License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.TIME.2019.10
URN: urn:nbn:de:0030-drops-113687
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2019/11368/
Go to the corresponding LIPIcs Volume Portal

Loli Piccolomini, Elena ; Gandolfi, Stefano ; Poluzzi, Luca ; Tavasci, Luca ; Cascarano, Pasquale ; Pascucci, Andrea

Recurrent Neural Networks Applied to GNSS Time Series for Denoising and Prediction

pdf-format:
LIPIcs-TIME-2019-10.pdf (2 MB)

Abstract

Global Navigation Satellite Systems (GNSS) are systems that continuously acquire data and provide position time series. Many monitoring applications are based on GNSS data and their efficiency depends on the capability in the time series analysis to characterize the signal content and/or to predict incoming coordinates. In this work we propose a suitable Network Architecture, based on Long Short Term Memory Recurrent Neural Networks, to solve two main tasks in GNSS time series analysis: denoising and prediction. We carry out an analysis on a synthetic time series, then we inspect two real different case studies and evaluate the results. We develop a non-deep network that removes almost the 50% of scattering from real GNSS time series and achieves a coordinate prediction with 1.1 millimeters of Mean Squared Error.

BibTeX - Entry

@InProceedings{lolipiccolomini_et_al:LIPIcs:2019:11368,
  author =	{Elena Loli Piccolomini and Stefano Gandolfi and Luca Poluzzi and Luca Tavasci and Pasquale Cascarano and Andrea Pascucci},
  title =	{{Recurrent Neural Networks Applied to GNSS Time Series for Denoising and Prediction}},
  booktitle =	{26th International Symposium on Temporal Representation and Reasoning (TIME 2019)},
  pages =	{10:1--10:12},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-127-6},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{147},
  editor =	{Johann Gamper and Sophie Pinchinat and Guido Sciavicco},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2019/11368},
  URN =		{urn:nbn:de:0030-drops-113687},
  doi =		{10.4230/LIPIcs.TIME.2019.10},
  annote =	{Keywords: Deep Neural Networks, Recurrent Neural Networks, Time Series Denoising, Time Series Prediction}
}

Keywords: Deep Neural Networks, Recurrent Neural Networks, Time Series Denoising, Time Series Prediction
Collection: 26th International Symposium on Temporal Representation and Reasoning (TIME 2019)
Issue Date: 2019
Date of publication: 07.10.2019

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI