Wavelet based feature extraction for classification of motor imagery signals

F. Sherwani, Shahnoor Shanta, B. S.K.K. Ibrahim, M. Saiful Huq

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

4 Citations (Scopus)

Abstract

The analysis of EEG signals play a significant role in brain related studies. Accurate investigation and analysis of the EEG signals from a subject can interpret the inherent information about the intention of the person to some extent. The accuracy of such interpretation or detection can be of utmost importance for various brain computer interface (BCI) based applications. For instance, within the last decade, BCI has been widely investigated and employed to assist in the restoration of sensory and motor functions in paralyzed individuals. EEG typically contains numerous information about the cognitive thinking and intention of a person, particularly in terms of motor movements. Due to this, comprehensive methods of EEG signal arrangement and pattern recognition through signal classification techniques are required to precisely predict the intended set of movements. In this study, an EEG classification technique based on a combination of wavelet transform analysis and Neural Networks (NN) is presented. Daubechies wavelet decomposition (db8) has been employed to decompose the recorded EEG signals into four levels. These decomposed level details are then used to calculate the feature set which is input to NN classifier for further classification. A total of 6 features were used to perform feature wise classification, where Integrated EEG (IEEG) feature set has been found to possess the highest classification accuracy of 89.39 % with a NN classifier of 9 hidden layers. Whereas, a classification accuracy of 94.86 % was achieved when the features were arranged and cascaded horizontally in form of a dataset as input to a NN classifier of 5 hidden layers.

Original languageEnglish
Title of host publicationIECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages360-364
Number of pages5
ISBN (Electronic)9781467377911
DOIs
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016 - Kuala Lumpur, Malaysia
Duration: 4 Dec 20168 Dec 2016

Publication series

NameIECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences

Conference

Conference2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016
CountryMalaysia
CityKuala Lumpur
Period4/12/168/12/16

Fingerprint

electroencephalography
Electroencephalography
pattern recognition
imagery
Feature extraction
classifiers
Neural networks
brain
Brain computer interface
Classifiers
Wavelet decomposition
wavelet analysis
restoration
Wavelet transforms
Restoration
Pattern recognition
Brain
decomposition

Keywords

  • Classsifciation
  • EEG
  • Feature extraction
  • Motor Imagery signals
  • Wavelet decomposition

ASJC Scopus subject areas

  • Biomedical Engineering
  • Instrumentation

Cite this

Sherwani, F., Shanta, S., Ibrahim, B. S. K. K., & Huq, M. S. (2016). Wavelet based feature extraction for classification of motor imagery signals. In IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences (pp. 360-364). [7843474] (IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECBES.2016.7843474

Wavelet based feature extraction for classification of motor imagery signals. / Sherwani, F.; Shanta, Shahnoor; Ibrahim, B. S.K.K.; Huq, M. Saiful.

IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc., 2016. p. 360-364 7843474 (IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences).

