<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1794-6190</journal-id>
<journal-title><![CDATA[Earth Sciences Research Journal]]></journal-title>
<abbrev-journal-title><![CDATA[Earth Sci. Res. J.]]></abbrev-journal-title>
<issn>1794-6190</issn>
<publisher>
<publisher-name><![CDATA[Universidad Nacional de Colombia]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1794-61902020000100097</article-id>
<article-id pub-id-type="doi">10.15446/esrj.v24n1.78880</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Estimation of GPS L2 signal observables using Multilayer Perceptron Artificial Neural Network for positional accuracy improvement]]></article-title>
<article-title xml:lang="es"><![CDATA[Estimación de los observables de señal GPS L2 utilizando redes neuronales artificiales de perceptrón multicapa para mejorar la precisión posicional]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Carletti Negri]]></surname>
<given-names><![CDATA[Cassio Vinícius]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Lima Segantine]]></surname>
<given-names><![CDATA[Paulo Cesar]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,University of São Paulo  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Brazil</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>03</month>
<year>2020</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>03</month>
<year>2020</year>
</pub-date>
<volume>24</volume>
<numero>1</numero>
<fpage>97</fpage>
<lpage>103</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S1794-61902020000100097&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S1794-61902020000100097&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S1794-61902020000100097&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[ABSTRACT In recent decades, due to the increasing mobility of people and goods, the rapid growth of users of mobile devices with location-based services has increased the need for geospatial information. In this context, positioning using data collected by the Global Navigation Satellite Systems (multi-GNSS) has gained more importance in the field of geomatics. The quality of the solutions is related, among other factors, to the receiver's type used in the work. To improve the positioning with low-cost devices and to avoid additional user expenses, this work aims to propose the implementation of an Artificial Neural Network (ANN) to estimate the GPS L2 carrier observables. For this, a network model was selected through the cross-validation (CV) technique, the observations were estimated, and the accuracy of the solutions was analyzed. The CV technique demonstrated that a Multilayer Perceptron with four intermediate layers and one with one intermediate layer are the most appropriate configurations for this problem. The dual-frequency RINEX processing (with artificial data) revealed significant improvements. For some tests, it was possible to comply with the rural property georeferencing regulations of the Brazilian National Institute of Colonization and Agrarian Reform (INCRA). The results indicate, therefore, that the methodological proposal of the present investigation is very promising for approximating the quality of positioning reachable using a dual-frequency receiver.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[RESUMEN En las últimas décadas, debido a la creciente movilidad de personas y bienes, el rápido crecimiento de los usuarios de dispositivos móviles con servicios basados en la ubicación ha aumentado la necesidad de información geoespacial. En este contexto, el posicionamiento utilizando los datos recopilados por los Sistemas Globales de Satélite de Navegación (multi-GNSS) ha ganado más importancia en el campo de la geomática. La calidad de las soluciones está relacionada, entre otros factores, con el tipo de receptor utilizado en el trabajo. Para mejorar el posicionamiento con dispositivos de bajo costo y evitar gastos adicionales del usuario, este trabajo tiene como objetivo proponer la implementación de una Red Neural Artificial (ANN) para estimar los observables del operador GPS L2. Para esto, se seleccionó un modelo de red a través de la técnica de validación cruzada (CV), se estimaron las observaciones y se analizó la precisión de las soluciones. La técnica CV demostró que un Perceptrón multicapa con cuatro capas intermedias y uno con una capa intermedia son las configuraciones más apropiadas para este problema. El procesamiento RINEX de doble frecuencia (con datos artificiales) reveló mejoras significativas. Para algunas pruebas, fue posible cumplir con las regulaciones de georreferenciación de propiedad rural del Instituto Nacional de Colonización y Reforma Agraria (INCRA). Los resultados indican, por lo tanto, que la propuesta metodológica de la presente investigación es muy prometedora para aproximar la calidad de posicionamiento accesible utilizando un receptor de doble frecuencia.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[GPS]]></kwd>
<kwd lng="en"><![CDATA[GNSS]]></kwd>
<kwd lng="en"><![CDATA[Point positioning]]></kwd>
<kwd lng="en"><![CDATA[ANN]]></kwd>
<kwd lng="en"><![CDATA[Estimation of the L2 carrier observables]]></kwd>
<kwd lng="es"><![CDATA[GPS]]></kwd>
<kwd lng="es"><![CDATA[GNSS]]></kwd>
<kwd lng="es"><![CDATA[Posicionamiento]]></kwd>
<kwd lng="es"><![CDATA[Red Artificial Neuronal]]></kwd>
<kwd lng="es"><![CDATA[Estimación de los observables L2]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Lecun]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Scaling Learning Algorithms towards AI]]></article-title>
