{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T17:23:55Z","timestamp":1774286635304,"version":"3.50.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T00:00:00Z","timestamp":1683763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Global Navigation Satellite System (GNSS) multipath has always been extensively researched as it is one of the hardest error sources to predict and model. External sensors are often used to remove or detect it, which transforms the process into a cumbersome data set-up. Thus, we decided to only use GNSS correlator outputs to detect a large-amplitude multipath, on Galileo E1-B and GPS L1 C\/A, using a convolutional neural network (CNN). This network was trained using 101 correlator outputs being used as a theoretical classifier. To take advantage of the strengths of convolutional neural networks for image detection, images representing the correlator output values as a function of delay and time were generated. The presented model has an F score of 94.7% on Galileo E1-B and 91.6% on GPS L1 C\/A. To reduce the computational load, the number of correlator outputs and correlator sampling frequency was then decreased by a factor of 4, and the convolutional neural network still has an F score of 91.8% on Galileo E1-B and 90.5% on GPS L1 C\/A.<\/jats:p>","DOI":"10.3389\/frobt.2023.1106439","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T07:09:37Z","timestamp":1683875377000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Using convolutional neural networks to detect GNSS multipath"],"prefix":"10.3389","volume":"10","author":[{"given":"Anthony","family":"Guillard","sequence":"first","affiliation":[]},{"given":"Paul","family":"Thevenon","sequence":"additional","affiliation":[]},{"given":"Carl","family":"Milner","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,5,11]]},"reference":[{"key":"B1","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"12th USENIX symposium on operating systems design and implementation","author":"Abadi","year":"2016"},{"key":"B2","article-title":"Deep learning using rectified linear units (relu)","author":"Agarap","year":"2018"},{"key":"B3","article-title":"Indoor multipath characterization and separation using distortions in gps receiver correlation peaks","author":"Bellad","year":"2013"},{"key":"B4","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/mits.2013.2263460","article-title":"A new modeling based on urban trenches to improve GNSS positioning quality of service in cities","volume":"5","author":"B\u00e9taille","year":"2013","journal-title":"Intell. Transp. Syst. Mag. IEEE"},{"key":"B5","doi-asserted-by":"publisher","first-page":"100167","DOI":"10.1016\/j.array.2022.100167","article-title":"A novel image representation of gnss correlation for deep learning multipath detection","volume":"14","author":"Blais","year":"2022","journal-title":"Array"},{"key":"B6","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1007\/978-3-319-42928-1_15","article-title":"Multipath","volume-title":"Springer handbook of global navigation satellite systems, chapter 15","author":"Braasch","year":"2017"},{"key":"B7","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","author":"Buda","year":"2017"},{"key":"B8","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/B978-0-12-810408-8.00019-5","article-title":"Chapter 14 - deep learning models for classifying mammogram","volume-title":"Deep learning for medical image analysis","author":"Carneiro","year":"2017"},{"key":"B9","unstructured":"keras\n            CholletF.\n          2015"},{"key":"B10","first-page":"45","volume-title":"Evaluation metrics and evaluation","author":"Dalianis","year":"2018"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between precision-recall and roc curves","author":"Davis","year":"2006"},{"key":"B12","first-page":"19","article-title":"Signal deformation monitoring scheme implemented in a prototype local area augmentation system ground installation","author":"Fan","year":"2006"},{"key":"B13","article-title":"A portfolio approach to nlos and multipath mitigation in dense urban areas","author":"Groves","year":"2013"},{"key":"B14","first-page":"1","article-title":"Gnss multipath detection using a machine learning approach","author":"Hsu","year":"2017"},{"key":"B15","unstructured":"Gnss r&d software receiver portfolio2023"},{"key":"B16","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/s10291-021-01101-6","article-title":"Probabilistic approach to detect and correct gnss nlos signals using an augmented state vector in the extended kalman filter","volume":"25","author":"Jiang","year":"2021","journal-title":"GPS Solut."