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

K-means clustering method for auditory evoked potentials selection.

B Gourevitch1, R Le Bouquin-Jeannes

  • 1Laboratoire Traitement du Signal et de l'Image, Université de Rennes 1, Rennes, France. boris.gourevitch@univ-rennes1.fr

Medical & Biological Engineering & Computing
|August 2, 2003
PubMed
Summary

This study introduces a k-means clustering method for automatically selecting important electrodes in surface auditory evoked potentials (SAEPs). The automated channel selection significantly reduces analysis time and avoids human variability.

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

Multisensory learning between odor and sound enhances beta oscillations.

Scientific reports·2019
Same author

Age-related Changes in Auditory Cortex Without Detectable Peripheral Alterations: A Multi-level Study in Sprague-Dawley Rats.

Neuroscience·2019
Same author

A Neural Substrate for Rapid Timbre Recognition? Neural and Behavioral Discrimination of Very Brief Acoustic Vowels.

Cerebral cortex (New York, N.Y. : 1991)·2015
Same author

Analysis of auditory evoked potential parameters in the presence of radiofrequency fields using a support vector machines method.

Medical & biological engineering & computing·2004
Same author

Seizures of temporal lobe epilepsy: identification of subtypes by coherence analysis using stereo-electro-encephalography.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·1999

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Surface auditory evoked potentials (SAEPs) are recorded using multi-electrode headsets, but signal quality varies across the scalp.
  • Accurate SAEP analysis, especially in radio-frequency (RF) fields, necessitates selecting electrodes with strong auditory activity.
  • Current manual visual selection of these channels is time-consuming and prone to human variability.

Purpose of the Study:

  • To develop and evaluate an automated method for selecting optimal electrode channels for SAEP analysis.
  • To compare the proposed automated method with traditional visual selection techniques.

Main Methods:

  • A k-means clustering algorithm was employed for the automatic selection of relevant electrode channels.
  • The performance of the k-means method was assessed against manual visual selection by multiple individuals.

Related Experiment Videos

Main Results:

  • The k-means clustering method achieved an 86.5% concordance rate with expert visual selection.
  • The automated selection resulted in a comparable final electrode set, with only two additional electrodes.
  • The automated channel selection process was approximately 100 times faster than manual selection.

Conclusions:

  • K-means clustering offers an efficient and reliable automated approach for selecting channels in SAEP recordings.
  • This method significantly reduces analysis time and eliminates inter-observer variability in channel selection.
  • The automated technique is particularly valuable for SAEP analysis in challenging environments like RF fields.