Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics

G. Muralidhar Bairy, Shreya Bhat, Lim Wei Jie Eugene, U. C. Niranjan, Subha D. Puthankattil, Paul K. Joseph

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Depression is a mental disorder that affects emotional and physical state of a person. It is a state of extremesadness and dejection. The electroencephalographic (EEG) signals can be used to detect the alterations in the brain's electrochemical potential. The highly irregular and complex EEG signal variations can be determined by different processing tools. The present work is based on the automated classification of the normal and depression EEG signals. The discrete cosine transform (DCT) decomposes the normal and depression EEG signals into different frequency sub-bands. Nonlinear methods such as sample entropy, correlation dimension, fractal dimension, largest Lyapunov exponent, Hurst exponent and detrended fluctuation analysis are applied to the DCT coefficients and the extracted characteristic features are ranked using t-value. These significant features are fed to decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN) and naïve Bayes (NB) classifiers. Five significant features are selected and the SVM classifier with radial basis function (RBF) results in a classification accuracy of 93.8%, sensitivity of 92% and specificity of 95.8%.

Original languageEnglish
Pages (from-to)635-640
Number of pages6
JournalJournal of Medical Imaging and Health Informatics
Volume5
Issue number3
DOIs
Publication statusPublished - 01-01-2015

Fingerprint

Nonlinear Dynamics
Depression
Fractals
Decision Trees
Entropy
Mental Disorders
Sensitivity and Specificity
Brain
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Muralidhar Bairy, G. ; Bhat, Shreya ; Eugene, Lim Wei Jie ; Niranjan, U. C. ; Puthankattil, Subha D. ; Joseph, Paul K. / Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics. In: Journal of Medical Imaging and Health Informatics. 2015 ; Vol. 5, No. 3. pp. 635-640.
@article{a33774b1a7384af7b7d86cfb8f4c6bd9,
title = "Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics",
abstract = "Depression is a mental disorder that affects emotional and physical state of a person. It is a state of extremesadness and dejection. The electroencephalographic (EEG) signals can be used to detect the alterations in the brain's electrochemical potential. The highly irregular and complex EEG signal variations can be determined by different processing tools. The present work is based on the automated classification of the normal and depression EEG signals. The discrete cosine transform (DCT) decomposes the normal and depression EEG signals into different frequency sub-bands. Nonlinear methods such as sample entropy, correlation dimension, fractal dimension, largest Lyapunov exponent, Hurst exponent and detrended fluctuation analysis are applied to the DCT coefficients and the extracted characteristic features are ranked using t-value. These significant features are fed to decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN) and na{\"i}ve Bayes (NB) classifiers. Five significant features are selected and the SVM classifier with radial basis function (RBF) results in a classification accuracy of 93.8{\%}, sensitivity of 92{\%} and specificity of 95.8{\%}.",
author = "{Muralidhar Bairy}, G. and Shreya Bhat and Eugene, {Lim Wei Jie} and Niranjan, {U. C.} and Puthankattil, {Subha D.} and Joseph, {Paul K.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1166/jmihi.2015.1418",
language = "English",
volume = "5",
pages = "635--640",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "3",

}

Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics. / Muralidhar Bairy, G.; Bhat, Shreya; Eugene, Lim Wei Jie; Niranjan, U. C.; Puthankattil, Subha D.; Joseph, Paul K.

In: Journal of Medical Imaging and Health Informatics, Vol. 5, No. 3, 01.01.2015, p. 635-640.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics

AU - Muralidhar Bairy, G.

AU - Bhat, Shreya

AU - Eugene, Lim Wei Jie

AU - Niranjan, U. C.

AU - Puthankattil, Subha D.

AU - Joseph, Paul K.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Depression is a mental disorder that affects emotional and physical state of a person. It is a state of extremesadness and dejection. The electroencephalographic (EEG) signals can be used to detect the alterations in the brain's electrochemical potential. The highly irregular and complex EEG signal variations can be determined by different processing tools. The present work is based on the automated classification of the normal and depression EEG signals. The discrete cosine transform (DCT) decomposes the normal and depression EEG signals into different frequency sub-bands. Nonlinear methods such as sample entropy, correlation dimension, fractal dimension, largest Lyapunov exponent, Hurst exponent and detrended fluctuation analysis are applied to the DCT coefficients and the extracted characteristic features are ranked using t-value. These significant features are fed to decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN) and naïve Bayes (NB) classifiers. Five significant features are selected and the SVM classifier with radial basis function (RBF) results in a classification accuracy of 93.8%, sensitivity of 92% and specificity of 95.8%.

AB - Depression is a mental disorder that affects emotional and physical state of a person. It is a state of extremesadness and dejection. The electroencephalographic (EEG) signals can be used to detect the alterations in the brain's electrochemical potential. The highly irregular and complex EEG signal variations can be determined by different processing tools. The present work is based on the automated classification of the normal and depression EEG signals. The discrete cosine transform (DCT) decomposes the normal and depression EEG signals into different frequency sub-bands. Nonlinear methods such as sample entropy, correlation dimension, fractal dimension, largest Lyapunov exponent, Hurst exponent and detrended fluctuation analysis are applied to the DCT coefficients and the extracted characteristic features are ranked using t-value. These significant features are fed to decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN) and naïve Bayes (NB) classifiers. Five significant features are selected and the SVM classifier with radial basis function (RBF) results in a classification accuracy of 93.8%, sensitivity of 92% and specificity of 95.8%.

UR - http://www.scopus.com/inward/record.url?scp=84923876873&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923876873&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2015.1418

DO - 10.1166/jmihi.2015.1418

M3 - Article

VL - 5

SP - 635

EP - 640

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 3

ER -