TitleDenver Groups Classification of Human Chromosomes Using CANN Teams Supplemented by a Nearest Neighbor Technique CANNT-S
Publication TypeJournal Article
Year of Publication2013
AuthorsGagula-Palalic, S, Can, M
JournalSoutheast Europe Journal of Soft Computing
Volume2
Issue2
Pagination63-68
Date Published09/2013
ISSN Number2233 -1859
Abstract

Human chromosomes can be classified into seven Denver groups (A – G) based on the position of the centromere. This classification is an important stage of human chromosome classification, as its output influence the second stage of classification, the correct classification of 24 classes of human chromosomes based on the banding pattern.In this article, the novel artificial neural network committee machines technique (CANNT) developed earlier is supplemented by a nearest neighbor technique, CANNT-S, and the correct classification rate in Denver Groups Classification of Human Chromosomes rose from 96% to a level of 98%.