Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals: A comparative study

R. Yuvaraj, M. Murugappan, Norlinah Mohamed Ibrahim, Mohd Iqbal Omar, Kenneth Sundaraj, Khairiyah Mohamad, R. Palaniappan, M. Satiyan

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Deficits in the ability to process emotions characterize several neuropsychiatric disorders and are traits of Parkinson's disease (PD), and there is need for a method of quantifying emotion, which is currently performed by clinical diagnosis. Electroencephalogram (EEG) signals, being an activity of central nervous system (CNS), can reflect the underlying true emotional state of a person. This study applied machine-learning algorithms to categorize EEG emotional states in PD patients that would classify six basic emotions (happiness and sadness, fear, anger, surprise and disgust) in comparison with healthy controls (HC). Emotional EEG data were recorded from 20 PD patients and 20 healthy age-, education level-and sex-matched controls using multimodal (audio-visual) stimuli. The use of nonlinear features motivated by the higher-order spectra (HOS) has been reported to be a promising approach to classify the emotional states. In this work, we made the comparative study of the performance of k-nearest neighbor (kNN) and support vector machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Analysis of variance (ANOVA) showed that power spectrum and HOS based features were statistically significant among the six emotional states (p < 0.0001). Classification results shows that using the selected HOS based features instead of power spectrum based features provided comparatively better accuracy for all the six classes with an overall accuracy of 70.10% ± 2.83% and 77.29% ± 1.73% for PD patients and HC in beta (13-30 Hz) band using SVM classifier. Besides, PD patients achieved less accuracy in the processing of negative emotions (sadness, fear, anger and disgust) than in processing of positive emotions (happiness, surprise) compared with HC. These results demonstrate the effectiveness of applying machine learning techniques to the classification of emotional states in PD patients in a user independent manner using EEG signals. The accuracy of the system can be improved by investigating the other HOS based features. This study might lead to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.

Original languageEnglish
Pages (from-to)89-120
Number of pages32
JournalJournal of Integrative Neuroscience
Volume13
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

Parkinson Disease
Electroencephalography
Emotions
Happiness
Anger
Fear
Aptitude
Sex Education
Nervous System Diseases
Analysis of Variance
Central Nervous System
Support Vector Machine
Machine Learning

Keywords

  • bispectrum
  • EEG
  • emotion
  • Parkinson's disease
  • pattern classification
  • power spectrum

ASJC Scopus subject areas

  • Neuroscience(all)
  • Medicine(all)

Cite this

Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals : A comparative study. / Yuvaraj, R.; Murugappan, M.; Mohamed Ibrahim, Norlinah; Omar, Mohd Iqbal; Sundaraj, Kenneth; Mohamad, Khairiyah; Palaniappan, R.; Satiyan, M.

In: Journal of Integrative Neuroscience, Vol. 13, No. 1, 2014, p. 89-120.

Research output: Contribution to journalArticle

Yuvaraj, R. ; Murugappan, M. ; Mohamed Ibrahim, Norlinah ; Omar, Mohd Iqbal ; Sundaraj, Kenneth ; Mohamad, Khairiyah ; Palaniappan, R. ; Satiyan, M. / Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals : A comparative study. In: Journal of Integrative Neuroscience. 2014 ; Vol. 13, No. 1. pp. 89-120.
@article{106948d122454375af60e06ff4d3f5a6,
title = "Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals: A comparative study",
abstract = "Deficits in the ability to process emotions characterize several neuropsychiatric disorders and are traits of Parkinson's disease (PD), and there is need for a method of quantifying emotion, which is currently performed by clinical diagnosis. Electroencephalogram (EEG) signals, being an activity of central nervous system (CNS), can reflect the underlying true emotional state of a person. This study applied machine-learning algorithms to categorize EEG emotional states in PD patients that would classify six basic emotions (happiness and sadness, fear, anger, surprise and disgust) in comparison with healthy controls (HC). Emotional EEG data were recorded from 20 PD patients and 20 healthy age-, education level-and sex-matched controls using multimodal (audio-visual) stimuli. The use of nonlinear features motivated by the higher-order spectra (HOS) has been reported to be a promising approach to classify the emotional states. In this work, we made the comparative study of the performance of k-nearest neighbor (kNN) and support vector machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Analysis of variance (ANOVA) showed that power spectrum and HOS based features were statistically significant among the six emotional states (p < 0.0001). Classification results shows that using the selected HOS based features instead of power spectrum based features provided comparatively better accuracy for all the six classes with an overall accuracy of 70.10{\%} ± 2.83{\%} and 77.29{\%} ± 1.73{\%} for PD patients and HC in beta (13-30 Hz) band using SVM classifier. Besides, PD patients achieved less accuracy in the processing of negative emotions (sadness, fear, anger and disgust) than in processing of positive emotions (happiness, surprise) compared with HC. These results demonstrate the effectiveness of applying machine learning techniques to the classification of emotional states in PD patients in a user independent manner using EEG signals. The accuracy of the system can be improved by investigating the other HOS based features. This study might lead to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.",
keywords = "bispectrum, EEG, emotion, Parkinson's disease, pattern classification, power spectrum",
author = "R. Yuvaraj and M. Murugappan and {Mohamed Ibrahim}, Norlinah and Omar, {Mohd Iqbal} and Kenneth Sundaraj and Khairiyah Mohamad and R. Palaniappan and M. Satiyan",
year = "2014",
doi = "10.1142/S021963521450006X",
language = "English",
volume = "13",
pages = "89--120",
journal = "Journal of Integrative Neuroscience",
issn = "0219-6352",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

