Title: ROC Analysis of Extreme Seeking Entropyfor Trend Change Detection
Authors: Vrba, Jan
Mareš, Jan
Citation: 2020 International Conference on Applied Electronics: Pilsen, 8th – 9h September 2020, Czech Republic.
Issue Date: 2020
Publisher: Západočeská univerzita v Plzni
Document type: conferenceObject
konferenční příspěvek
URI: http://hdl.handle.net/11025/39932
ISBN: 978-80-261-0891-7 (Print)
978-80-261-0892-4 (Online)
ISSN: 1803-7232 (Print)
1805-9597 (Online)
Keywords: zpracování signálu;adaptivní systémy;adaptivní algoritmy;detekce novinky;detekce změny trendu
Keywords in different language: signal processing;adaptive systems;adaptive algorithms;novelty detection;trend change detection
Abstract in different language: This paper is dedicated to the evaluation ofthe ROC curve of recently introduced Extreme SeekingEntropy algorithm. The ROC curve is evaluated for atrend change in the signal that contains additive Gaussiannoise. The resulting ROC curve of the Extreme SeekingEntropy algorithm is compared with other adaptivenovelty detection methods, namely Learning Entropyand Error and Learning Based Novelty Detection asthose algorithms are also evaluating the adaptive weightsincrements. The ROC curves are evaluated for multiplenoise variances and area under those ROC curves isestimated.
Rights: © Západočeská univerzita v Plzni
Appears in Collections:Applied Electronics 2020
Applied Electronics 2020

Files in This Item:
File Description SizeFormat 
09232845.pdfPlný text314,76 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/39932

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