Analysing epileptic EEGs with a visibility graph algorithm
- 1 October 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 432-436
Abstract
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.Keywords
This publication has 16 references indexed in Scilit:
- Clustering technique-based least square support vector machine for EEG signal classificationComputer Methods and Programs in Biomedicine, 2011
- Classification of electroencephalogram signals with combined time and frequency featuresExpert Systems with Applications, 2011
- EEG signal classification using PCA, ICA, LDA and support vector machinesExpert Systems with Applications, 2010
- Comment on “Network analysis of human heartbeat dynamics” [Appl. Phys. Lett. 96, 073703 (2010)]Applied Physics Letters, 2010
- Network analysis of human heartbeat dynamicsApplied Physics Letters, 2010
- Complex brain networks: graph theoretical analysis of structural and functional systemsNature Reviews Neuroscience, 2009
- The application of graph theoretical analysis to complex networks in the brainClinical Neurophysiology, 2007
- Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transformApplied Mathematics and Computation, 2007
- Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain statePhysical Review E, 2001
- Real‐Time Automated Detection and Quantitative Analysis of Seizures and Short‐Term Prediction of Clinical OnsetEpilepsia, 1998