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

Automatic recognition of alertness level by using wavelet transform and artificial neural network.

M Kemal Kiymik1, Mehmet Akin, Abdulhamit Subasi

  • 1Department of Electrical and Electronics Engineering, Kahramanmaras Sutcu Imam University, Kahramanmara 46100, Turkey.

Journal of Neuroscience Methods
|October 19, 2004
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

Does the type of rapid maxillary expansion appliance affect root resorption? A retrospective CBCT study.

BMC oral health·2026
Same author

Electromyography Signal Classification With Artificial Intelligence for Detection of Neuromuscular Disorders Using a Large Clinically-Acquired Database.

Muscle & nerve·2025
Same author

A Comparison of the Effectiveness of Combined Primer and Adhesive Systems in Orthodontic Bonding: An In Vitro Study.

Journal of clinical medicine·2025
Same author

Identifying Risk Factors of Substance Use in Finland: A Machine Learning Approach.

Substance use & misuse·2025
Same author

A Novel NICU Sleep State Stratification: Multiperspective Features, Adaptive Feature Selection and Ensemble Model.

IEEE transactions on bio-medical engineering·2025
Same author

Multidomain Selective Feature Fusion and Stacking Based Ensemble Framework for EEG-Based Neonatal Sleep Stratification.

IEEE journal of biomedical and health informatics·2025

This study introduces an artificial neural network (ANN) for automatic alertness recognition using electroencephalogram (EEG) data. The novel method accurately distinguishes between alert, drowsy, and sleep states from EEG recordings.

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Monitoring alertness is crucial for safety and performance.
  • Current methods for assessing alertness can be subjective or invasive.
  • Electroencephalogram (EEG) offers objective physiological measures of brain activity.

Purpose of the Study:

  • To develop and validate a novel method for automatic recognition of alertness levels from full-spectrum EEG recordings.
  • To assess the efficacy of an artificial neural network (ANN) in classifying alertness states.
  • To determine the applicability of the developed algorithm for distinguishing between alert, drowsy, and sleep states.

Main Methods:

  • Utilized power spectral density (PSD) derived from discrete wavelet transform (DWT) of full-spectrum EEG signals as input features.

Related Experiment Videos

  • Employed an error backpropagation artificial neural network (ANN) with three discrete outputs: alert, drowsy, and sleep.
  • Trained and tested the ANN using EEG data from 30 healthy subjects, with validation on a separate set of 12 subjects.

    • Main Results:

    • The ANN achieved high classification accuracy: 96% for alert, 95% for drowsy, and 94% for sleep states.
    • Performance was validated on EEG recordings not previously used for training, demonstrating robust generalization.
    • The algorithm showed significant potential for practical application in alertness monitoring.

    Conclusions:

    • The proposed automatic recognition algorithm effectively distinguishes between alert, drowsy, and sleep states using EEG data.
    • The ANN-based approach offers a reliable and accurate method for objective alertness assessment.
    • This technology has potential applications in various fields requiring continuous monitoring of cognitive states.