TY - GEN
T1 - Understanding hotspots
T2 - 23rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2015
AU - Lukasczyk, Jonas
AU - Maciejewski, Ross
AU - Garth, Christoph
AU - Hagen, Hans
N1 - Funding Information:
Some of the material presented here was sponsored by Department of Defense and is approved for public release, case number 15-383 and upon work supported by the NSF under Grant No. 1350573.
PY - 2015/11/3
Y1 - 2015/11/3
N2 - Analysis of spatio-temporal event data is of central importance in many domains of science and policy making. Current visualization methods rely on animation, small multiples, and space-time cubes to enable spatio-temporal data exploration. These methods require the user to remember state spaces or deal with layout occlusions when exploring their data. To overcome such issues, we propose a novel visualization technique for such data that applies the topological notion of Reeb graphs to identify hotspots as areas of relatively high event density within kernel density estimates. We illustrate that the topological identification of hotspots proposed in this paper is able to elucidate lifetime, properties, and relationships of hotspots by visualizing their temporal evolution based on the spatio-temporal Reeb graph. To validate our approach, we demonstrate our method on an epidemiological and a crime dataset. The resulting visualizations assist users in quickly identifying and comprehending important dates, events, hotspot properties, and relationships between hotspots.
AB - Analysis of spatio-temporal event data is of central importance in many domains of science and policy making. Current visualization methods rely on animation, small multiples, and space-time cubes to enable spatio-temporal data exploration. These methods require the user to remember state spaces or deal with layout occlusions when exploring their data. To overcome such issues, we propose a novel visualization technique for such data that applies the topological notion of Reeb graphs to identify hotspots as areas of relatively high event density within kernel density estimates. We illustrate that the topological identification of hotspots proposed in this paper is able to elucidate lifetime, properties, and relationships of hotspots by visualizing their temporal evolution based on the spatio-temporal Reeb graph. To validate our approach, we demonstrate our method on an epidemiological and a crime dataset. The resulting visualizations assist users in quickly identifying and comprehending important dates, events, hotspot properties, and relationships between hotspots.
KW - Density estimation
KW - Geovisualization
KW - Hotspots
KW - Reeb graph
KW - Spatio-temporal event data
KW - Topology
UR - http://www.scopus.com/inward/record.url?scp=84961207954&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961207954&partnerID=8YFLogxK
U2 - 10.1145/2820783.2820817
DO - 10.1145/2820783.2820817
M3 - Conference contribution
AN - SCOPUS:84961207954
T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
BT - 23rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2015
A2 - Huang, Yan
A2 - Ali, Mohamed
A2 - Sankaranarayanan, Jagan
A2 - Renz, Matthias
A2 - Gertz, Michael
PB - Association for Computing Machinery
Y2 - 3 November 2015 through 6 November 2015
ER -