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

MART: a multichannel ART-based neural network.

M Fernández-Delgado1, S Barro Ameneiro

  • 1Department of Electronics and Computing, University of Santiago de Compostela, 15706 Santiago de Compostela, Spain.

IEEE Transactions on Neural Networks
|February 7, 2008
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

Cognitive and clinical predictors of a long-term course in obsessive compulsive disorder: A machine learning approach in a prospective cohort study.

Journal of affective disorders·2024
Same author

Anaphylactic Shock due to Isatuximab and Successful Desensitization.

Journal of investigational allergology & clinical immunology·2023
Same author

Virulence properties and antimicrobial resistance of Pseudomonas aeruginosa isolated from cave waters at Roraima Tepui, Guayana Highlands.

Letters in applied microbiology·2020
Same author

An extensive experimental survey of regression methods.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

A new approach for TU complex characterization.

IEEE transactions on bio-medical engineering·2000
Same author

Intelligent telemonitoring of critical-care patients.

IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society·1999
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces MART, an adaptive neural network for classifying multichannel signals without prior learning. It effectively handles noisy data by considering individual channel reliability, reducing classification errors.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Adaptive Resonance Theory (ART) classifiers are useful when the number of pattern categories is unknown.
  • Existing ART classifiers struggle with noisy signals and lack multichannel orientation.
  • Accurate classification of multichannel signals is crucial in various applications, including biomedical engineering.

Purpose of the Study:

  • To introduce MART, a novel ART-based neural network designed for adaptive classification of multichannel signal patterns.
  • To address the limitations of existing ART classifiers in handling noisy multichannel data.
  • To develop a method that quantifies and utilizes individual channel reliability for improved pattern classification.

Main Methods:

  • Developed MART, an ART-based neural network with a multichannel orientation.

Related Experiment Videos

  • Implemented a mechanism within MART to quantify and incorporate the reliability of individual signal channels during classification.
  • Evaluated MART's performance on classifying QRS complexes in two-channel ECG signals from the MIT-BIH database, including noisy samples.

    • Main Results:

    • MART demonstrates effective adaptive classification of multichannel signal patterns without requiring prior supervised learning.
    • The network's ability to account for varying channel reliability significantly reduces the creation of spurious or duplicate categories in noisy signals.
    • Successful classification of QRS complexes in noisy two-channel ECG traces was achieved, showcasing MART's practical utility.

    Conclusions:

    • MART offers a robust solution for adaptive multichannel signal classification, particularly in scenarios with unknown category numbers and noisy data.
    • The novel approach of incorporating individual channel reliability enhances classification accuracy and reduces errors compared to traditional ART methods.
    • MART shows promise for applications requiring reliable signal pattern recognition, such as in the analysis of electrocardiogram (ECG) data.