TY - JOUR

T1 - Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals

T2 - A comparative study

AU - Yuvaraj, R.

AU - Murugappan, M.

AU - Mohamed Ibrahim, Norlinah

AU - Omar, Mohd Iqbal

AU - Sundaraj, Kenneth

AU - Mohamad, Khairiyah

AU - Palaniappan, R.

AU - Satiyan, M.

PY - 2014

Y1 - 2014

N2 - Deficits in the ability to process emotions characterize several neuropsychiatric disorders and are traits of Parkinson's disease (PD), and there is need for a method of quantifying emotion, which is currently performed by clinical diagnosis. Electroencephalogram (EEG) signals, being an activity of central nervous system (CNS), can reflect the underlying true emotional state of a person. This study applied machine-learning algorithms to categorize EEG emotional states in PD patients that would classify six basic emotions (happiness and sadness, fear, anger, surprise and disgust) in comparison with healthy controls (HC). Emotional EEG data were recorded from 20 PD patients and 20 healthy age-, education level-and sex-matched controls using multimodal (audio-visual) stimuli. The use of nonlinear features motivated by the higher-order spectra (HOS) has been reported to be a promising approach to classify the emotional states. In this work, we made the comparative study of the performance of k-nearest neighbor (kNN) and support vector machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Analysis of variance (ANOVA) showed that power spectrum and HOS based features were statistically significant among the six emotional states (p < 0.0001). Classification results shows that using the selected HOS based features instead of power spectrum based features provided comparatively better accuracy for all the six classes with an overall accuracy of 70.10% ± 2.83% and 77.29% ± 1.73% for PD patients and HC in beta (13-30 Hz) band using SVM classifier. Besides, PD patients achieved less accuracy in the processing of negative emotions (sadness, fear, anger and disgust) than in processing of positive emotions (happiness, surprise) compared with HC. These results demonstrate the effectiveness of applying machine learning techniques to the classification of emotional states in PD patients in a user independent manner using EEG signals. The accuracy of the system can be improved by investigating the other HOS based features. This study might lead to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.

AB - Deficits in the ability to process emotions characterize several neuropsychiatric disorders and are traits of Parkinson's disease (PD), and there is need for a method of quantifying emotion, which is currently performed by clinical diagnosis. Electroencephalogram (EEG) signals, being an activity of central nervous system (CNS), can reflect the underlying true emotional state of a person. This study applied machine-learning algorithms to categorize EEG emotional states in PD patients that would classify six basic emotions (happiness and sadness, fear, anger, surprise and disgust) in comparison with healthy controls (HC). Emotional EEG data were recorded from 20 PD patients and 20 healthy age-, education level-and sex-matched controls using multimodal (audio-visual) stimuli. The use of nonlinear features motivated by the higher-order spectra (HOS) has been reported to be a promising approach to classify the emotional states. In this work, we made the comparative study of the performance of k-nearest neighbor (kNN) and support vector machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Analysis of variance (ANOVA) showed that power spectrum and HOS based features were statistically significant among the six emotional states (p < 0.0001). Classification results shows that using the selected HOS based features instead of power spectrum based features provided comparatively better accuracy for all the six classes with an overall accuracy of 70.10% ± 2.83% and 77.29% ± 1.73% for PD patients and HC in beta (13-30 Hz) band using SVM classifier. Besides, PD patients achieved less accuracy in the processing of negative emotions (sadness, fear, anger and disgust) than in processing of positive emotions (happiness, surprise) compared with HC. These results demonstrate the effectiveness of applying machine learning techniques to the classification of emotional states in PD patients in a user independent manner using EEG signals. The accuracy of the system can be improved by investigating the other HOS based features. This study might lead to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.

KW - bispectrum

KW - EEG

KW - emotion

KW - Parkinson's disease

KW - pattern classification

KW - power spectrum

UR - http://www.scopus.com/inward/record.url?scp=84898930153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898930153&partnerID=8YFLogxK

U2 - 10.1142/S021963521450006X

DO - 10.1142/S021963521450006X

M3 - Article

C2 - 24738541

AN - SCOPUS:84898930153

VL - 13

SP - 89

EP - 120

JO - Journal of Integrative Neuroscience

JF - Journal of Integrative Neuroscience

SN - 0219-6352

IS - 1

ER -