Increased Accuracy in Indoor Location based on Neural Networks

The use of WiFi is widely used by a large number of devices, including those that make up the Internet of Things (IoT) and Artificial Intelligence (AI) systems. The location problem has been under investigation for a long time. In some cases, the radio signals used to transmit information are also u...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gerez, Agustín, Goñi, Oscar Enrique, Leiva, Lucas
Formato: Artículo publishedVersion
Lenguaje:Español
Publicado: FIUBA 2020
Materias:
localization
triangulation
distance
ANN
localización
triangulación
distancia
Acceso en línea:https://elektron.fi.uba.ar/elektron/article/view/114
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=114_oai
Aporte de:
Repositorio Digital de la Universidad de Buenos Aires (UBA) de Universidad de Buenos Aires
id I28-R145-114_oai
record_format dspace
spelling I28-R145-114_oai2026-02-11 Gerez, Agustín Goñi, Oscar Enrique Leiva, Lucas 2020-12-14 The use of WiFi is widely used by a large number of devices, including those that make up the Internet of Things (IoT) and Artificial Intelligence (AI) systems. The location problem has been under investigation for a long time. In some cases, the radio signals used to transmit information are also used to make position estimates. However, its use is affected by the constant fluctuation of the signal. It is possible that when estimating the position of a component, it is influenced by obstacles, multipath and signal reflection. Its use improves when spatial localization is carried out, where assets can be traced within an indoor environment. In this work, the relationship of the distance estimation algorithms using RSSI and triangulation is analyzed, and a solution based on Neural Networks is proposed that combines the results of three distance estimation algorithms in order to increase precision. La tecnología WiFi es ampliamente utilizada por un gran número de dispositivos, incluyendo aquellos que componen sistemas de Internet de las Cosas (IoT) y de Inteligencia Artificial (IA). En ambos contextos, el problema de localización ha sido objeto de investigación durante mucho tiempo. En algunos casos, las señales de radio utilizadas para transmitir información son además aprovechadas para realizar estimaciones de posición. Sin embargo, este enfoque se encuentra afectado por la constante fluctuación de la señal. Es posible que al momento de realizar una estimación de posición de un componente emisor, éste se encuentre influenciado por los obstáculos, el multitrayecto y la reflexión de la señal. Sin embargo, su uso mejora cuando se realiza localización espacial considerando diferentes referencias. De esta manera, es posible trazar activos dentro de un ambiente indoor. En este trabajo se analiza la relación de los algoritmos de estimación de distancia utilizando RSSI y triangulación, y se propone una solución basada en Redes Neuronales que combina los resultados de tres algoritmos de estimación de distancia con el fin de aumentar la precisión. application/pdf text/html https://elektron.fi.uba.ar/elektron/article/view/114 10.37537/rev.elektron.4.2.114.2020 spa FIUBA https://elektron.fi.uba.ar/elektron/article/view/114/203 https://elektron.fi.uba.ar/elektron/article/view/114/216 Derechos de autor 2020 Agustín Gerez, Oscar Enrique Goñi, Lucas Leiva Elektron Journal; Vol. 4 No. 2 (2020); 74-80 Revista Elektron; Vol. 4 Núm. 2 (2020); 74-80 Revista Elektron; v. 4 n. 2 (2020); 74-80 2525-0159 2525-0159 localization triangulation distance ANN localización triangulación distancia ANN Increased Accuracy in Indoor Location based on Neural Networks Aumento de Precisión en Localización Indoor basado en Redes Neuronales info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=114_oai
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-145
collection Repositorio Digital de la Universidad de Buenos Aires (UBA)
language Español
orig_language_str_mv spa
topic localization
triangulation
distance
ANN
localización
triangulación
distancia
ANN
spellingShingle localization
triangulation
distance
ANN
localización
triangulación
distancia
ANN
Gerez, Agustín
Goñi, Oscar Enrique
Leiva, Lucas
Increased Accuracy in Indoor Location based on Neural Networks
topic_facet localization
triangulation
distance
ANN
localización
triangulación
distancia
ANN
description The use of WiFi is widely used by a large number of devices, including those that make up the Internet of Things (IoT) and Artificial Intelligence (AI) systems. The location problem has been under investigation for a long time. In some cases, the radio signals used to transmit information are also used to make position estimates. However, its use is affected by the constant fluctuation of the signal. It is possible that when estimating the position of a component, it is influenced by obstacles, multipath and signal reflection. Its use improves when spatial localization is carried out, where assets can be traced within an indoor environment. In this work, the relationship of the distance estimation algorithms using RSSI and triangulation is analyzed, and a solution based on Neural Networks is proposed that combines the results of three distance estimation algorithms in order to increase precision.
format Artículo
publishedVersion
author Gerez, Agustín
Goñi, Oscar Enrique
Leiva, Lucas
author_facet Gerez, Agustín
Goñi, Oscar Enrique
Leiva, Lucas
author_sort Gerez, Agustín
title Increased Accuracy in Indoor Location based on Neural Networks
title_short Increased Accuracy in Indoor Location based on Neural Networks
title_full Increased Accuracy in Indoor Location based on Neural Networks
title_fullStr Increased Accuracy in Indoor Location based on Neural Networks
title_full_unstemmed Increased Accuracy in Indoor Location based on Neural Networks
title_sort increased accuracy in indoor location based on neural networks
publisher FIUBA
publishDate 2020
url https://elektron.fi.uba.ar/elektron/article/view/114
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=114_oai
work_keys_str_mv AT gerezagustin increasedaccuracyinindoorlocationbasedonneuralnetworks
AT gonioscarenrique increasedaccuracyinindoorlocationbasedonneuralnetworks
AT leivalucas increasedaccuracyinindoorlocationbasedonneuralnetworks
AT gerezagustin aumentodeprecisionenlocalizacionindoorbasadoenredesneuronales
AT gonioscarenrique aumentodeprecisionenlocalizacionindoorbasadoenredesneuronales
AT leivalucas aumentodeprecisionenlocalizacionindoorbasadoenredesneuronales
_version_ 1857042979457335296

Ejemplares similares