A Biologically Inspired Approach to Frequency Domain Feature Extraction for EEG Classification

Nurhan Gursel Ozmen, Levent Gumusel, Yuan Yang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Classification of electroencephalogram (EEG) signal is important in mental decoding for brain-computer interfaces (BCI). We introduced a feature extraction approach based on frequency domain analysis to improve the classification performance on different mental tasks using single-channel EEG. This biologically inspired method extracts the most discriminative spectral features from power spectral densities (PSDs) of the EEG signals. We applied our method on a dataset of six subjects who performed five different imagination tasks: (i) resting state, (ii) mental arithmetic, (iii) imagination of left hand movement, (iv) imagination of right hand movement, and (v) imagination of letter "A." Pairwise and multiclass classifications were performed in single EEG channel using Linear Discriminant Analysis and Support Vector Machines. Our method produced results (mean classification accuracy of 83.06% for binary classification and 91.85% for multiclassification) that are on par with the state-of-The-Art methods, using single-channel EEG with low computational cost. Among all task pairs, mental arithmetic versus letter imagination yielded the best result (mean classification accuracy of 90.29%), indicating that this task pair could be the most suitable pair for a binary class BCI. This study contributes to the development of single-channel BCI, as well as finding the best task pair for user defined applications.

Original languageEnglish (US)
Article number9890132
JournalComputational and Mathematical Methods in Medicine
Volume2018
DOIs
StatePublished - Jan 1 2018

Fingerprint

Imagination
Electroencephalography
Feature Extraction
Frequency Domain
Feature extraction
Mental arithmetic
Brain-Computer Interfaces
Brain computer interface
Frequency Domain Analysis
Hand
Multi-class Classification
Binary Classification
Power Spectral Density
Frequency domain analysis
Discriminant Analysis
Power spectral density
Discriminant analysis
Decoding
Computational Cost
Pairwise

ASJC Scopus subject areas

  • Modeling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Applied Mathematics

Cite this

@article{190c0060e9704d0a984976291320b3a6,
title = "A Biologically Inspired Approach to Frequency Domain Feature Extraction for EEG Classification",
abstract = "Classification of electroencephalogram (EEG) signal is important in mental decoding for brain-computer interfaces (BCI). We introduced a feature extraction approach based on frequency domain analysis to improve the classification performance on different mental tasks using single-channel EEG. This biologically inspired method extracts the most discriminative spectral features from power spectral densities (PSDs) of the EEG signals. We applied our method on a dataset of six subjects who performed five different imagination tasks: (i) resting state, (ii) mental arithmetic, (iii) imagination of left hand movement, (iv) imagination of right hand movement, and (v) imagination of letter {"}A.{"} Pairwise and multiclass classifications were performed in single EEG channel using Linear Discriminant Analysis and Support Vector Machines. Our method produced results (mean classification accuracy of 83.06{\%} for binary classification and 91.85{\%} for multiclassification) that are on par with the state-of-The-Art methods, using single-channel EEG with low computational cost. Among all task pairs, mental arithmetic versus letter imagination yielded the best result (mean classification accuracy of 90.29{\%}), indicating that this task pair could be the most suitable pair for a binary class BCI. This study contributes to the development of single-channel BCI, as well as finding the best task pair for user defined applications.",
author = "{Gursel Ozmen}, Nurhan and Levent Gumusel and Yuan Yang",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/9890132",
language = "English (US)",
volume = "2018",
journal = "Computational and Mathematical Methods in Medicine",
issn = "1748-670X",
publisher = "Hindawi Publishing Corporation",

}

A Biologically Inspired Approach to Frequency Domain Feature Extraction for EEG Classification. / Gursel Ozmen, Nurhan; Gumusel, Levent; Yang, Yuan.

In: Computational and Mathematical Methods in Medicine, Vol. 2018, 9890132, 01.01.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Biologically Inspired Approach to Frequency Domain Feature Extraction for EEG Classification

AU - Gursel Ozmen, Nurhan

AU - Gumusel, Levent

AU - Yang, Yuan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Classification of electroencephalogram (EEG) signal is important in mental decoding for brain-computer interfaces (BCI). We introduced a feature extraction approach based on frequency domain analysis to improve the classification performance on different mental tasks using single-channel EEG. This biologically inspired method extracts the most discriminative spectral features from power spectral densities (PSDs) of the EEG signals. We applied our method on a dataset of six subjects who performed five different imagination tasks: (i) resting state, (ii) mental arithmetic, (iii) imagination of left hand movement, (iv) imagination of right hand movement, and (v) imagination of letter "A." Pairwise and multiclass classifications were performed in single EEG channel using Linear Discriminant Analysis and Support Vector Machines. Our method produced results (mean classification accuracy of 83.06% for binary classification and 91.85% for multiclassification) that are on par with the state-of-The-Art methods, using single-channel EEG with low computational cost. Among all task pairs, mental arithmetic versus letter imagination yielded the best result (mean classification accuracy of 90.29%), indicating that this task pair could be the most suitable pair for a binary class BCI. This study contributes to the development of single-channel BCI, as well as finding the best task pair for user defined applications.

AB - Classification of electroencephalogram (EEG) signal is important in mental decoding for brain-computer interfaces (BCI). We introduced a feature extraction approach based on frequency domain analysis to improve the classification performance on different mental tasks using single-channel EEG. This biologically inspired method extracts the most discriminative spectral features from power spectral densities (PSDs) of the EEG signals. We applied our method on a dataset of six subjects who performed five different imagination tasks: (i) resting state, (ii) mental arithmetic, (iii) imagination of left hand movement, (iv) imagination of right hand movement, and (v) imagination of letter "A." Pairwise and multiclass classifications were performed in single EEG channel using Linear Discriminant Analysis and Support Vector Machines. Our method produced results (mean classification accuracy of 83.06% for binary classification and 91.85% for multiclassification) that are on par with the state-of-The-Art methods, using single-channel EEG with low computational cost. Among all task pairs, mental arithmetic versus letter imagination yielded the best result (mean classification accuracy of 90.29%), indicating that this task pair could be the most suitable pair for a binary class BCI. This study contributes to the development of single-channel BCI, as well as finding the best task pair for user defined applications.

UR - http://www.scopus.com/inward/record.url?scp=85041699092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041699092&partnerID=8YFLogxK

U2 - 10.1155/2018/9890132

DO - 10.1155/2018/9890132

M3 - Article

VL - 2018

JO - Computational and Mathematical Methods in Medicine

JF - Computational and Mathematical Methods in Medicine

SN - 1748-670X

M1 - 9890132

ER -