Automated Identification of Epileptic and Alcoholic EEG Signals using Recurrence Quantification Analysis

EE Ping, N G and Lim, Teik-Cheng and Subhagata, Chattopadhyay and Bairy, Muralidhar G (2012) Automated Identification of Epileptic and Alcoholic EEG Signals using Recurrence Quantification Analysis. Journal of Mechanics in Medicine and Biology, 12 (5). ISSN 1793-6810

[img] PDF
Automated_Identification_of_epileptic_and_alcoholic_eEG_sihnals_using_RQA.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: http://www.worldscientific.com/worldscinet/jmmb

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 ¯ts. Hence, it is challenging to di®erentiate the cause of ¯ts as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically di®erentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is di±cult 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 quanti¯cation 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 classi¯ers, 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 classi¯ers have been developed to accomplish this task. Results show that the GMM classi¯er outperformed the other classi¯ers with a classi¯- cation sensitivity of 99.6%, speci¯city of 98.3%, and accuracy of 98.6%.

Item Type: Article
Uncontrolled Keywords: EEG; normal; alcoholic; recurrence quanti¯cation analysis; classi¯ers; diagnosis
Subjects: Engineering > MIT Manipal > Biomedical
Depositing User: MIT Library
Date Deposited: 01 Apr 2013 09:42
Last Modified: 21 Nov 2014 04:50
URI: http://eprints.manipal.edu/id/eprint/79360

Actions (login required)

View Item View Item