MASS LESION DETECTION WITH A FUZZY NEURAL NETWORK

منو

" MASS LESION DETECTION WITH A FUZZY NEURAL NETWORK "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151394
Doc. No	:	ET23186
Main Entry	:	Muyi Cui
Title Proper	:	MASS LESION DETECTION WITH A FUZZY NEURAL NETWORK
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	This thesis presents a new fuzzy neural network (FNN) approach to detect malignantmass lesions on mammograms. The FNN used has four layers. The first layer is the inputlayer consisting of four input fuzzy neurons. The second layer has four ordinary neurons.The third layer consists of n maximum fuzzy neurons. The number of fuzzy neurons inthe third layer is determined during the training process and varies with the networkparameters and data distribution. The fourth layer has two maximum fuzzy neurons andone competitive fuzzy neuron. Mammograms were obtained from the digital database forscreening mammography (DDSM) at the University of South Florida. Six-hundred-seventy regions of interest (ROls) were extracted from 100 mammograms. All extractedROIs are randomly divided into two groups: training and testing....-....,....-...,..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	:	TL46422.pdf
Title and statement of responsibility and	:	MASS LESION DETECTION WITH A FUZZY NEURAL NETWORK [Thesis]