Title: Adaptive Novelty Detection with Generalized Extreme Value Distribution
Authors: Vrba, Jan
Citation: 2018 International Conference on Applied Electronics: Pilsen, 11th – 12th September 2018, Czech Republic, 169-172.
Issue Date: 2018
Publisher: Západočeská univerzita v Plzni
Document type: konferenční příspěvek
URI: http://hdl.handle.net/11025/35495
ISBN: 978–80–261–0721–7
ISSN: 1803–7232
Keywords: zpracování signálu;adaptivní systémy;adaptivní algoritmy;detekce změn;zobecněné rozdělení extrémních hodnot
Keywords in different language: signal processing;adaptive systems;adaptive algorithms;novelty detection;generalized extreme value distribution
Abstract in different language: This paper introduces the new adaptive novelty detection method. The proposed method is using generalized extreme value distribution to evaluate the absolute value of adaptive system weight increments in time. The detection of novelty is threshold-based and the threshold ζ corresponds to the value of joint probability density function. Performance of the proposed algorithm is shown on artificial data. For comparison also results of Learning Entropy algorithm are shown, as this algorithm also evaluates the increments of adaptive weights.
Rights: © Západočeská univerzita v Plzni
Appears in Collections:Applied Electronics 2018
Applied Electronics 2018

Files in This Item:
File Description SizeFormat 
Vrba.pdfPlný text851,47 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/35495

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.