On the application of graph neural networks for indoor positioning systems.
Due to the inability of GPS (or other GNSS methods) to provide satisfactory precision for the indoor location scenario, indoor positioning systems resort to other signals already available on site, typically Wi-Fi given its ubiquity. However, instead of relying on an error-prone propagation model as...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Format: | bookPart |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/20.500.12008/37987 |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1868889916587376640 |
|---|---|
| author | Lezama, Facundo |
| author2 | Larroca, Federico Capdehourat, Germán |
| author2_role | author author |
| author_browse | Capdehourat, Germán Larroca, Federico Lezama, Facundo |
| author_facet | Lezama, Facundo Larroca, Federico Capdehourat, Germán |
| author_role | author |
| collection | COLIBRI |
| dc.contributor.none.fl_str_mv | Lezama Facundo, Universidad de la República (Uruguay). Facultad de Ingeniería. Larroca Federico, Universidad de la República (Uruguay). Facultad de Ingeniería. Capdehourat Germán, Universidad de la República (Uruguay). Facultad de Ingeniería. |
| dc.creator.none.fl_str_mv | Lezama, Facundo Larroca, Federico Capdehourat, Germán |
| dc.date.none.fl_str_mv | 2023-07-05T21:02:24Z 2023-07-05T21:02:24Z 2023 |
| dc.format.none.fl_str_mv | 20 p. application/pdf |
| dc.identifier.none.fl_str_mv | Lezama, F., Larroca, F. y Capdehourat, G. On the application of graph neural networks for indoor positioning systems [Preprint]. Publicado en: Machine Learning for Indoor Localization and Navigation. Springer, Cham, 2023. DOI: 10.1007/978-3-031-26712-3_10 https://hdl.handle.net/20.500.12008/37987 |
| dc.language.none.fl_str_mv | en eng |
| dc.rights.none.fl_str_mv | info:eu-repo/semantics/openAccess Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| dc.source.none.fl_str_mv | reponame:COLIBRI instname:Universidad de la República instacron:Universidad de la República |
| dc.subject.none.fl_str_mv | Graph classification Graph signal interpolation Localization |
| dc.title.none.fl_str_mv | On the application of graph neural networks for indoor positioning systems. |
| dc.type.none.fl_str_mv | Capítulo de libro info:eu-repo/semantics/bookPart info:eu-repo/semantics/publishedVersion |
| description | Due to the inability of GPS (or other GNSS methods) to provide satisfactory precision for the indoor location scenario, indoor positioning systems resort to other signals already available on site, typically Wi-Fi given its ubiquity. However, instead of relying on an error-prone propagation model as in ranging methods, the popular fingerprinting positioning technique considers a more direct data-driven approach to the problem. First of all, the area of interest is divided into zones, and then a machine learning algorithm is trained to map, for instance, power measurements (RSSI) from APs to the localization zone, thus effectively turning the problem into a classification one. However, although the positioning problem is a geometrical one, virtually all methods proposed in the literature disregard the underlying structure of the data, using generic machine learning algorithms. In this chapter we consider instead a graph-based learning method, Graph Neural Networks, a paradigm that has emerged in the last few years and that constitutes the state of the art for several problems. After presenting the pertinent theoretical background, we discuss two possibilities to construct the underlying graph for the positioning problem. We then perform a thorough evaluation of both possibilities and compare it with some of the most popular machine learning alternatives. The main conclusion is that these graph-based methods obtain systematically better results, particularly with regard to practical aspects (e.g., gracefully tolerating faulty APs), which makes them a serious candidate to consider when deploying positioning systems. |
| eu_rights_str_mv | openAccess |
| format | bookPart |
| id | anni_00213ea796d5fff7d563c280cfe42bf2 |
| identifier_str_mv | Lezama, F., Larroca, F. y Capdehourat, G. On the application of graph neural networks for indoor positioning systems [Preprint]. Publicado en: Machine Learning for Indoor Localization and Navigation. Springer, Cham, 2023. DOI: 10.1007/978-3-031-26712-3_10 |
| instacron_str | Universidad de la República |
| institution | Universidad de la República |
| instname_str | Universidad de la República |
| language | eng |
| language_invalid_str_mv | en |
| network_acronym_str | anni |
| network_name_str | oai-lr-anni |
| oai_identifier_str | oai:colibri.udelar.edu.uy:20.500.12008/37987 |
| publishDate | 2023 |
| publishDateSort | 2023 |
| reponame_str | COLIBRI |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| spelling | On the application of graph neural networks for indoor positioning systems.Lezama, FacundoLarroca, FedericoCapdehourat, GermánGraph classificationGraph signal interpolationLocalizationDue to the inability of GPS (or other GNSS methods) to provide satisfactory precision for the indoor location scenario, indoor positioning systems resort to other signals already available on site, typically Wi-Fi given its ubiquity. However, instead of relying on an error-prone propagation model as in ranging methods, the popular fingerprinting positioning technique considers a more direct data-driven approach to the problem. First of all, the area of interest is divided into zones, and then a machine learning algorithm is trained to map, for instance, power measurements (RSSI) from APs to the localization zone, thus effectively turning the problem into a classification one. However, although the positioning problem is a geometrical one, virtually all methods proposed in the literature disregard the underlying structure of the data, using generic machine learning algorithms. In this chapter we consider instead a graph-based learning method, Graph Neural Networks, a paradigm that has emerged in the last few years and that constitutes the state of the art for several problems. After presenting the pertinent theoretical background, we discuss two possibilities to construct the underlying graph for the positioning problem. We then perform a thorough evaluation of both possibilities and compare it with some of the most popular machine learning alternatives. The main conclusion is that these graph-based methods obtain systematically better results, particularly with regard to practical aspects (e.g., gracefully tolerating faulty APs), which makes them a serious candidate to consider when deploying positioning systems.Lezama Facundo, Universidad de la República (Uruguay). Facultad de Ingeniería.Larroca Federico, Universidad de la República (Uruguay). Facultad de Ingeniería.Capdehourat Germán, Universidad de la República (Uruguay). Facultad de Ingeniería.2023-07-05T21:02:24Z2023-07-05T21:02:24Z2023Capítulo de libroinfo:eu-repo/semantics/bookPartinfo:eu-repo/semantics/publishedVersion20 p.application/pdfLezama, F., Larroca, F. y Capdehourat, G. On the application of graph neural networks for indoor positioning systems [Preprint]. Publicado en: Machine Learning for Indoor Localization and Navigation. Springer, Cham, 2023. DOI: 10.1007/978-3-031-26712-3_10https://hdl.handle.net/20.500.12008/37987reponame:COLIBRIinstname:Universidad de la Repúblicainstacron:Universidad de la RepúblicaenengLas obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014)info:eu-repo/semantics/openAccessLicencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)oai:colibri.udelar.edu.uy:20.500.12008/379872026-04-14T10:15:25Z |
| spellingShingle | On the application of graph neural networks for indoor positioning systems. Lezama, Facundo Graph classification Graph signal interpolation Localization |
| status_str | publishedVersion |
| title | On the application of graph neural networks for indoor positioning systems. |
| title_full | On the application of graph neural networks for indoor positioning systems. |
| title_fullStr | On the application of graph neural networks for indoor positioning systems. |
| title_full_unstemmed | On the application of graph neural networks for indoor positioning systems. |
| title_short | On the application of graph neural networks for indoor positioning systems. |
| title_sort | On the application of graph neural networks for indoor positioning systems. |
| topic | Graph classification Graph signal interpolation Localization |
| url | https://hdl.handle.net/20.500.12008/37987 |