Automated identification of epileptic and alcoholic EEG signals using recurrence quantification analysis

Ee Ping Ng, Teik Cheng Lim, Subhagata Chattopadhyay, Muralidhar Bairy

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Epilepsy is a common neurological disorder characterized by recurrence seizures. Alcoholism causes organic changes in the brain, resulting in seizure attacks similar to epileptic fits. Hence, it is challenging to differentiate the cause of fits as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically differentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is difficult to tell the subtle changes in these signals with the help of linear techniques or by the naked eye. Therefore, to analyze the normal (control), epileptic, and alcoholic EEG signals, two non-linear methods, such as recurrence plots (RPs) and then recurrence quantification analysis (RQA) are adopted. Approximately 10 RQA parameters have been used to classify the EEG signals into three distinct classes, i.e., normal, epileptic, and alcoholic. Six classifiers, such as support vector machine (SVM), radial basis probabilistic neural network (RBPNN), decision tree (DT), Gaussian mixture model (GMM), k-nearest neighbor (kNN), and fuzzy Sugeno classifiers have been developed to accomplish this task. Results show that the GMM classifier outperformed the other classifiers with a classification sensitivity of 99.6%, specificity of 98.3%, and accuracy of 98.6%.

Original languageEnglish
Article number1240028
JournalJournal of Mechanics in Medicine and Biology
Volume12
Issue number5
DOIs
Publication statusPublished - 01-12-2012

Fingerprint

Electroencephalography
Classifiers
Neurology
Decision trees
Support vector machines
Brain
Neural networks

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{d060b244b4814103ae9b1d98b2a70c21,
title = "Automated identification of epileptic and alcoholic EEG signals using recurrence quantification analysis",
abstract = "Epilepsy is a common neurological disorder characterized by recurrence seizures. Alcoholism causes organic changes in the brain, resulting in seizure attacks similar to epileptic fits. Hence, it is challenging to differentiate the cause of fits as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically differentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is difficult to tell the subtle changes in these signals with the help of linear techniques or by the naked eye. Therefore, to analyze the normal (control), epileptic, and alcoholic EEG signals, two non-linear methods, such as recurrence plots (RPs) and then recurrence quantification analysis (RQA) are adopted. Approximately 10 RQA parameters have been used to classify the EEG signals into three distinct classes, i.e., normal, epileptic, and alcoholic. Six classifiers, such as support vector machine (SVM), radial basis probabilistic neural network (RBPNN), decision tree (DT), Gaussian mixture model (GMM), k-nearest neighbor (kNN), and fuzzy Sugeno classifiers have been developed to accomplish this task. Results show that the GMM classifier outperformed the other classifiers with a classification sensitivity of 99.6{\%}, specificity of 98.3{\%}, and accuracy of 98.6{\%}.",
author = "Ng, {Ee Ping} and Lim, {Teik Cheng} and Subhagata Chattopadhyay and Muralidhar Bairy",
year = "2012",
month = "12",
day = "1",
doi = "10.1142/S0219519412400283",
language = "English",
volume = "12",
journal = "Journal of Mechanics in Medicine and Biology",
issn = "0219-5194",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "5",

}

Automated identification of epileptic and alcoholic EEG signals using recurrence quantification analysis. / Ng, Ee Ping; Lim, Teik Cheng; Chattopadhyay, Subhagata; Bairy, Muralidhar.

In: Journal of Mechanics in Medicine and Biology, Vol. 12, No. 5, 1240028, 01.12.2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated identification of epileptic and alcoholic EEG signals using recurrence quantification analysis

AU - Ng, Ee Ping

AU - Lim, Teik Cheng

AU - Chattopadhyay, Subhagata

AU - Bairy, Muralidhar

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Epilepsy is a common neurological disorder characterized by recurrence seizures. Alcoholism causes organic changes in the brain, resulting in seizure attacks similar to epileptic fits. Hence, it is challenging to differentiate the cause of fits as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically differentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is difficult to tell the subtle changes in these signals with the help of linear techniques or by the naked eye. Therefore, to analyze the normal (control), epileptic, and alcoholic EEG signals, two non-linear methods, such as recurrence plots (RPs) and then recurrence quantification analysis (RQA) are adopted. Approximately 10 RQA parameters have been used to classify the EEG signals into three distinct classes, i.e., normal, epileptic, and alcoholic. Six classifiers, such as support vector machine (SVM), radial basis probabilistic neural network (RBPNN), decision tree (DT), Gaussian mixture model (GMM), k-nearest neighbor (kNN), and fuzzy Sugeno classifiers have been developed to accomplish this task. Results show that the GMM classifier outperformed the other classifiers with a classification sensitivity of 99.6%, specificity of 98.3%, and accuracy of 98.6%.

AB - Epilepsy is a common neurological disorder characterized by recurrence seizures. Alcoholism causes organic changes in the brain, resulting in seizure attacks similar to epileptic fits. Hence, it is challenging to differentiate the cause of fits as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically differentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is difficult to tell the subtle changes in these signals with the help of linear techniques or by the naked eye. Therefore, to analyze the normal (control), epileptic, and alcoholic EEG signals, two non-linear methods, such as recurrence plots (RPs) and then recurrence quantification analysis (RQA) are adopted. Approximately 10 RQA parameters have been used to classify the EEG signals into three distinct classes, i.e., normal, epileptic, and alcoholic. Six classifiers, such as support vector machine (SVM), radial basis probabilistic neural network (RBPNN), decision tree (DT), Gaussian mixture model (GMM), k-nearest neighbor (kNN), and fuzzy Sugeno classifiers have been developed to accomplish this task. Results show that the GMM classifier outperformed the other classifiers with a classification sensitivity of 99.6%, specificity of 98.3%, and accuracy of 98.6%.

UR - http://www.scopus.com/inward/record.url?scp=84871584511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871584511&partnerID=8YFLogxK

U2 - 10.1142/S0219519412400283

DO - 10.1142/S0219519412400283

M3 - Article

VL - 12

JO - Journal of Mechanics in Medicine and Biology

JF - Journal of Mechanics in Medicine and Biology

SN - 0219-5194

IS - 5

M1 - 1240028

ER -