User behaviour identification based on location data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/21711 |
Resumo: | Over the years there has been an almost exponential increase in the use of new technologies in various sectors. These technologies have as their main objective, to improve or facilitate our daily life. This study will focus on one of these technologies used within a theme that has been widely talked about over the last few years, the use of personal data of various people to identify certain types of behavior. More specifically, this study aims primarily to use the GPS data stored in the respective Google accounts of nine volunteers in order to identify the places they frequent most, also known as Points of Interest. This same data will also be used to identify the trajectories covered more often by each of the same volunteers. A study was carried out with a sample of 9 participants, sending them their maps with POI and trajectories, thus obtaining their validation. It was thus possible to conclude that the best way to identify POI is to use daily clusters using DBSCAN. In the case of trajectories, the Snap-to-Road method was the one that gave the best results. It was found that it was possible to respond to the initial problem, and thus a method was found that identifies most of the POI successfully and also some trajectories.Based on this work, there is a great opportunity to improve some of the algorithms and processes that have some limitations in the future, and with this in mind it's possible to develop more effective solutions. |
id |
RCAP_ec148687bb64e1e4e6616101051e95a0 |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/21711 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
User behaviour identification based on location dataPatternsArtificial intelligenceGPSPadrõesInteligência artificialOver the years there has been an almost exponential increase in the use of new technologies in various sectors. These technologies have as their main objective, to improve or facilitate our daily life. This study will focus on one of these technologies used within a theme that has been widely talked about over the last few years, the use of personal data of various people to identify certain types of behavior. More specifically, this study aims primarily to use the GPS data stored in the respective Google accounts of nine volunteers in order to identify the places they frequent most, also known as Points of Interest. This same data will also be used to identify the trajectories covered more often by each of the same volunteers. A study was carried out with a sample of 9 participants, sending them their maps with POI and trajectories, thus obtaining their validation. It was thus possible to conclude that the best way to identify POI is to use daily clusters using DBSCAN. In the case of trajectories, the Snap-to-Road method was the one that gave the best results. It was found that it was possible to respond to the initial problem, and thus a method was found that identifies most of the POI successfully and also some trajectories.Based on this work, there is a great opportunity to improve some of the algorithms and processes that have some limitations in the future, and with this in mind it's possible to develop more effective solutions.Ao longo dos anos tem-se verificado um aumento quase exponencial no que toca à utilização de novas tecnologias em vários sectores. Estas tecnologias têm como objetivo principal, melhorar ou facilitar o quotidiano. O presente estudo vai incidir sobre uma destas tecnologias utilizada dentro de um tema que tem sido muito falado nos últimos anos, a utilização de dados pessoais de um grupo de indvíduos para identificar certos tipos de comportamentos. Mais concretamente, tem como objetivo utilizar os dados de GPS, guardados nas respectivas contas Google de nove voluntários, de modo a identificar os locais que estes mais frequentam - Pontos de Interesse. Os dados são utilizados também para identificar as trajectórias percorridas mais vezes por cada um dos voluntários. Foi realizado um estudo com uma amostra de 9 participantes, enviando-lhes os respectivos mapas com POI e trajectórias obtendo assim a validação dos mesmos. Desta forma foi possível concluir que que a melhor forma de identificar POI tem como base a utilização de clusters diários utilizando DBSCAN. Para o caso das trajectórias, o método Snap-to-Road foi o que originou melhores resultados. Verificou-se que foi possível responder ao problema inicial, desta forma, foi encontrado um método que identifica a maior parte dos POI com sucesso, bem como algumas trajetórias. Com base neste trabalho, existe uma oportunidade para futuramente melhorar alguns dos algoritmos e processos que possuem algumas limitações de modo a desenvolver soluções mais eficazes.2021-11-27T00:00:00Z2020-11-27T00:00:00Z2020-11-272020-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/21711TID:202576299engBento, Miguel José Candeiasinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:52:11Zoai:repositorio.iscte-iul.pt:10071/21711Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:25:58.636110Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
User behaviour identification based on location data |
title |
User behaviour identification based on location data |
spellingShingle |
User behaviour identification based on location data Bento, Miguel José Candeias Patterns Artificial intelligence GPS Padrões Inteligência artificial |
title_short |
User behaviour identification based on location data |
title_full |
User behaviour identification based on location data |
title_fullStr |
User behaviour identification based on location data |
title_full_unstemmed |
User behaviour identification based on location data |
title_sort |
User behaviour identification based on location data |
author |
Bento, Miguel José Candeias |
author_facet |
Bento, Miguel José Candeias |
author_role |
author |
dc.contributor.author.fl_str_mv |
Bento, Miguel José Candeias |
dc.subject.por.fl_str_mv |
Patterns Artificial intelligence GPS Padrões Inteligência artificial |
topic |
Patterns Artificial intelligence GPS Padrões Inteligência artificial |
description |
Over the years there has been an almost exponential increase in the use of new technologies in various sectors. These technologies have as their main objective, to improve or facilitate our daily life. This study will focus on one of these technologies used within a theme that has been widely talked about over the last few years, the use of personal data of various people to identify certain types of behavior. More specifically, this study aims primarily to use the GPS data stored in the respective Google accounts of nine volunteers in order to identify the places they frequent most, also known as Points of Interest. This same data will also be used to identify the trajectories covered more often by each of the same volunteers. A study was carried out with a sample of 9 participants, sending them their maps with POI and trajectories, thus obtaining their validation. It was thus possible to conclude that the best way to identify POI is to use daily clusters using DBSCAN. In the case of trajectories, the Snap-to-Road method was the one that gave the best results. It was found that it was possible to respond to the initial problem, and thus a method was found that identifies most of the POI successfully and also some trajectories.Based on this work, there is a great opportunity to improve some of the algorithms and processes that have some limitations in the future, and with this in mind it's possible to develop more effective solutions. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-11-27T00:00:00Z 2020-11-27 2020-10 2021-11-27T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/21711 TID:202576299 |
url |
http://hdl.handle.net/10071/21711 |
identifier_str_mv |
TID:202576299 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134822677872640 |