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

Visual classification of medical data using MLP mapping

E Cağatay Güler1, B Sankur, Y P Kahya

  • 1Biomedical Engineering Institute, Boğaziçi University, Istanbul, Turkey.

Computers in Biology and Medicine
|October 24, 1998
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

Computerized diagnosis of respiratory disorders. SVM based classification of VAR model parameters of respiratory sounds.

Methods of information in medicine·2014
Same author

On dimensionality, sample size, classification error, and complexity of classification algorithm in pattern recognition.

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

VQ-adaptive block transform coding of images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

k-nearest neighbors directed noise injection in multilayer perceptron training.

IEEE transactions on neural networks·2008
Same author

A review of image watermarking applications in healthcare.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same author

A multi-channel device for respiratory sound data acquisition and transient detection.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same journal

sEEGnal: an automated EEG preprocessing pipeline evaluated against expert-driven preprocessing.

Computers in biology and medicine·2026
Same journal

Corrigendum to "Integrating experimental biology, computational methods, and artificial Intelligence in anticancer drug discovery: Bridging the translational Gap" [Comput. Biol. Med. 213 (2026) 111832].

Computers in biology and medicine·2026
Same journal

Organ dose optimization for a point-of-care forearm X-ray photon-counting CT.

Computers in biology and medicine·2026
Same journal

Physics-guided transformation of breathomic feature spaces into disease-specific representations for respiratory disease classification.

Computers in biology and medicine·2026
Same journal

An AI-driven deep learning pipeline for taxonomic classification and biodiversity assessment of deep-sea environmental DNA.

Computers in biology and medicine·2026
Same journal

Rapid personalisation of cardiovascular models using invasively measured right ventricular pressure.

Computers in biology and medicine·2026
See all related articles

This study introduces a new non-linear mapping method for visual classification using multilayer perceptrons (MLP). The method visually maps class membership to target values in a 2D feature space for improved accuracy.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional visual classification methods often struggle with complex, non-linear data patterns.
  • Multilayer perceptrons (MLP) are powerful tools for non-linear function approximation but require effective training strategies.

Purpose of the Study:

  • To design and present a novel non-linear mapping method for visual classification.
  • To leverage multilayer perceptrons (MLP) with assigned class target values for enhanced classification accuracy.
  • To interpret class membership visually as proximity to target values in a 2D feature space.

Main Methods:

  • A novel non-linear mapping technique is proposed for visual classification tasks.
  • The method utilizes multilayer perceptrons (MLP) trained with specific class target values.

Related Experiment Videos

  • Class membership is represented by the proximity of data points to assigned 2D target values in a feature space.
  • Network weights are optimized to map training data features to their corresponding 2D target values.

    • Main Results:

    • The proposed MLP-based method effectively learns a non-linear mapping for visual classification.
    • Training data points are successfully mapped to their designated 2D target values, reflecting class membership.
    • The approach demonstrates a visually interpretable way to represent class distinctions in a feature space.

    Conclusions:

    • The developed non-linear mapping method offers a promising approach for visual classification using MLPs.
    • Interpreting class membership through proximity to 2D target values enhances the understanding of classification boundaries.
    • This technique provides a robust framework for improving the performance and interpretability of MLP-based classifiers.