| 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.
|
|---|