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

Hybrid systems: a promising solution for better decision support tools

B D Leão1, E B Reátegui, A Guazzelli

  • 1Institute of Cardiology RS, Porto Alegre RS, Brazil.

Medinfo. MEDINFO
|January 1, 1995
PubMed
Summary

HYCONES II enables building hybrid expert systems by integrating frames and neural networks for classification tasks. This tool compares three neural network models, including the novel Semantic ART (SMART), for medical diagnostics.

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

Using narrative reports to support a digital library.

Proceedings. AMIA Symposium·2002
Same author

Competitive Hebbian learning and the hippocampal place cell system: modeling the interaction of visual and path integration cues.

Hippocampus·2002
Same author

Dissociation of the effects of bilateral lesions of the dorsal hippocampus and parietal cortex on path integration in the rat.

Behavioral neuroscience·2002
Same author

Building a knowledge base to support a digital library.

Studies in health technology and informatics·2001
Same author

Accessing heterogeneous sources of evidence to answer clinical questions.

Journal of biomedical informatics·2001
Same author

An evaluation of patient access to their electronic medical records via the World Wide Web.

Proceedings. AMIA Symposium·2000

Area of Science:

  • Artificial Intelligence
  • Computational Intelligence
  • Expert Systems

Background:

  • Expert systems and neural networks are powerful tools for classification.
  • Integrating symbolic (frames) and sub-symbolic (neural networks) knowledge offers synergistic advantages.
  • Developing hybrid systems requires robust frameworks for knowledge representation and processing.

Purpose of the Study:

  • To introduce HYCONES II, a tool for constructing tightly coupled Hybrid Connectionist Expert Systems (HCES).
  • To integrate frame-based knowledge representation with diverse neural network models.
  • To evaluate the performance of different neural network architectures in classification tasks, particularly in medical diagnostics.

Main Methods:

  • HYCONES II utilizes a hybrid knowledge base integrating frames with neural networks.

Related Experiment Videos

  • Three neural network models are available: CNM, Fuzzy ARTMAP, and the novel Semantic ART (SMART).
  • Model performance is validated through comparative analysis in two medical diagnostic domains.

    • Main Results:

    • The study validates the performance of CNM, Fuzzy ARTMAP, and SMART in medical diagnostic classification.
    • SMART, a novel model combining previous architectures, is presented and evaluated.
    • Comparative analysis highlights the effectiveness of the integrated approach for classification problems.

    Conclusions:

    • HYCONES II provides a framework for building effective HCES for classification.
    • The integration of frames and neural networks, including novel models like SMART, shows promise for complex problem-solving.
    • Further development of HYCONES II aims to enhance its capabilities for advanced AI applications.