<source><![CDATA[Large Scale Kernel Machines]]></source>
<year>2007</year>
<numero>1</numero>
<issue>1</issue>
<page-range>321-60</page-range></nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Shen]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[W. Bin]]></given-names>
</name>
<name>
<surname><![CDATA[Tomizuka]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Chiu]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Novel hybrid of strong tracking Kalman ilter and wavelet neural network for GPS/INS during GPS outages]]></article-title>
<source><![CDATA[Measurement]]></source>
<year>2013</year>
<volume>46</volume>
<numero>10</numero>
<issue>10</issue>
<page-range>3847-54</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Géron]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Hands-On Machine Learning with Scikit-Learn and Tensor Flow]]></source>
<year>2017</year>
<edition>1</edition>
<publisher-loc><![CDATA[Sebastopol ]]></publisher-loc>
<publisher-name><![CDATA[O'Reilly Media]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Goodfellow]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Courville]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Deep learning (adaptive computation and machine learning series). Adaptive Computation and Machine Learning series]]></source>
<year>2016</year>
<publisher-loc><![CDATA[Cambridge ]]></publisher-loc>
<publisher-name><![CDATA[MIT Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Haykin]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural Networks and Learning Machines]]></source>
<year>2008</year>
<edition>3</edition>
<publisher-loc><![CDATA[Upper Saddle River ]]></publisher-loc>
<publisher-name><![CDATA[Pearson Prentice Hall]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hopfield]]></surname>
<given-names><![CDATA[J. J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Neural networks and physical systems with emergent collective computational abilities]]></article-title>
<source><![CDATA[Proceedings of the National Academy of Sciences]]></source>
<year>1982</year>
<volume>79</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>2554-8</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hornik]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Stinchcombe]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[White]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multilayer Feedforward networks are universal approximators]]></article-title>
<source><![CDATA[Neural Networks]]></source>
<year>1989</year>
<volume>2</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>359-66</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="">
<collab>IBGE</collab>
<source><![CDATA[IBGE | Portal do IBGE]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Indriyatmoko]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Kang]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[Y. J.]]></given-names>
</name>
<name>
<surname><![CDATA[Jee]]></surname>
<given-names><![CDATA[G. I.]]></given-names>
</name>
<name>
<surname><![CDATA[Cho]]></surname>
<given-names><![CDATA[Y. B.]]></given-names>
</name>
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Artiicial neural networks for predicting DGPS carrier phase and pseudorange correction]]></article-title>
<source><![CDATA[GPS Solutions]]></source>
<year>2008</year>
<volume>12</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>237-47</page-range></nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jwo]]></surname>
<given-names><![CDATA[D. J.]]></given-names>
</name>
<name>
<surname><![CDATA[Chin]]></surname>
<given-names><![CDATA[K. P]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Applying Back-propagation neural networks to GDOP approximation]]></article-title>
<source><![CDATA[The Journal of Navigation]]></source>
<year>2002</year>
<volume>55</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>97-108</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jwo]]></surname>
<given-names><![CDATA[D. J.]]></given-names>
</name>
<name>
<surname><![CDATA[Lai]]></surname>
<given-names><![CDATA[C. C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Neural network-based GPS GDOP approximation and classification]]></article-title>
<source><![CDATA[GPS Solutions]]></source>
<year>2007</year>
<volume>11</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>51-60</page-range></nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kingma]]></surname>
<given-names><![CDATA[D. P.]]></given-names>
</name>
<name>
<surname><![CDATA[Ba]]></surname>
<given-names><![CDATA[J. L]]></given-names>
</name>
</person-group>
<source><![CDATA[Adam: a method for Stochastic optimization]]></source>
<year>2014</year>
<conf-name><![CDATA[ International Conference on Learning Representations]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1-15</page-range></nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Leandro]]></surname>
<given-names><![CDATA[R. F.]]></given-names>
</name>
<name>
<surname><![CDATA[Silva]]></surname>
<given-names><![CDATA[C. A. U.]]></given-names>
</name>
<name>
<surname><![CDATA[Santos]]></surname>
<given-names><![CDATA[M. C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Feeding neural network models with GPS observations: a challenging task]]></article-title>
<source><![CDATA[Dynamic Planet]]></source>
<year>2007</year>
<volume>150</volume>
