Knowledge Uncertainty and Composed Classifier

0307496 - ÚTIA 2008 RIV US eng J - Journal Article
Klimešová, Dana - Ocelíková, E.
Knowledge Uncertainty and Composed Classifier.
[Neurčitost znalostí a složený klasifikátor.]
International Journal of Circuits, Systems and Signal Processing. Roč. 1, č. 2 (2007), s. 101-105. ISSN 1998-0140
Institutional research plan: CEZ:AV0Z10750506
Keywords : Boosting architecture * contextual modelling * composed classifier * knowledge management, * knowledge * uncertainty
Subject RIV: IN - Informatics, Computer Science

The paper discuss the problem of wide context (temporal, spatial, local, objective, attribute oriented, relation oriented) as a tool to compensate and to decrease the uncertainty of data, classification and analytical process at all process to increase the information value of decision support. The contribution deals with a problem of creating the composed classifier with boosting architecture, whose components are composed of classifiers working with k - NN algorithm (k - th nearest neighbour).

Příspěvek je věnován problematice širokého kontextu z hlediska jeho možností kompenzovat neurčitost dat.
Permanent Link: http://hdl.handle.net/11104/0160247