Map matching: uma análise de dados streaming de trajetórias de GPS no transporte público
Ensuring public transport that meets the needs of a growing population is a challenge, especially in developing countries where resources and investment are limited. With the cheapening and installation of Internet of Things (IoT) devices such as embedded, sensors, Global Positioning System (GPS) in...
| Autor principal: | Martins, Tiago Stapenhorst |
|---|---|
| Formato: | Dissertação |
| Idioma: | Português |
| Publicado em: |
Universidade Tecnológica Federal do Paraná
2022
|
| Assuntos: | |
| Acesso em linha: |
http://repositorio.utfpr.edu.br/jspui/handle/1/30064 |
| Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
| Resumo: |
Ensuring public transport that meets the needs of a growing population is a challenge, especially in developing countries where resources and investment are limited. With the cheapening and installation of Internet of Things (IoT) devices such as embedded, sensors, Global Positioning System (GPS) in public transport buses, a large amount of data can be generated and used as basis for decision making. However, if the data are affected by errors and uncertainties such analyzes may be invalid. The open data on the movement of buses in Curitiba is vast, but they present inconsistencies and do not inform the time of passage of buses at bus stops. The large amount of data by itself will be valuable if processing and algorithms extract the value of this data. This work presents a four-step method to analyze the Streaming data from GPS trajectories, containing 1) data analysis and cleaning; 2) extraction of azimuths; 3) a method for detecting the moment (time) of buses passing at the respective bus stops of their operating line and 4) correlation of the real and theoretical times of passing at the bus stops. Concepts of Geographic Information Systems, Smart Cities and Open Data are used. Tests performed on open Streaming data from GPS trajectories of public transport in Curitiba illustrated the efficiency of the methodology of the proposed algorithms, in addition to indicating factors for data improvement. |
|---|