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

Human chromosome classification using multilayer perceptron neural network

B Lerner1, H Guterman, I Dinstein

  • 1Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel.

International Journal of Neural Systems
|September 1, 1995
PubMed
Summary
This summary is machine-generated.

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

Automatic feedback control by image processing for mixing solutions in a microfluidic device.

Biomicrofluidics·2022
Same author

Effectiveness of a Cognitive Behavioral Randomized Controlled Trial for People Living with HIV Who are Heavy Drinkers: The Holistic Health Recovery Program (HHRP) Trial in Miami.

Journal of clinical psychology in medical settings·2022
Same author

The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism.

Molecular psychiatry·2013
Same author

Nurses' attitudes towards breastfeeding among women with schizophrenia in southern Israel.

Journal of psychiatric and mental health nursing·2011
Same author

Handling memory overflow in connected component labeling applications.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Projection-based geometrical feature extraction for computer vision: algorithms in pipeline architectures.

IEEE transactions on pattern analysis and machine intelligence·2011
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A multilayer perceptron (MLP) neural network effectively classifies human chromosomes using minimal data. Principal component analysis (PCA) aids network initialization and feature reduction, outperforming traditional classifiers.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning in genetics

Background:

  • Accurate human chromosome classification is crucial for genetic research and diagnostics.
  • Traditional classification methods can be data-intensive and sensitive to feature ratios.

Purpose of the Study:

  • To evaluate the efficacy of a multilayer perceptron (MLP) neural network for human chromosome classification.
  • To investigate the role of principal component analysis (PCA) in optimizing MLP performance for this task.

Main Methods:

  • Utilized a multilayer perceptron (MLP) neural network for chromosome classification.
  • Employed principal component analysis (PCA) for network initialization and feature reduction.
  • Compared MLP performance against a Bayes piecewise classifier.

Related Experiment Videos

Main Results:

  • MLP achieved high performance with as few as 10-20 examples for classifying 5 chromosome types.
  • The entropic error showed an empirical dependence on the number of examples comparable to the 1/t function.
  • PCA highlighted the importance of retaining image information with small training sets.
  • MLP consistently outperformed the Bayes piecewise classifier across all tested scenarios.
  • MLP demonstrated robustness to the training vector-to-feature ratio, unlike the piecewise classifier.

Conclusions:

  • MLP neural networks offer an efficient and robust solution for human chromosome classification, even with limited datasets.
  • PCA is a valuable tool for enhancing MLP performance in chromosome classification by optimizing feature representation.
  • MLP classifiers present a significant advantage over traditional methods due to their data efficiency and insensitivity to feature dimensionality.