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

Integrating support vector machines and neural networks.

Rosario Capparuccia1, Renato De Leone, Emilia Marchitto

  • 1Sigma S.p.A. Via Po, 14, 63010 Altidona (AP), Italy.

Neural Networks : the Official Journal of the International Neural Network Society
|February 20, 2007
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

Approximate Synchronization in Distribution of Coupled Probabilistic Boolean Networks.

IEEE transactions on cybernetics·2026
Same author

Stability of large-scale probabilistic Boolean networks via network aggregation.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Six-Month Synbio<sup>®</sup> Administration Affects Nutritional and Inflammatory Parameters of Older Adults Included in the PROBIOSENIOR Project.

Microorganisms·2023
Same author

A Bayesian Network Approach to Explainable Reinforcement Learning with Distal Information.

Sensors (Basel, Switzerland)·2023
Same author

Joint selection of brain network nodes and edges for MCI identification.

Computer methods and programs in biomedicine·2022
Same author

Impact of a probiotic diet on well-being of healthy senior: THE PROBIOSENIOR PROJECT.

Journal of applied microbiology·2022

This study integrates support vector machines (SVMs) and artificial neural networks for object classification. The combined approach accurately determines tile quality using optical data and feature selection.

Area of Science:

  • Machine Learning
  • Computer Vision
  • Materials Science

Background:

  • Support Vector Machines (SVMs) are advanced algorithms for classification and regression.
  • Artificial Neural Networks (ANNs) are widely used for complex pattern recognition tasks.
  • Accurate quality assessment of manufactured goods like tiles is crucial for industrial applications.

Purpose of the Study:

  • To integrate Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) for enhanced object classification.
  • To apply this integrated technique to the specific problem of tile quality determination.
  • To optimize the classification process by identifying a relevant subset of extracted features.

Main Methods:

  • Utilizing an optical reader system for automatic feature extraction from tiles.

Related Experiment Videos

  • Implementing a hybrid model combining SVMs and ANNs for classification.
  • Employing a feature selection process to identify the most informative subset of features.
  • Classifying tiles based on the selected feature subset.

    • Main Results:

    • Successful classification of tile quality using the integrated SVM and ANN model.
    • Demonstration of the effectiveness of the hybrid approach in an industrial context.
    • Identification of a reduced feature subset that maintains high classification accuracy.

    Conclusions:

    • The integration of SVMs and ANNs provides a powerful and effective method for object classification.
    • This hybrid technique is well-suited for automated quality control in manufacturing, specifically for tiles.
    • Feature selection is a critical step in optimizing the performance and efficiency of the classification system.