<page-range>186-93</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Leick]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Rapoport]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Tatarnikov]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<source><![CDATA[GPS Satellite Surveying]]></source>
<year>2015</year>
<edition>4</edition>
<publisher-loc><![CDATA[Hoboken ]]></publisher-loc>
<publisher-name><![CDATA[JohnWiley &amp; Sons]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mazzetto]]></surname>
<given-names><![CDATA[J. V. B]]></given-names>
</name>
</person-group>
<source><![CDATA[Estimation of L2 observables of the GPS system through the use of Artificial Neural Networks]]></source>
<year>2017</year>
<publisher-loc><![CDATA[São Carlos ]]></publisher-loc>
<publisher-name><![CDATA[São Carlos School of Engineering - University of São Paulo (EESC-USP)]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[McCulloch]]></surname>
<given-names><![CDATA[W. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Pitts]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A logical calculus of the ideas immanent in nervous activity]]></article-title>
<source><![CDATA[The Bulletin of Mathematical Biophysics]]></source>
<year>1943</year>
<volume>5</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>115-33</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mosavi]]></surname>
<given-names><![CDATA[M. R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Wavelet Based Neural Network for DGPS corrections prediction]]></article-title>
<source><![CDATA[WSEAS Transactions on Systems]]></source>
<year>2004</year>
<volume>5</volume>
<numero>10</numero>
<issue>10</issue>
<page-range>3070-5</page-range></nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mosavi]]></surname>
<given-names><![CDATA[M. R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[GPS receivers timing data processing using Neural Networks: optimal estimation and errors modeling]]></article-title>
<source><![CDATA[International Journal of Neural Systems]]></source>
<year>2007</year>
<volume>17</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>383-93</page-range></nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rosenblatt]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[The perceptron: A probabilistic model for information storage and organization in the brain]]></article-title>
<source><![CDATA[Psychological Review]]></source>
<year>1958</year>
<volume>65</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>386-408</page-range></nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rumelhart]]></surname>
<given-names><![CDATA[D. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Hinton]]></surname>
<given-names><![CDATA[G. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Williams]]></surname>
<given-names><![CDATA[R. J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Learning representations by Back-propagating errors]]></article-title>
<source><![CDATA[Nature]]></source>
<year>1986</year>
<volume>525</volume>
<numero>6088</numero>
<issue>6088</issue>
<page-range>533-6</page-range></nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sang]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Kubik]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<source><![CDATA[Prediction of DGPS Corrections with Neural Networks]]></source>
<year>1997</year>
<publisher-name><![CDATA[Knowledge-Basedlntelligent Electronic Systems. IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="">
<collab>Scikit-learn</collab>
<source><![CDATA[Scikit-learn: Machine Learning in Python]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Segantine]]></surname>
<given-names><![CDATA[P. C. L]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Semeniuk]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Noureldin]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Bridging GPS outages using neural network estimates of INS position and velocity errors]]></article-title>
<source><![CDATA[Measurement Science and Technology]]></source>
<year>2006</year>
<volume>17</volume>
<numero>10</numero>
<issue>10</issue>
<page-range>2783-98</page-range></nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Silva]]></surname>
<given-names><![CDATA[C. A. U. da]]></given-names>
</name>
</person-group>
<source><![CDATA[A method to estimate GPS data observables using artificial neural networks]]></source>
<year>2003</year>
<publisher-loc><![CDATA[São Carlos ]]></publisher-loc>
<publisher-name><![CDATA[São Carlos School of Engineering -University of São Paulo (EESC-USP)]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Silva]]></surname>
<given-names><![CDATA[I. N.]]></given-names>
</name>
<name>
<surname><![CDATA[Spatti]]></surname>
<given-names><![CDATA[D. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Flauzino]]></surname>
<given-names><![CDATA[R. A]]></given-names>
</name>
</person-group>
<source><![CDATA[Redes Neurais Artificiais para Engenharia e Ciências aplicadas]]></source>
<year>2010</year>
<edition>2</edition>
<publisher-loc><![CDATA[São Paulo ]]></publisher-loc>
<publisher-name><![CDATA[Artliber]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="">
<collab>TensorFlow</collab>
<source><![CDATA[TensorFlow]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Widrow]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Hoff]]></surname>
<given-names><![CDATA[M. E]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Adaptive switching circuits]]></article-title>
<source><![CDATA[Neurocomputing: Foundations of Research]]></source>
<year>1960</year>
<page-range>123-34</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
