Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Mouse chromosome classification by radial basis function network with fast orthogonal search.

M T. Musavi1, R J. Bryant, M Qiao

  • 1Department of Electrical and Computer Engineering, University of Maine, Orono, USA

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[The best preferable sagittal vertical axis for the ankylosis spondylitis with thoracolumbar kyphosis following one-level pedicle subtraction osteotomy under different cervical range of motion].

Zhonghua yi xue za zhi·2025
Same author

[Role of intercellular adhesion molecule-1 in adhesion and migration of mesenchymal stem cells in ankylosing spondylitis and its mechanisms].

Zhonghua yi xue za zhi·2024
Same author

[Adrenal cortical carcinoma in children: a clinicopathological analysis of 25 cases].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2024
Same author

Novel chlorine-extending polymer coating with prolonged antiviral activity against SARS-CoV-2.

Letters in applied microbiology·2022
Same author

[Association between root abnormalities and related pathogenic genes in patients with generalized aggressive periodontitis].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·2021
Same author

[Neuropsychiatric symptoms and caregivers' distress in anti-N-methyl-D-aspartate receptor encephalitis].

Zhonghua yi xue za zhi·2020

This study compared three neural networks for automatic mouse chromosome classification. The radial basis function network achieved the best classification error rate of 12.7%.

Area of Science:

  • Genetics
  • Bioinformatics
  • Computational Biology

Background:

  • Accurate classification of chromosomes is crucial for genetic research and disease diagnosis.
  • Automated methods can improve the efficiency and consistency of chromosome analysis.
  • Previous studies have explored various machine learning techniques for cytogenetic data.

Purpose of the Study:

  • To evaluate and compare the performance of different neural network architectures for the automatic classification of mouse chromosomes.
  • To determine the optimal neural network model and training strategy for accurate chromosome identification based on banding profiles.

Main Methods:

  • A dataset of 3723 mouse chromosomes was analyzed.
  • Chromosomes were represented as 30-point banding profiles.

Related Experiment Videos

  • Three neural network models were implemented and compared: radial basis function (RBF) network, multi-layer perceptron (MLP), and probabilistic neural network (PNN).
  • The fast orthogonal search (FOS) learning rule was used for training the RBF network.

    • Main Results:

    • The radial basis function network, trained with the fast orthogonal search learning rule, achieved the highest classification accuracy.
    • The best unconstrained classification error rate obtained was 12.7%.
    • This optimal performance was achieved using a training set of 2250 chromosomes.

    Conclusions:

    • The radial basis function neural network, particularly when trained with the fast orthogonal search learning rule, demonstrates superior performance for automatic mouse chromosome classification.
    • Automated chromosome classification using neural networks holds significant potential for advancing genetic research and diagnostic applications.