ROBUST ENSEMBLE CLASSIFIERS THEIR APPLICATIONS TO LANDMINE DETECTION

منو

" ROBUST ENSEMBLE CLASSIFIERS THEIR APPLICATIONS TO LANDMINE DETECTION "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150516
Doc. No	:	ET22308
Main Entry	:	Yijun Sun
Title Proper	:	ROBUST ENSEMBLE CLASSIFIERS THEIR APPLICATIONS TO LANDMINE DETECTION
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	AdaBoost is one of the most important recent developments in the classi-fication methodology. AdaBoost works by repeatedly applying the base learningalgorithm to the re-sampled versions of the training data to produce a coIlection ofhypothesis functions which are finally combined via a weighted linear vote to formthe final decision. Under mild assumptions, AdaBoost can lead to a classification al-gorithm with arbitrary accuracy. By pursuing a large norm-l margin, Adaalso significantly improve the generalization performances in many cases. However,recent studies showed that AdaBoost performs poorly on noisy data. In this workwe present several new regularized boosting algorithms to mitigate the overfitting-...,..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	:	TL45514.pdf
Title and statement of responsibility and	:	ROBUST ENSEMBLE CLASSIFIERS THEIR APPLICATIONS TO LANDMINE DETECTION [Thesis]