Fig 9.TIF (411.51 kB)
The AUC values for the large kdd99 dataset for 0 < k < 100.
figure
posted on 2016-04-19, 05:27 authored by Markus Goldstein, Seiichi UchidaIt can be easily seen that the performance of local anomaly detection algorithms is poor for this global anomaly detection challenge.
History
Usage metrics
Categories
Keywords
Comparative EvaluationdatasetUnsupervised Anomaly Detection Algorithmsalgorithm selectionanomaly detectionclassification tasksfraud detectionlife sciencesource codeunsupervised anomaly detection researchanomaly detection performanceunsupervised anomaly detection algorithmsMultivariate Data Anomaly detectionunsupervised anomaly detectionnetwork intrusion detectionparameter settingsapplication domainsresearch community
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC