Analysing epileptic EEGs with a visibility graph algorithm

This paper analyzes the human epileptic electroencephalogram (EEG) based on a visibility graph algorithm. A single-channel EEG is mapped into a visibility graph (VG). Then its mean degree and degree distribution on the VG are extracted. It is shown that the mean degree on a VG from an epileptic subj...

Full description

Saved in:
Bibliographic Details
Published in:2012 5th International Conference on Biomedical Engineering and Informatics pp. 432 - 436
Main Authors: Zhu, Guohun, Li, Yan, Wen, Peng
Format: Conference Proceeding
Language:English
Published: IEEE 01.10.2012
Subjects:
Australia
Classification algorithms
degree distribtuion
EEG
Electroencephalography
Epilepsy
nonlinear discriminat analysis
Seizure
Systems biology
Time series analysis
visiblity graph
ISBN:9781467311830, 1467311839
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper analyzes the human epileptic electroencephalogram (EEG) based on a visibility graph algorithm. A single-channel EEG is mapped into a visibility graph (VG). Then its mean degree and degree distribution on the VG are extracted. It is shown that the mean degree on a VG from an epileptic subject is larger than that on a healthy subject based on the VG. The number of nodes having five degree on a VG from a healthy subject is significantly different from the number of nodes having the same degree on the VG from an epileptic subject. The mean degree and the number of nodes with five and eight degrees are used to discriminate the healthy EEGs, seizure EEGs and inter-ictal EEGs. Experimental results demonstrate that the visibility graph algorithm has a high classification accuracy to identify these three types of EEGs.
ISBN:9781467311830
1467311839
DOI:10.1109/BMEI.2012.6513212