Győző Gidófalvi, Associate Professor

Picture of Gy—z— Gidófalvi

Geoinformatics, KTH
Drottning Kristinas väg 30
100 44 Stockholm

Room: 5053
Phone: +46 8-790 70 21
Fax: +46 8-790 85 80
Email: gyozo.gidofalvi(a)

"The sciences do not try to explain, they hardly
even try to interpret, they mainly make models.
By a model is meant a mathematical construct
which... describe observed phenomena. The
justification of such a mathematical construct
is solely and precisely that it is expected to
- John von Neumann


I am an Associate Professor at the Geodesy and Geoinformatics Division at the Department for Urban Planning and Environment at the Royal Institute of Technology (KTH) in Stockholm, Sweden. My main research interests include spatio-temporal data mining and analysis, Location-Based Services (LBS), locations privacy, Intelligent Transportation Systems (ITS), and related GIS areas such as web and mobile GIS and spatial databases. Previously, I have been a Postdoctoral Fellow at the Uppsala Database Laboratory (UDBL) at the Department of Information Technology, Uppsala University, where I was involved in the iStreams project, where my task was to develop methods and tools for analyzing and mining high-volume industrial data streams. During my industrial Ph.D. study at Geomatic a/s and Aalborg University, I have been focusing on developing Spatio-Temporal Data Mining Methods for Location-Based Services. During my M.Sc. study at the University of California, San Diego, I have been mainly focusing on financial text mining, but I also have had some experience in connectionist learning methods, genetic algorithms, statistical learning methods, and computer vision. For more information please refer to my CV.

Ph.D. Study

Spatio-temporal Data Mining for Location-based Services
(Industrial Ph.D. study at Geomatic a/s and Aalborg University, Denmark)
Abstract: Recent advances in communication and information technology, such as the increasing accuracy of GPS technology and the miniaturization of wireless communication devices pave the road for Location-Based Services (LBS). To achieve high quality for such services, data mining techniques are suggested for the analysis of the huge amount of data collected from location-aware mobile devices. Since the two most important attributes of the data collected is time and location, the objective of this study is to develop spatio-temporal data mining techniques to extract interesting knowledge for LBS. The company Geomatic-employer of the candidate-presently works with advanced data mining techniques on geo-statistical data, and foresees highly promising business opportunities in LBS.

Final thesis: short abstract and full version.