Learning in dynamic environments: application to the diagnosis of evolving systems

DOI

10.2991/eusflat.2011.40How to use a DOI?

Keywords

Classification; incremental learning; dynamic environments; evolving systems.

Abstract

In dynamic environments, data characteristics may drift over time. This leads to deteriorate dramatically the performance of incremental learning algorithms over time. This is because of the use of data which is no more consistent with the characteristics of new incoming one. In this paper, an approach for learning in dynamic environments is proposed. This approach integrates a mechanism to use only the recent and useful patterns to update the classifier without a "catastrophic forgetting". This approach is used for the acoustic leak detection in the steam generator unit of the nuclear power generator "Prototype Fast React".

Copyright

© 2011, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Moamar Sayed-Mouchaweh
AU  - Omar Ayad
AU  - Noureddine Malki
PY  - 2011/08
DA  - 2011/08
TI  - Learning in dynamic environments: application to the diagnosis of evolving systems
BT  - Proceedings of the 7th conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-11)
PB  - Atlantis Press
SP  - 396
EP  - 401
SN  - 1951-6851
UR  - https://doi.org/10.2991/eusflat.2011.40
DO  - 10.2991/eusflat.2011.40
ID  - Sayed-Mouchaweh2011/08
ER  -