COMBINING DISCRIMINANT-BASED CLASSIFIERS, A STUDY IN DECISION LEVEL FUSION

منو

" COMBINING DISCRIMINANT-BASED CLASSIFIERS, A STUDY IN DECISION LEVEL FUSION "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	152003
Doc. No	:	ET23795
Main Entry	:	ROBERT G. GORE
Title Proper	:	COMBINING DISCRIMINANT-BASED CLASSIFIERS, A STUDY IN DECISION LEVEL FUSION
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Many successful pattern recognition solutions have been developed in recentyears, despite the fact that pattern recognition is ill-defined and difficult due to noiseand large variations in the input data. A promising approach is to fuse the decisioncapabilities of several classifier designs, such that they reduce the combined recognitionerror rate. This thesis confronts the recognition problem and proposes a method oftraining a Linear Fusion Network (LFN) using the Output-Reset (OR) algorithm.Training algorithms are enhanced by a closed form solution to OR. A linear network.............-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL47055.pdf
Title and statement of responsibility and	:	COMBINING DISCRIMINANT-BASED CLASSIFIERS, A STUDY IN DECISION LEVEL FUSION [Thesis]