[ ILPnet2 | Library | Newsletter | CSCW | Education | End-User Club | Events | Nodes | Systems | Applications | Members only ]
Knowledge Discovery in Spatial Data by Means of ILP
L. Popelinsky.
In J. M. Zytkow
and M. Quafafou, editors, Principles of Data Mining and
Knowledge Discovery. PKDD'98 Nantes France., volume 1510 of Lecture
Notes in Computer Science, pages 271--279. Springer Verlag, September
1998.
Abstract
The paper shows that ILP can serve as a powerful tool for spatial data mining.
The presented approach proceeds in the direction started by GeoMiner. There
are developed arguments to prove that ILP technigues suggested for database
schema design in deductive O-O databases are not only re-usable for spatial
data mining, but that their experessive power overcomes some other mining
methods used in this context. There is proposed an inductive query language
with rich semantics which allows to express some improved versions of queries
used by DBMiner. Moreover, the new query language introduces a new feature, a
dependency rule, which allows to compare two or more subsets by searching for
qualitative characterization of their mutual difference. Preliminary version
of the QWiM minig system implementing the described ILP features is available
on request from the author (popel@fi.muni.cz).
BibTeX entry.
Other publications
ILPnet2 librarian,
ilpnet2-lib@cs.bris.ac.uk. Last modified on Wednesday 9 April 2003 at 18:31. © 2003 ILPnet2