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

An artificial neural network approach to ERP classification

L Gupta1, D L Molfese, R Tammana

  • 1Department of Electrical Engineering, Southern Illinois University at Carbondale, USA.

Brain and Cognition
|April 1, 1995
PubMed
Summary

Artificial neural networks accurately classify event-related potential (ERP) waveforms for match/no-match decisions. This study demonstrates the effectiveness of neural networks in analyzing complex brain signal data.

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

Healthcare utilization and unmet needs of patients with antisynthetase syndrome: An international patient survey.

Rheumatology international·2023
Same author

Abnormal Blood Oxygen Level-Dependent Fluctuations in Focal Cortical Dysplasia and the Perilesional Zone: Initial Findings.

AJNR. American journal of neuroradiology·2018
Same author

Comparative efficacy of four treatment regimens in Type 2 Leprosy Reactions (Prednisolone alone, Thalidomide alone, Prednisolone plus Thalidomide and Prednisolone plus Clofazimine).

Indian journal of leprosy·2018
Same author

Seven cases of probable endotoxin poisoning related to contaminated glutathione infusions.

Epidemiology and infection·2018
Same author

Primary Aortoenteric fistula : An alarming entity warranting early diagnosis.

Tropical gastroenterology : official journal of the Digestive Diseases Foundation·2018
Same author

Ketogenic diet in endocrine disorders: Current perspectives.

Journal of postgraduate medicine·2017

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Signal Processing

Background:

  • Event-related potentials (ERPs) are crucial for understanding cognitive processes.
  • Classifying ERP waveforms traditionally presents analytical challenges.
  • Artificial neural networks offer a promising approach for complex signal analysis.

Purpose of the Study:

  • To develop and evaluate artificial neural network (ANN) models for classifying event-related potential (ERP) waveforms.
  • To differentiate between 'match' and 'no-match' decisions based on scalp-recorded ERPs.
  • To compare global and local ANN classification strategies.

Main Methods:

  • Utilized scalp-recorded ERPs from six electrode sites during an auditory/visual object recognition task.
  • Implemented a three-layer backpropagation neural network.

Related Experiment Videos

  • Developed two classification approaches: a global model averaging ERPs across sites and a local model using individual site data.
  • Trained and tested networks on a small dataset of eight match and eight no-match ERP responses.

    • Main Results:

    • ANN-based classifiers demonstrated high accuracy in discriminating between match and no-match ERP conditions.
    • Both global and local classification approaches showed effectiveness.
    • The study confirmed the capability of neural networks to analyze and classify ERP data.

    Conclusions:

    • Artificial neural networks are effective tools for classifying ERP waveforms.
    • The developed models can accurately distinguish cognitive states related to match/no-match decisions.
    • This approach holds potential for advancing brain-computer interfaces and cognitive neuroscience research.