Transcript PPT

DISCOVERING PATTERNS OF INSURGENCY VIA SPATIO-TEMPORAL DATA MINING
James P.Rogers¹, James A.Shine¹, Shashi Shekhar², Mete Celik²
¹U.S. Army ERDC, Topographic Engineering Center, VA, USA {james.p.rogers.II, james.a.shine}@erdc.uasce.army.mil
²Department of Computer Science, University of Minnesota, MN, USA {shekhar,mcelik}@cs.umn.edu
Abstract
Motivating Example: Input
The need to discover patterns in spatio-temporal (ST)
data has driven much recent research in ST cooccurrence patterns. Early work focused on spatial
patterns such as co-location ignoring the temporal
aspects of ST datasets. This work describes a novel
set of co-occurrence patterns called mixed-drove cooccurrence patterns (MDCOPs). They represent
subsets of two or more different ST object types
whose instance are close to each other spatially and
temporally.
Algorithms
Object Types
Challenges
Output
Problem Statement
Experimental Evaluation
Figure 1
POSTER TEMPLATES BY:
www.POSTERPRESENTATIONS.com
Figure 2
Figure 3
Figure 4