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

Multireference adaptive noise canceling applied to the EEG

C J James1, M T Hagan, R D Jones

  • 1Department of Electrical and Electronic Engineering, University of Canterbury, Christchurch, New Zealand.

IEEE Transactions on Bio-Medical Engineering
|August 1, 1997
PubMed
Summary

This study enhances electroencephalogram (EEG) signals using multireference adaptive noise canceling (MRANC) with an artificial neural network (ANN). The nonlinear ANN approach improved signal-to-noise ratio (SNR) more effectively than linear methods.

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

Improving quality of life in the elderly: hearing loss treatment with cochlear implants.

BMC geriatrics·2024
Same author

Reservoir computing using networks of memristors: effects of topology and heterogeneity.

Nanoscale·2023
Same author

Reservoir computing with 3D nanowire networks.

Neural networks : the official journal of the International Neural Network Society·2022
Same author

The French MBAA2 sentence recognition in noise test for cochlear implant users.

International journal of audiology·2022
Same author

Arthropathy in hereditary haemochromatosis segregates with elevated erythrocyte mean corpuscular volume.

Scandinavian journal of rheumatology·2020
Same author

Wavefront prediction with reservoir computing for minimizing the effects of angular anisoplanatism.

Applied optics·2018

Area of Science:

  • Neuroscience
  • Signal Processing
  • Artificial Intelligence

Background:

  • Transient nonstationarities in electroencephalogram (EEG) signals present challenges for accurate analysis.
  • Adaptive noise canceling (ANC) techniques are employed to improve signal quality.
  • Multireference adaptive noise canceling (MRANC) offers spatial filtering capabilities.

Purpose of the Study:

  • To enhance transient nonstationarities in EEG signals using MRANC.
  • To implement MRANC adaptation with a multilayer-perception artificial neural network (ANN).
  • To compare the performance of a nonlinear ANN-based MRANC with a linear MRANC implementation and other filtering techniques.

Main Methods:

  • Application of multireference adaptive noise canceling (MRANC) to recorded EEG segments.

Related Experiment Videos

  • Implementation of MRANC adaptation using a multilayer-perception artificial neural network (ANN).
  • Comparison of MRANC performance against inverse auto-regressive filtering.

    • Main Results:

    • The ANN-based (nonlinear) MRANC demonstrated improved performance, specifically a higher signal-to-noise ratio (SNR) for nonstationarities, compared to linear MRANC.
    • Both linear and nonlinear MRANC implementations resulted in an improved SNR.
    • MRANC's spatial filtering advantage was evident when compared to purely temporal inverse auto-regressive filtering.

    Conclusions:

    • Artificial neural network-based MRANC provides a superior method for enhancing transient nonstationarities in EEG signals compared to linear approaches.
    • MRANC, particularly with its nonlinear ANN implementation, offers significant improvements in EEG signal quality.
    • The spatial filtering capability of MRANC is a key advantage for EEG signal processing.