Localization in internal environments using IEEE 802.11 networks

Autor: Ferreira, David Alan de Oliveira, https://orcid.org/0000-0001-5717-4018
Přispěvatelé: Carvalho, Celso Barbosa, Bezerra, Thiago Brito, Ayres J??nior, Florindo Ant??nio de Carvalho
Jazyk: portugalština
Rok vydání: 2019
Předmět:
Zdroj: Biblioteca Digital de Teses e Dissertações da UFAM
Universidade Federal do Amazonas (UFAM)
instacron:UFAM
Popis: Submitted by David Ferreira (ferreirad08@gmail.com) on 2019-05-03T14:18:50Z No. of bitstreams: 3 Disserta????o - David Ferreira.pdf: 1796336 bytes, checksum: 862d8ef4cf25a00e1375dabdb2baed09 (MD5) carta de encaminhamento auto dep??sito.pdf: 142038 bytes, checksum: 2e7ab534e1f4883fbd866a39a7872ed2 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Approved for entry into archive by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br) on 2019-05-06T12:32:02Z (GMT) No. of bitstreams: 3 Disserta????o - David Ferreira.pdf: 1796336 bytes, checksum: 862d8ef4cf25a00e1375dabdb2baed09 (MD5) carta de encaminhamento auto dep??sito.pdf: 142038 bytes, checksum: 2e7ab534e1f4883fbd866a39a7872ed2 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Approved for entry into archive by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2019-05-07T13:47:38Z (GMT) No. of bitstreams: 3 Disserta????o - David Ferreira.pdf: 1796336 bytes, checksum: 862d8ef4cf25a00e1375dabdb2baed09 (MD5) carta de encaminhamento auto dep??sito.pdf: 142038 bytes, checksum: 2e7ab534e1f4883fbd866a39a7872ed2 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Made available in DSpace on 2019-05-07T13:47:38Z (GMT). No. of bitstreams: 3 Disserta????o - David Ferreira.pdf: 1796336 bytes, checksum: 862d8ef4cf25a00e1375dabdb2baed09 (MD5) carta de encaminhamento auto dep??sito.pdf: 142038 bytes, checksum: 2e7ab534e1f4883fbd866a39a7872ed2 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2019-03-27 CAPES - Coordena????o de Aperfei??oamento de Pessoal de N??vel Superior 92999712074 This work proposes a method that employs the k-Nearest Neighbors (kNN) machine learning algorithm to determine the location of moving objects indoors. In the test scenario, the mobile object is represented by a Wireless Station (WSTA) that uses Wi-Fi (Wireless Fidelity) technology. In order to estimate the location of the WSTA, measurements were made of the Received Signal Strength Indicator (RSSI), from signals from access points (APs), from specific collection points denoted as points reference points (RPs). In this scenario, in an initial phase of training the algorithm, each RP is used to collect RSSI samples in a process of scanning APs installed in the environment. Also in the training phase, quartiles measurements are used to represent the behavior of these RSSI samples. Subsequently, in the test phase, the training set data, formed by the quartiles, are compared with new data in order to determine the position of the WSTA. In the performance evaluation, it was verified that the proposed algorithm had null error with only four APs e 10 readings per sample with 17.27 seconds of processing time. It is verified that the results with these values are important contributions, which ensures that using the kNN algorithm adopting a dataset summarized with quartiles measurements is a promising method to locate objects indoors. Este trabalho prop??e um m??todo que emprega o algoritmo de aprendizado de m??quina k-Nearest Neighbors (kNN) para determinar a localiza????o de objetos m??veis em ambientes internos. No cen??rio de testes, o objeto m??vel ?? representado por uma esta????o sem fio (Wireless Station - WSTA) que utiliza tecnologia Wi-Fi (Wireless Fidelity). Para estimar a localiza????o da WSTA realizaram-se medi????es do Indicador de Intensidade do Sinal Recebido (Received Signal Strength Indicator - RSSI), dos sinais provenientes de pontos de acesso (Access Points - APs), a partir de pontos de coleta espec??ficos denotados como pontos de refer??ncia (Reference Points - RPs). Neste cen??rio, em uma fase inicial de treinamento do algoritmo, cada RP ?? utilizado para coletar amostras de RSSI em um processo de varredura dos APs instalados no ambiente. Ainda na fase de treinamento, utilizam-se medidas de quartis para representar o comportamento destas amostras de RSSI. Posteriormente, na fase de testes, os dados do conjunto de treinamento, formado pelos quartis, s??o comparados com novos dados a fim de determinar a posi????o da WSTA. Na avalia????o de desempenho, verificou-se que o algoritmo proposto possuiu erro nulo com apenas quatro APs e 10 leituras por amostras com 17,27 segundos de tempo de processamento. Verifica-se que os resultados com estes valores s??o contribui????es importantes, o que assegura que utilizar o algoritmo kNN adotando um conjunto de dados sumarizado com medidas de quartis, ?? um m??todo promissor para localizar objetos em ambientes internos.
Databáze: OpenAIRE
Externí odkaz: