|
Title:
|
GEOSPATIAL DATA MINING PROBLEMS |
|
Author(s):
|
Magdalene Grantson Borgelt |
|
ISBN:
|
978-972-8924-40-9 |
|
Editors:
|
Jörg Roth, Jairo Gutiérrez and Ajith P. Abraham (series editors: Piet Kommers, Pedro Isaías and Nian-Shing Chen) |
|
Year:
|
2007 |
|
Edition:
|
Single |
|
Keywords:
|
Geospatial data, data mining techniques, association rules, clustering, outlier detection. |
|
Type:
|
Poster/Demonstration |
|
First Page:
|
227 |
|
Last Page:
|
229 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
While classical data mining is mainly concerned with relational and transactional data, geospatial data mining works on
data that is embedded into (Euclidean) space. As a consequence, simply applying classical data mining techniques to
geospatial data leads to problems, due to the special meaning of geographical features, the need for non-relational data
structures, and failing independence assumptions. We study some of these problems and ways of coping with them. |
|
|
|
|
|
|
