Název:	Comparison of One-Dimensional and Two-Dimensional Reference Signal Representation for Insulation Aging State Recognition
Autoři:	Olkhovskiy, Mikhail Müllerová, Eva Martínek, Petr
Citace zdrojového dokumentu:	OLKHOVSKIY, M. MÜLLEROVÁ, E. MARTÍNEK, P. Comparison of One-Dimensional and Two-Dimensional Reference Signal Representation for Insulation Aging State Recognition. In Proceedings of the 2022 International Conference on Diagnostics in Electrical Engineering (Diagnostika) : CDEE 2022. Pilsen: University of West Bohemia in Pilsen, 2022. s. nestránkováno. ISBN: 978-1-66548-082-6
Datum vydání:	2022
Nakladatel:	University of West Bohemia in Pilsen
Typ dokumentu:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85141397372 http://hdl.handle.net/11025/50534
ISBN:	978-1-66548-082-6
Klíčová slova v dalším jazyce:	one-dimensional neural networks;convolutional networks;reference signal processing;signal analysis;cable insulation;classification accuracy
Abstrakt v dalším jazyce:	This paper compares the performance of one-dimensional and two-dimensional convolutional neural networks in the task of analyzing a reference signal while determining the degradation level of single-core polymer-insulated cable. In this work was designed the set of reference signals and several forms of representing of these signals in the form of one-dimensional and two-dimensional tensors. Then, an experimental determination of the most effective version of the reference signal is carried out in terms of classification accuracy and the most effective form of representation of this signal was found, as well as most efficient type of neural network.
Práva:	© IEEE
Vyskytuje se v kolekcích:	OBD

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.