A Study for the Feature Selection to Identify GIEMSA-Stained Human Chromosomes Based on Artificial Neural Network
Abstract
Many studies for computer-based chromosome analysis have shown that it is possible to classify chromosomes into 24 subgroups. In addition, artificial neural network (ANN) has been adopted for the human chromosome classification. It is important to select optimum features for training neural network classifier. We selected some features - relative length, normalized density profile (d.p) and centromeric index - used to identify chromosomes and trained neural network classifier changing the number of samples which used to get d.p. We found the fact that the classification error showed to be minimum when this number was equal to or greater than the length of No. 1 human chromosome.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 25, 2001
- Accession Number
- ADA410471
Entities
People
- Jong M. Cho
- Seung H. Woo
- Seung Y. Ryu
Organizations
- Inje University