Titulo Estágio
Implementation of the FireLoc Application
Áreas de especialidade
Engenharia de Software
Local do Estágio
DEI
Enquadramento
FireLoc is a research project funded by Fundação para a Ciência e a Tecnologia. It aims at developing a system that will allow:
1) the report of a spotted fire by any volunteer citizen provided with a smartphone, including automatic geolocation (place of observation), imagery of what is being observed (e.g. photograph taken with the smartphone), and data enabling to georeference the observed phenomenon - namely, the orientation (automatically picked up from the smartphone) and the approximate distance between the observer and the observed event;
2) the identification, for each contribution, of the approximate geolocation of the observed event, the degree of confidence of data received (whose determination will be based on volunteer’s credibility according to the personal profile and history of contributions), and the geographic context of both sites, the observation site and event site (this will be based on land cover information of the vicinity of both sites and on digital terrain models);
3) the integration and processing of data made available by volunteers who are meant to provide data/information almost in real time on geolocation, severity and extent of the observed phenomena.
This system comprises three components:
a) a data collection component, which will be developed for mobile platforms;
b) a data integration and processing component, which includes a geospatial component, and therefore will be developed using Geographic Information Systems, and will allow the evaluation of credibility of reported information and also the identification of the geolocation of events and their geospatial extent;
c) a component for providing information to the general public and institutions, which will be developed for both mobile and desktop platforms and will allow the monitoring of the reported events’ progress.
Objetivo
FireLoc will allow the development of an innovative system capable of reporting, integrating, and validating georeferenced data in real-time related to forest fires. This will allow in turn the monitoring of a fire progress totally based on information provided by citizens. Strong aspects are as follows: 1) all citizens are potential users and can in fact report spotted fires – given the fact that in Portugal’s rural areas many villages and local communities are part of the forest fabric itself, these citizens constitute valuable potential users of the proposed system that can be extremely useful in quickly detecting & reporting new fire occurrences; 2) a system where visual perception of the geolocation of reported events is evident; 3) a system that can be used not only by the general public, but also by authorities – different sorts of user-profiles will be allowed providing each type of user with specific sorts of services and specific sorts of information according to the typical user-profile needs. Limitations typically associated to a system with such characteristics, mainly refer to the quality and reliability of data/information provided by volunteer citizens. That is why the incorporation in the system of adequate methodologies capable of validating data/information provided by volunteers constitutes precisely one of the main challenges of this project.
In this internship, the student should develop several parts of the system that do not exist yet, such as the web forms where users submit their information; use Machine Learning algorithms, possibly available on the cloud, to identify the location and extension of the fire; and, finally, make the information available to the general public. The latter part of the work will receive contributions from other team members and from systems that already exist.
Plano de Trabalhos - Semestre 1
- Define the requirements of the system (1 months);
- Evaluate Machine Learning algorithms (1 month);
- Define the architecture of the system (1 months);
- Start implementing the forms for information submission (1 month)
- Write intermediate report (1 month);
Plano de Trabalhos - Semestre 2
- Implement the system (2 months);
- Select and configure the machine learning algorithms (2 months)
- Test and evaluate performance (1 months);
- Write final report (1 month);
Condições
This work should take place in the context of the FireLoc research project. A 3-month scholarship of 745 euros per month is foreseen for this work. If the work goes according to planned, a 3-month extension, for a total of 6 months is foreseen.
Orientador
Filipe Araújo e Alberto Cardoso
filipius@uc.pt 📩