural network. The proposed method is validated with simulated and real GPS data and compared with existing multipath mitigation methods in position domain. The results show the proposed method can detect about 80% multipath errors (i.e., recall) in both simulated and real data. The impact of the proposed method on positioning accuracy improvement is demonstrated with two datasets, 18–30% improvement is obtained by down-weighting the detected multipath measurements. The focus of this paper is on the development and test of the proposed convolutional neural network based multipath detection algorithm.
first_indexed 2025-11-14T20:32:20Z
format Article
id nottingham-55854
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:32:20Z
publishDate 2018
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling nottingham-558542019-01-08T09:06:25Z https://eprints.nottingham.ac.uk/55854/ Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning Quan, Yiming Lau, Lawrence Roberts, Gethin Wyn Meng, Xiaolin Zhang, Chao Global Positioning System (GPS) has been used in many aerial and terrestrial high precision positioning applications. Multipath affects positioning and navigation performance. This paper proposes a convolutional neural network based carrier-phase multipath detection method. The method is based on the fact that the features of multipath characteristics in multipath contaminated data can be learned and identified by a convolutional neural network. The proposed method is validated with simulated and real GPS data and compared with existing multipath mitigation methods in position domain. The results show the proposed method can detect about 80% multipath errors (i.e., recall) in both simulated and real data. The impact of the proposed method on positioning accuracy improvement is demonstrated with two datasets, 18–30% improvement is obtained by down-weighting the detected multipath measurements. The focus of this paper is on the development and test of the proposed convolutional neural network based multipath detection algorithm. MDPI 2018-12-17 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/55854/1/remotesensing-10-02052-v3.pdf Quan, Yiming, Lau, Lawrence, Roberts, Gethin Wyn, Meng, Xiaolin and Zhang, Chao (2018) Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning. Remote Sensing, 10 (12). 2052/1-2052/18. ISSN 2072-4292 Global Positioning System (GPS); Convolutional Neural Network (CNN); multipath detection; machine learning; high precision positioning http://dx.doi.org/10.3390/rs10122052 doi:10.3390/rs10122052 doi:10.3390/rs10122052
spellingShingle Global Positioning System (GPS); Convolutional Neural Network (CNN); multipath detection; machine learning; high precision positioning
Quan, Yiming
Lau, Lawrence
Roberts, Gethin Wyn
Meng, Xiaolin
Zhang, Chao
Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title_full Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title_fullStr Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title_full_unstemmed Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title_short Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning
title_sort convolutional neural network based multipath detection method for static and kinematic gps high precision positioning
topic Global Positioning System (GPS); Convolutional Neural Network (CNN); multipath detection; machine learning; high precision positioning
url https://eprints.nottingham.ac.uk/55854/
https://eprints.nottingham.ac.uk/55854/
https://eprints.nottingham.ac.uk/55854/