Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines

被引：383

作者：

Nicolaou, Nicoletta ^{[1
]}

Georgiou, Julius

机构：

[1] Univ Cyprus, Dept Elect & Comp Engn, KIOS Res Ctr, CY-1678 Nicosia, Cyprus

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2012年 / 39卷 / 01期

关键词：

Electroencephalogram (EEG); Permutation Entropy (PE); Support Vector Machine (SVM); Epilepsy; Seizure; ARTIFICIAL NEURAL-NETWORK; SEIZURE DETECTION; SCALP EEG;

D O I：

10.1016/j.eswa.2011.07.008

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The electroencephalogram (EEG) has proven a valuable tool in the study and detection of epilepsy. This paper investigates for the first time the use of Permutation Entropy (PE) as a feature for automated epileptic seizure detection. A Support Vector Machine (SVM) is used to classify segments of normal and epileptic EEG based on PE values. The proposed system utilizes the fact that the EEG during epileptic seizures is characterized by lower PE than normal EEG. It is shown that average sensitivity of 94.38% and average specificity of 93.23% is obtained by using PE as a feature to characterize epileptic and seizure-free EEG, while 100% sensitivity and specificity were also obtained in single-trial classifications. (C) 2011 Elsevier Ltd. All rights reserved.

引用

页码：202 / 209

页数：8

共 35 条

[1] Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state [J].

Andrzejak, RG ;

Lehnertz, K ;

Mormann, F ;

Rieke, C ;

David, P ;

Elger, CE .

PHYSICAL REVIEW E, 2001, 64 (06) :8-061907

[2] Permutation entropy: A natural complexity measure for time series [J].

Bandt, C ;

Pompe, B .

PHYSICAL REVIEW LETTERS, 2002, 88 (17) :4

[3] Permutation entropy to detect vigilance changes and preictal states from scalp EEG in epileptic patients. A preliminary study [J].

Bruzzo, Angela A. ;

Gesierich, Benno ;

Santi, Maurizio ;

Tassinari, Carlo Alberto ;

Birbaumer, Niels ;

Rubboli, Guido .

NEUROLOGICAL SCIENCES, 2008, 29 (01) :3-9

[4] A tutorial on Support Vector Machines for pattern recognition [J].

Burges, CJC .

DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) :121-167

[5]

Cao YH, 2004, PHYS REV E, V70, DOI 10.1103/PhysRevE.70.046217

[6] Adult epilepsy [J].

Duncan, JS ;

Sander, JW ;

Sisodiya, SM ;

Walker, MC .

LANCET, 2006, 367 (9516) :1087-1100

[7]

Gabor AJ, 1996, ELECTROEN CLIN NEURO, V99, P257, DOI 10.1016/0013-4694(96)96001-0

[8] Recurrent neural networks employing Lyapunov exponents for EEG signals classification [J].

Güler, NF ;

Übeyli, ED ;

Güler, I .

EXPERT SYSTEMS WITH APPLICATIONS, 2005, 29 (03) :506-514

[9] Entropies for detection of epilepsy in EEG [J].

Kannathal, N ;

Choo, ML ;

Acharya, UR ;

Sadasivan, PK .

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2005, 80 (03) :187-194

[10] Neural networks with periodogram and autoregressive spectral analysis methods in detection of epileptic seizure [J].

Kiymik M.K. ;

Subasi A. ;

Ozcalik H.R. .

Journal of Medical Systems, 2004, 28 (6) :511-522

← 1 2 3 4 →