Expert system approach to electroencephalogram signal processing

doi:10.1016/0950-7051(95)96213-B

Knowledge-Based Systems

Volume 8, Issue 4, August 1995, Pages 164-173

https://doi.org/10.1016/0950-7051(95)96213-B Get rights and content

Abstract

The human electroencephalogram (EEG) is often corrupted by ocular artefacts (OAs) caused by the movement of the eyes and/or the eyelids, making the recognition of abnormal EEG signals more difficult. The removal of OAs using conventional signal processing is complicated by the similarity between abnormal EEGs and OAs, which can lead to corruption of the EEG signal. The paper describes the development of a novel approach that uses expert system techniques to differentiate OAs from genuine EEG signals, enabling OA removal to be applied only where appropriate, and ensuring that clinically relevant EEG information is left unaffected.

References (12)

L.A. Zadeh
Fuzzy sets
Information & Control
(1965)
B.W. Jervis et al.
The removal of ocular artefacts from the electroencephalogram: a review
Med. & Biol. Eng. & Comput.
(1988)
E.C. Ifeachor et al.
Knowledge based enhancement of human EEG signals
E.C. Ifeachor et al.
A new microcomputer-based online ocular artefact removal (OAR) system
P.Y. Ktonas
Automated analysis of abnormal electroencephalograms
CRC Critical Reviews in Biomedical Engineering
(1983)
J.S. Muras et al.
The recognition of frontal slow activity in the presence of eye movements

There are more references available in the full text version of this article.

Cited by (8)

Automatic signal abnormality detection using time-frequency features and machine learning: A newborn EEG seizure case study
2016, Knowledge-Based Systems
Time-frequency (TF) based machine learning methodologies can improve the design of classification systems for non-stationary signals. Using selected TF distributions (TFDs), TF feature extraction is performed on multi-channel recordings using channel fusion and feature fusion approaches. Following the findings of previous studies, a TF feature set is defined to include three complementary categories: signal related features, statistical features and image features. Multi-class strategies are then used to improve the classification algorithm robustness to artifacts. The optimal subset of TF features is selected using the wrapper method with sequential forward feature selection (SFFS). In addition, a new proposed measure for TF feature selection is shown to improve the sensitivity of the classifier (while slightly reducing total accuracy and specificity). As an illustration, the TF approach is applied to the design of a system for detection of seizure activity in real newborn EEG signals. Experimental results indicate that: (1) The compact kernel distribution (CKD) outperforms other TFDs in classification accuracy; (2) a feature fusion strategy gives better classification than a channel fusion strategy; e.g. using all TF features, the CKD achieves a classification accuracy of 82% with feature fusion, which is 4% more than the channel fusion approach; (3) the SFFS wrapper feature selection method improves the classification performance for all TFDs; e.g. total accuracy is improved by 4.6%; (4) the multi-class strategy improves the seizure detection accuracy in the presence of artifacts; e.g. a total accuracy of 86.61% with one vs. one multi-class approach is achieved i.e. 0.91% more than the binary classification approach. The results obtained on a large practical real data set confirm the improved performance capability of TF features for knowledge based systems.
Biomedical Signal Processing and Artificial Intelligence in EOG Signals
2023, Advances in Non-Invasive Biomedical Signal Sensing and Processing with Machine Learning
Blind source separation techniques based eye blinks rejection in EEG signals
2014, Information Technology Journal
Estimation of sleep stages by an artificial neural network employing EEG, EMG and EOG
2010, Journal of Medical Systems
Removal of eye blink artifacts from EEG signals based on cross-correlation
2007, 2007 International Conference on Convergence Information Technology, ICCIT 2007
Online removal of ocular artefacts from the electroencephalogram
2004, IEE Proceedings: Science, Measurement and Technology

View all citing articles on Scopus

^b: M T Hellyar is also at Digital Signal Processing, Computing and Communication, Z-TEC Ltd, Devonia House, 85 North Hill, Plymouth, UK

View full text

Expert system approach to electroencephalogram signal processing

Abstract

Information & Control

The removal of ocular artefacts from the electroencephalogram: a review

Med. & Biol. Eng. & Comput.

Knowledge based enhancement of human EEG signals

A new microcomputer-based online ocular artefact removal (OAR) system

Automated analysis of abnormal electroencephalograms

CRC Critical Reviews in Biomedical Engineering

The recognition of frontal slow activity in the presence of eye movements