Name
Abstract | ||
|---|---|---|
The availability of large geospatial data from dif- ferent sources has dramatically increased, but for the usage of such data in geo-mashup or context- aware systems, a data fusion component is neces- sary. To solve the integration issue classifiers are obtained by supervised training, with feature vec- tors derived from textual and geospatial attributes. In an application example, a coherent part of Ger- many was annotated by humans and used for super- vised learning. Annotation by humans is not free of errors, which decreases the performance of the classifier. We show how visual analytics techniques can be used to efficiently detect such false anno- tations. Especially the textual features introduce high-dimensional feature vectors, where visual an- alytics becomes important and helps to understand and improve the trained classifiers. Particular tech- nical components used in our systems are scatter- plots, multiple coordinated views, and interactive data drill-down. |
Year | Venue | Keywords |
|---|---|---|
2009 | VMV | visual analytics,geospatial data,feature vector,data fusion |
Field | DocType | Citations |
Data mining,Computer science,Visual analytics,Artificial intelligence,Supervised training,Classifier (linguistics),Geospatial analysis,Computer vision,Feature vector,Annotation,Sensor fusion,Supervised learning,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 14 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Harald Sanftmann | 1 | 20 | 3.12 |
| André Blessing | 2 | 26 | 9.20 |
| Hinrich Schütze | 3 | 2113 | 362.21 |
| Daniel Weiskopf | 4 | 2988 | 204.30 |