On-line probabilistic classification with particle filters

Autor:	P.A.d.F.R. Hojen-Sorensen, T. Fog, N. de Freitas
Rok vydání:	2002
Předmět:	Engineering Probabilistic classification Artificial neural network business.industry Classification scheme Pattern recognition Fault detection and isolation Simple (abstract algebra) Line (geometry) SDG 14 - Life Below Water Artificial intelligence business Particle filter Parametric statistics
Zdroj:	Højen-Sørensen, P, de Freitas, N & Fog, T L 2000 probabilistic classification with particle filters . in Proceedings of the 2000 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing X, 2000. . IEEE, 2000 IEEE Workshop on Neural Networks for Signal Processing X, Sydney, New South Wales, Australia, 11/12/2000 . https://doi.org/10.1109/NNSP.2000.889430
Popis:	We apply particle filters to the problem of on-line classification with possibly overlapping classes. This allows us to compute the probabilities of class membership as the classes evolve. Although we adopt neural network classifiers, the work can be extended to any other parametric classification scheme. We demonstrate our methodology on a simple example and on the problem of fault detection of dynamically operated marine diesel engines.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6108f902a9db7090cb0a29ea191d2c04 https://doi.org/10.1109/nnsp.2000.889430 Zobrazit plný text záznamu