When Individual Data Points Matter: Interactively Analysing Classification Landscapes

dc.contributor.authorSchneider, Brunoen_US
dc.contributor.authorMittelstädt, Sebastianen_US
dc.contributor.authorKeim, Daniel A.en_US
dc.contributor.editorTobias Isenberg and Filip Sadloen_US
dc.date.accessioned2016-06-09T09:33:30Z
dc.date.available2016-06-09T09:33:30Z
dc.date.issued2016en_US
dc.description.abstractThe selection of classification models among several options with similar accuracy cannot be done through purely automated methods, and especially in scenarios in which the cost of misclassified instances is crucial, such as criminal intelligence analysis. To tackle this problem and illustrate our ideas, we developed a prototype for the visualization and comparison of classification landscapes. In our system, the same data is given to different classification models. Classification landscapes are shown in the scatter plots, together with their geographical location on a map and detailed textual description for each data record. To enhance model comparison, we implemented interactive anchor-points selection in classification landscapes. Using those anchors, the user can manipulate and reproject the model results in order to get more comparable classification landscapes. We provided a use case with crime data, for crime intelligence analysis.en_US
dc.description.sectionheadersPosteren_US
dc.description.seriesinformationEuroVis 2016 - Postersen_US
dc.identifier.doi10.2312/eurp.20161130en_US
dc.identifier.isbn978-3-03868-015-4en_US
dc.identifier.issn-en_US
dc.identifier.pages13-15en_US
dc.identifier.urihttps://doi.org/10.2312/eurp.20161130en_US
dc.identifier.urihttps://diglib.eg.org:443/handle/10
dc.publisherThe Eurographics Associationen_US
dc.subjectI.5.2 [Pattern Recognition]en_US
dc.subjectDesign Methodologyen_US
dc.subjectClassifier design and evaluationen_US
dc.titleWhen Individual Data Points Matter: Interactively Analysing Classification Landscapesen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
013-015.pdf
Size:
771.03 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
a0-poster-1004-cready.pdf
Size:
801.86 KB
Format:
Adobe Portable Document Format