Auto mutual information analysis with order patterns for epileptic EEG

Authors:
Gaoxiang Ouyang;Yao Wang;Xiaoli Li
Affiliations:
Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China;Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China;Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Year:
2009

Citing 3
Cited 0

Coarse-grained entropy rates for characterization of complex time series

Physica D
Application of wavelet-based similarity analysis to epileptic seizures prediction

Computers in Biology and Medicine
Entropies for detection of epilepsy in EEG

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this study, we investigated auto mutual information (AMI), based on order patterns analysis, as a tool to evaluate the dynamical characteristics of electroencephalogram (EEG) during interictal, preictal and ictal phase, respectively. Permutation entropy quantifies regularity in time series, while AMI detects the mutual information (MI) between a time series and a delayed version of itself. The results show that AMI method was able to reveal that the highest entropy values were assigned to interictal EEG recordings and the lowest entropy values were assigned to ictal EEG recordings. The classification ability of the AMI measures is tested using ANFIS classifier. Test results confirm that AMI method has potential in classifying the epileptic EEG signals.