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.

Open PDF

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

Tags

DTIC Thesaurus Topics

  • Amniotic Fluid
  • Biomedical Engineering
  • Biomedical Research
  • Cells
  • Character Recognition
  • Chromosomes
  • Classification
  • Data Sets
  • Databases
  • Engineering
  • Feature Extraction
  • Feature Selection
  • Genetics
  • Machine Learning
  • Neural Networks
  • Test Sets
  • Training

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Molecular and genetic basis of cancer.
  • Psychometric Testing or Psychological Assessment.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks