CLASSIFICATION OF POLYNOMIAL-SHAPED MEASUREMENT SIGNALS USING A BACKPROPAGATION NEURAL-NETWORK

Authors
LAMPINEN J OVASKA SJ UGAROV A
Citation
J. Lampinen et al., CLASSIFICATION OF POLYNOMIAL-SHAPED MEASUREMENT SIGNALS USING A BACKPROPAGATION NEURAL-NETWORK, IEEE transactions on instrumentation and measurement, 43(6), 1994, pp. 933-936
Citations number
6
Categorie Soggetti
Engineering, Eletrical & Electronic","Instument & Instrumentation
Journal title
IEEE transactions on instrumentation and measurement → ACNP
ISSN journal
00189456
Volume
43
Issue
6
Year of publication
1994
Pages
933 - 936
Database
ISI
SICI code
0018-9456(1994)43:6<933:COPMSU>2.0.ZU;2-B
Abstract
Smoothly varying signals are frequently encountered in the field of in strumentation and measurement, and they can be accurately modeled by l ow-order polynomials. The order identification is difficult when the m easured noisy signal has frequent order variations in the underlying p olynomial. In this paper, we introduce a flexible real-time order esti mator, which is based on a backpropagation neural network.