},{"key":"B17","first-page":"2319","article-title":"Feature extraction using convolution neural networks (cnn) and deep learning","author":"Jogin","year":"2018"},{"key":"B18","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1561\/0600000027","article-title":"Kernel methods in computer vision","volume":"4","author":"Lampert","year":"2009","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"B19","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/B978-0-12-818617-6.00009-3","article-title":"Chapter 4 - gnss multipath errors and mitigation techniques","volume-title":"GPS and GNSS Technology in geosciences","author":"Lau","year":"2021"},{"key":"B20","volume-title":"Improvement of pseudorange measurements accuracy by using fast adaptive bandwidth lock loops","author":"Legrand","year":"2000"},{"key":"B21","doi-asserted-by":"publisher","first-page":"062032","DOI":"10.1088\/1742-6596\/1087\/6\/062032","article-title":"Feature extraction and image recognition with convolutional neural networks","volume":"1087","author":"Liu","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"B22","first-page":"177","article-title":"Characterization of line-of-sight and non-line-of-sight pseudorange multipath errors in urban environment for GPS and galileo","author":"Matera","year":"2019"},{"key":"B23","first-page":"2018","article-title":"Gnss multipath detection using embedded deep cnn on intel\u00ae neural compute stick","author":"Munin","year":"2020"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1145\/1015330.1015435","article-title":"Feature selection, l1 vs. l2 regularization, and rotational invariance","author":"Ng","year":"2004"},{"key":"B25","first-page":"1","article-title":"Additional sqm metrics for generic tm detection","author":"Pagot","year":"2017"},{"key":"B26","volume-title":"Estimation of gnss signals\u2019 nominal distortions from correlation and chip domain","author":"Pagot","year":"2015"},{"key":"B27","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/mra.2013.2295944","article-title":"Gnss autonomous localization: Nlos satellite detection based on 3-d maps","volume":"21","author":"Peyret","year":"2014","journal-title":"IEEE Robotics Automation Mag."},{"key":"B28","article-title":"Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlation","author":"Powers","year":"2020"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.3390\/rs13122295","article-title":"Analysis of the impact of multipath on galileo system measurements","volume":"13","author":"Prochniewicz","year":"2021","journal-title":"Remote Sens."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2052","DOI":"10.3390\/rs10122052","article-title":"Convolutional neural network based multipath detection method for static and kinematic gps high precision positioning","volume":"10","author":"Quan","year":"2018","journal-title":"Remote Sens."},{"key":"B31","doi-asserted-by":"publisher","first-page":"25","DOI":"10.4236\/jcc.2015.36004","article-title":"Integrity monitoring in navigation systems: Fault detection and exclusion raim algorithm implementation","volume":"3","author":"Rakipi","year":"2015","journal-title":"J. Comput. Commun."},{"key":"B32","article-title":"Use of a fisheye camera for gnss nlos exclusion and characterization in urban environments","author":"Sanrom\u00e0 S\u00e1nchez","year":"2016"},{"key":"B33","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/navi.360","article-title":"Signal deformation fault monitors for dual-frequency gbas","volume":"67","author":"Song","year":"2020","journal-title":"NAVIGATION J. Inst. Navigation"},{"key":"B34","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"B35","doi-asserted-by":"publisher","first-page":"2503","DOI":"10.3390\/s21072503","article-title":"Nlos multipath classification of gnss signal correlation output using machine learning","volume":"21","author":"Suzuki","year":"2021","journal-title":"Sensors"},{"key":"B36","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s10291-020-01006-w","article-title":"Rotating gnss antennas: Simultaneous los and nlos multipath mitigation","volume":"24","author":"Suzuki","year":"2020","journal-title":"GPS Solutions"},{"key":"B37","first-page":"21","article-title":"Cycle slip detection and fixing by mems-imu\/gps integration for mobile environment rtk-gps","author":"Takasu Tomoji","year":"2008"},{"key":"B38","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1002\/j.2161-4296.1992.tb02276.x","article-title":"Theory and performance of narrow correlator spacing in a gps receiver","volume":"39","author":"Van Dierendonck","year":"1992","journal-title":"NAVIGATION"},{"key":"B39","article-title":"Effect of multipath on code-tracking error jitter of a delay locked loop","author":"Vergara","year":"2009"},{"key":"B40","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s43020-020-00016-w","article-title":"Machine learning based los\/nlos classifier and robust estimator for gnss shadow matching","volume":"1","author":"Xu","year":"2020","journal-title":"Satell. Navig."},{"key":"B41","doi-asserted-by":"publisher","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An overview of overfitting and its solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"B42","doi-asserted-by":"publisher","first-page":"8643","DOI":"10.3390\/app12178643","article-title":"A comparison of pooling methods for convolutional neural networks","volume":"12","author":"Zafar","year":"2022","journal-title":"Appl. Sci."},{"key":"B43","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"Zhang","year":"2018"},{"key":"B44","first-page":"5163","article-title":"28 ghz millimeter wave cellular communication measurements for reflection and penetration loss in and around buildings in New York city","author":"Zhao","year":"2013"},{"key":"B45","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1106439\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T07:09:49Z","timestamp":1683875389000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1106439\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,11]]},"references-count":45,"alternative-id":["10.3389\/frobt.2023.1106439"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2023.1106439","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,11]]},"article-number":"1106439"}}