Detalhes bibliográficos
| Ano de defesa: |
2017 |
| Autor(a) principal: |
Diego Vilela Monteiro |
| Orientador(a): |
Karine Reis Ferreira,
Rafael Duarte Coelho dos Santos |
| Banca de defesa: |
Pedro Ribeiro de Andrade Neto,
Sandro Klippel |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
eng |
| Instituição de defesa: |
Instituto Nacional de Pesquisas Espaciais (INPE)
|
| Programa de Pós-Graduação: |
Programa de Pós-Graduação do INPE em Computação Aplicada
|
| Departamento: |
Não Informado pela instituição
|
| País: |
BR
|
| Link de acesso: |
http://urlib.net/sid.inpe.br/mtc-m21b/2017/07.06.12.27
|
Resumo: |
Spatiotemporal data are everywhere, being collected from different devices such as Earth Observation and GPS satellites, sensor networks, vehicles and smartphones. Data collected from those devices may contain valuable information about different subjects, including environmental monitoring, weather as well as mobility. Of these subjects, one of particular interest is moving objects trajectory data. In order to process this kind of data, there is a need for high-level programming environments that allow users to quickly and easily develop new algorithms. In this work, I propose a framework that extends the R environment for big trajectory data mining. I designed and developed two new packages that allow R users to efficiently deal with big trajectory data sets and fast implement new mining algorithms over them. I also propose an efficient method to discover partners in moving object trajectories. Such method identifies pairs of trajectories whose objects stay together during certain periods, based on distance time series analysis. Finally, I validate both the framework and method via case studies. |
