Jove
Visualize
Contact Us

Related Experiment Videos

Automatic classification of electroencephalograms: Kullback-Leibler nearest neighbor rules.

W Gersch, F Martinelli, J Yonemoto

    Science (New York, N.Y.)
    |July 13, 1979
    PubMed
    Summary

    The Kullback-Leibler nearest neighbor rule accurately classifies electroencephalogram (EEG) states using minimal data. This method reliably estimates minimal electroencephalogram misclassification probability for anesthesia monitoring.

    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

    Methodological and reporting standards for quality-of-life data eligible for European Society for Medical Oncology-Magnitude of Clinical Benefit Scale (ESMO-MCBS) credit.

    Annals of oncology : official journal of the European Society for Medical Oncology·2022
    Same author

    Response to treatment and prognostic significance of supradiaphragmatic disease in patients with high-grade serous ovarian cancer.

    European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2022
    Same author

    Reducing energy demand by the combined application of advanced control strategies in a full scale WWTP.

    Water science and technology : a journal of the International Association on Water Pollution Research·2021
    Same author

    Using rADioMIcs and machine learning with ultrasonography for the differential diagnosis of myometRiAL tumors (the ADMIRAL pilot study). Radiomics and differential diagnosis of myometrial tumors.

    Gynecologic oncology·2021
    Same author

    The size, shape, density and ring of the dwarf planet Haumea from a stellar occultation.

    Nature·2017
    Same author

    Sentinel Node Mapping in Endometrial Cancer By Using Hysteroscopic Injection of Indocyanine Green and Laparoscopic Near-Infrared Fluorescence Imaging: A Preliminary Experience.

    Journal of minimally invasive gynecology·2016
    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

    Area of Science:

    • Computational neuroscience
    • Machine learning in medicine
    • Signal processing

    Background:

    • Automatic classification of electroencephalogram (EEG) time series is crucial for medical diagnostics.
    • Accurate anesthesia monitoring requires reliable classification of EEG states.

    Purpose of the Study:

    • To apply the Kullback-Leibler nearest neighbor rule for classifying electroencephalogram (EEG) time series.
    • To estimate the minimal probability of EEG misclassification in automatic classification tasks.

    Main Methods:

    • Utilized the Kullback-Leibler nearest neighbor rule for classification.
    • Employed machine computation on electroencephalogram (EEG) data alone.
    • Focused on classifying anesthesia levels L1 (insufficient) and L3 (sufficient for deep surgery).

    Related Experiment Videos

    Main Results:

    • The Kullback-Leibler nearest neighbor approach provides a statistically reliable estimate of minimal electroencephalogram misclassification probability.
    • Achieved automatic classification of anesthesia levels using only EEG signals.
    • Demonstrated effectiveness with a relatively small number of labeled EEG samples.

    Conclusions:

    • The Kullback-Leibler nearest neighbor rule is effective for the automatic classification of electroencephalogram (EEG) time series.
    • This method offers a reliable approach to estimating minimal misclassification rates in EEG analysis.
    • Machine computation on EEG data alone can accurately classify anesthesia levels.