Variance estimation for two-class and multi-class ROC analysis using operating point averaging
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F08%3A00317798" target="_blank" >RIV/67985556:_____/08:00317798 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Variance estimation for two-class and multi-class ROC analysis using operating point averaging
Original language description
Receiver Operator Characteristic (ROC) analysis enables fine-tuning of a trained classifier to a desired error trade-off situation. ROC estimated from a single test set is, however, insufficient for the sake of classifier comparison as it neglects performance variances. This research presents a practical algorithm for variance estimation at individual operating points of ROC curves or surfaces. It generalizes the threshold averaging of Fawcett et.al. to arbitrary operating point definition including theweighting-based formulation used in multi-class ROC analysis. The statistical test of comparison of performance differences between operating points of the same curve is illustrated for two-class and multi-class ROC.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2008
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings on the 19th International Conference on Pattern Recognition
ISBN
978-1-4244-2174-9
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
IEEE
Place of publication
Tampa
Event location
Tampa
Event date
Dec 8, 2008
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—