Thales Sehn Korting

• Course: Remote Sensing(INPE)
• Level: PhD
• Graduation: Computer Engeneering
• Advisors: Dr. Leila Maria Garcia Fonseca and Dr. Gilberto Câmara
• Research: Geographical Data Mining
• Contact: tkorting@dpi.inpe.br
• CV: Lattes

Several themes:

• Temporal Data Mining
  • Evolving Objects
  • Change Mining
  • Extend CBR
• Sustainable Computation
  • Deforestation
  • Urban analysis
  • Application or software (?)
• Image Segmentation
  • Scale-Space
  • Attributes-Space
• Visualization Techniques for Geographical Databases
• Parallel algorithms
  • Segmentation
  • Classification

• Qual a hipótese serve de base para o trabalho? It is possible to set a temporal signature to forest degradation.
• O que estamos querendo demonstrar ou explicar? Forest degradation are defined by smooth (light, slim, slight?), moderate and intense levels. With a set of snapshots from remote sensing images, one can develop an algorithm to detect such levels of degradation and to model its temporal signature.
• Qual a pergunta científica que vai ser respondida? Forest degradation can be modelled?

The project entitled Geographical Data Mining Analyst - GeoDMA, is a plugin for TerraView software, used for geographical data mining. With a single image, the user can perform segmentation, attributes extraction, normalization and classification. More information at GeoDMA homepage. This project has started in 2008 and will finish in 2011, with funding resources by CAPES.

In the following figures we show some screenshots of GeoDMA and TerraView interface.

GeoDMA is available for download at the GeoDMA official homepage.

Full-access to pdf and bibliographic information, in my homepage.

• Thales Sehn Korting, Luciano Vieira Dutra, Leila Maria Garcia Fonseca. Detecting Rectangular Objects in Urban Imagery - A Re-Segmentation Approach. VISAPP. Lisbon, Portugal. 2009.
• Thales Sehn Korting, Leila Maria Garcia Fonseca, Maria Isabel Sobral Escada, Gilberto Câmara. GeoDMA - Um sistema para mineração de dados de sensoriamento remoto. Simpósio Brasileiro de Sensoriamento Remoto. Natal, RN, Brasil. 2009.
• Thales Sehn Korting, Leila Maria Garcia Fonseca, Maria Isabel Sobral Escada, Felipe Castro da Silva, Marcelino Pereira dos Santos Silva. GeoDMA - A novel system for spatial data mining. Data Mining Workshops, 2008. ICDMW '08. IEEE International Conference on. Pisa, Italy. 2008.
• Thales Sehn Korting, Felipe Castro da Silva. WebDMA - Data Mining Analyst Web Service. GI-Days Young Researchers Forum. Munster, Germany. 2007.

• Bottcher, M. & Hoppner, F. & Spiliopoulou, M. SIGKDD Newsletter, Volume 10, Issue 2. On Exploiting the Power of Time in Data Mining, 2008.
• Han, J. & Kamber, M. Data mining: concepts and techniques Morgan Kaufmann, 2006
• Hastie, T.; Tibshirani, R. & Friedman, J. The elements of statistical learning: data mining, inference, and prediction. Springer, 2001
• Langran, G. Time in geographic information systems. Taylor & Francis, 1992
• Miller, H. & Han, J. Geographic data mining and knowledge discovery. CRC Press, 2001
• Pelekis, N.; Theodoulidis, B.; Kopanakis, I. & Theodoridis, Y. Literature review of spatio-temporal database models. The Knowledge Engineering Review, Cambridge Univ Press, 2005, 19, 235-274
• Rasinmäki, J. Modelling spatio-temporal environmental data. Environmental Modelling & Software, 2003, 18, 877 - 886