Data Mining on Spatial Data
Qin Ding
Department of Computer Science, Penn State Harrisburg
Tuesday, February 25, 2003 14:00-15:00,
Room 145, NIST North (820)
Gaithersburg
Tuesday, February 25, 2003 12:00-13:00,
Room 4550
Boulder
Abstract:
The progress of data-collection technology, such as bar-code scanners
in
commercial domains and sensors in scientific and industrial domains,
generates massive amounts of data. This explosive growth in data
generates the need for new techniques and tools that can intelligently
and automatically transform the data into useful information and
knowledge.
Data mining, also referred to as knowledge discovery in databases
(KDD),
is a process of nontrivial extraction of implicit, previous unknown
and potentially useful information (such as knowledge rules, constrains,
regularities) from data in databases. Various data mining techniques
have
been proposed, including association rule mining, classification,
clustering,
etc. Data mining techniques have been applied to many areas, such as
market
basket data, web data, DNA data, text data, and spatial data.
Extracting interesting patterns and rules from spatial datasets, such
as remotely sensed imagery and associated ground data, can be of
importance
in precision agriculture, community planning, resource discovery and
other
areas. However, in most cases the image data sizes are too large to be
mined in a reasonable amount of time using existing algorithms. In this
seminar, we will introduce approaches to perform efficient and effective
data mining (including association rule mining, classification, and
clustering) on spatial data using Peano Count Tree (P-tree) structure.
P-tree structure facilitates significant pruning techniques and proves
to be a promising approach to spatial data mining.
Contact: J. E. TerrillNote: Visitors from outside NIST must contact
Robin Bickel; (301) 975-3668;
at least 24 hours in advance.
|
