Related Experiment Video
Updated: Jan 6, 2026
10:41
Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content
Published on: May 26, 2018
7.2K
Automatic eye blink artifact removal for EEG based on a sparse coding technique for assessing major mental disorders.
Raheel Zafar1, Abdul Qayyum2, Wajid Mumtaz2
1Department of Engineering, National University of Modern Languages, Islamabad 44000, Pakistan.
Journal of Integrative Neuroscience
|October 12, 2019
Summary
This study introduces an automatic method using sparse coding to detect and correct eye blink artifacts in electroencephalogram (EEG) data. The novel technique achieves 89.6% accuracy, outperforming existing classifiers for cleaner EEG signal analysis.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Signal Processing
Background:
- Electroencephalogram (EEG) data frequently contains artifacts, particularly from eye blinks, which can confound analysis.
- Existing methods for artifact detection and removal vary, with a need for more accurate automatic solutions.
Purpose of the Study:
- To propose and validate an automatic method for detecting and correcting eye blink artifacts in EEG data using sparse coding.
- To evaluate the performance of the proposed method against established classifiers.
Main Methods:
- Utilized sparse coding with a hybrid dictionary based on ridgelet transformation for feature extraction.
- Analyzed independent components from multi-channel EEG datasets.
- Tested the method on five diverse EEG datasets for artifact detection and correction.
Main Results:
- The proposed method successfully identified the precise locations of eye blink artifacts.
- Achieved an automatic detection accuracy of 89.6%.
- Demonstrated superior performance compared to an extreme learning machine classifier.
Conclusions:
- The developed sparse coding technique offers a promising approach for accurate automatic eye blink artifact detection and correction in EEG.
- This method provides a more precise estimation of artifact locations than current machine learning classifiers.
