Titulo Estágio
POI mining and generation
Área Tecnológica
Artificial Intelligence, Ubiquitous Computing
Local do Estágio
DEI
Enquadramento
With the current broad use of location aware devices, the activity of geo-tagging is becoming normal. The most atomic unit of this activity is the Point Of Interest (or landmark) which consists of a pair of Latitude/Longitude coordinates and a tag, normally the name of the place, a word that unambiguously identifies it and, possibly, some extra information such as the category of the POI.
POIs can be used in navigation, characterization of a place, sociology, city dynamics analysis, geo-reference of texts, etc. Such a simple information structure can be used and enriched such that context-aware systems behave more intelligently.
However, the production of POIs is scattered across a myriad of different websites, systems, devices, etc. thus making it extremely difficult to obtain an exhaustive database of such extremely wealthy information. In this project, we intend to explore a number of techniques to overcome this problem.
Objetivo
This project will consist of two main research approaches:
- Enumeration and exploration of organized online resources that contain/provide POI lists. This should include Yellow Pages, Yahoo! directories, POI factory, etc. The system should extract and store locally the POIs from these resources.
- Automatic generation of new POIs out of data analysis of geo-codable information. An example is the use of Flickr database to infer places that are, for one reason or the other, of interest to a number of users
This project is directly related to the AIDA, CityMotion and SOTUR projects with MIT, IST and FEUP.
Plano de Trabalhos - Semestre 1
During the first semester, the student will perform the following tasks:
- October 15th – State of the art (1.5 months)
- October 31st - Understanding of the CityMotion platform + Requirements specification (2 months)
- November 30th - Approach 1 implementation. (1 month)
- December 15th – Experimentation. (1 month)
- January 15th - Paper submission (2 months)
- February 27th - Intermediate report including requirements specification for approach 2. (1 month)
Plano de Trabalhos - Semestre 2
During the second semester, the student will perform the following tasks:
- March 30th – Analysis of potential sources for POI generation (1 months)
- May 30th - Implementation of approach 2 (2.5 months)
- June 30th – Experiments. (1.5 months)
- July 10th - MSc thesis (1 months)
Condições
Strong skills in programming (Java), Web crawling, screen scrapping.
Will to communicate in English with other researchers is also important.
Other interesting skills include Information Extraction techniques, Artificial Intelligence, Ubiquitous Computing
Orientador
Francisco Câmara Pereira
camara@dei.uc.pt 📩