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Sherwani, F, Shanta, S, Ibrahim, BSKK & Huq, MS 2016, Wavelet based feature extraction for classification of motor imagery signals. in IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences., 7843474, IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences, Institute of Electrical and Electronics Engineers Inc., pp. 360-364, 2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016, Kuala Lumpur, Malaysia, 4/12/16. https://doi.org/10.1109/IECBES.2016.7843474
Sherwani F, Shanta S, Ibrahim BSKK, Huq MS. Wavelet based feature extraction for classification of motor imagery signals. In IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc. 2016. p. 360-364. 7843474. (IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences). https://doi.org/10.1109/IECBES.2016.7843474
Sherwani, F. ; Shanta, Shahnoor ; Ibrahim, B. S.K.K. ; Huq, M. Saiful. / Wavelet based feature extraction for classification of motor imagery signals. IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 360-364 (IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences).
@inproceedings{bf20be2848f64839b7583c0ee8c2b4d8,
title = "Wavelet based feature extraction for classification of motor imagery signals",
abstract = "The analysis of EEG signals play a significant role in brain related studies. Accurate investigation and analysis of the EEG signals from a subject can interpret the inherent information about the intention of the person to some extent. The accuracy of such interpretation or detection can be of utmost importance for various brain computer interface (BCI) based applications. For instance, within the last decade, BCI has been widely investigated and employed to assist in the restoration of sensory and motor functions in paralyzed individuals. EEG typically contains numerous information about the cognitive thinking and intention of a person, particularly in terms of motor movements. Due to this, comprehensive methods of EEG signal arrangement and pattern recognition through signal classification techniques are required to precisely predict the intended set of movements. In this study, an EEG classification technique based on a combination of wavelet transform analysis and Neural Networks (NN) is presented. Daubechies wavelet decomposition (db8) has been employed to decompose the recorded EEG signals into four levels. These decomposed level details are then used to calculate the feature set which is input to NN classifier for further classification. A total of 6 features were used to perform feature wise classification, where Integrated EEG (IEEG) feature set has been found to possess the highest classification accuracy of 89.39 {\%} with a NN classifier of 9 hidden layers. Whereas, a classification accuracy of 94.86 {\%} was achieved when the features were arranged and cascaded horizontally in form of a dataset as input to a NN classifier of 5 hidden layers.",
keywords = "Classsifciation, EEG, Feature extraction, Motor Imagery signals, Wavelet decomposition",
author = "F. Sherwani and Shahnoor Shanta and Ibrahim, {B. S.K.K.} and Huq, {M. Saiful}",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/IECBES.2016.7843474",
language = "English",
series = "IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "360--364",
booktitle = "IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences",
address = "United States",

}

TY - GEN

T1 - Wavelet based feature extraction for classification of motor imagery signals

AU - Sherwani, F.

AU - Shanta, Shahnoor

AU - Ibrahim, B. S.K.K.

AU - Huq, M. Saiful

PY - 2016/1/1

Y1 - 2016/1/1

N2 - The analysis of EEG signals play a significant role in brain related studies. Accurate investigation and analysis of the EEG signals from a subject can interpret the inherent information about the intention of the person to some extent. The accuracy of such interpretation or detection can be of utmost importance for various brain computer interface (BCI) based applications. For instance, within the last decade, BCI has been widely investigated and employed to assist in the restoration of sensory and motor functions in paralyzed individuals. EEG typically contains numerous information about the cognitive thinking and intention of a person, particularly in terms of motor movements. Due to this, comprehensive methods of EEG signal arrangement and pattern recognition through signal classification techniques are required to precisely predict the intended set of movements. In this study, an EEG classification technique based on a combination of wavelet transform analysis and Neural Networks (NN) is presented. Daubechies wavelet decomposition (db8) has been employed to decompose the recorded EEG signals into four levels. These decomposed level details are then used to calculate the feature set which is input to NN classifier for further classification. A total of 6 features were used to perform feature wise classification, where Integrated EEG (IEEG) feature set has been found to possess the highest classification accuracy of 89.39 % with a NN classifier of 9 hidden layers. Whereas, a classification accuracy of 94.86 % was achieved when the features were arranged and cascaded horizontally in form of a dataset as input to a NN classifier of 5 hidden layers.

AB - The analysis of EEG signals play a significant role in brain related studies. Accurate investigation and analysis of the EEG signals from a subject can interpret the inherent information about the intention of the person to some extent. The accuracy of such interpretation or detection can be of utmost importance for various brain computer interface (BCI) based applications. For instance, within the last decade, BCI has been widely investigated and employed to assist in the restoration of sensory and motor functions in paralyzed individuals. EEG typically contains numerous information about the cognitive thinking and intention of a person, particularly in terms of motor movements. Due to this, comprehensive methods of EEG signal arrangement and pattern recognition through signal classification techniques are required to precisely predict the intended set of movements. In this study, an EEG classification technique based on a combination of wavelet transform analysis and Neural Networks (NN) is presented. Daubechies wavelet decomposition (db8) has been employed to decompose the recorded EEG signals into four levels. These decomposed level details are then used to calculate the feature set which is input to NN classifier for further classification. A total of 6 features were used to perform feature wise classification, where Integrated EEG (IEEG) feature set has been found to possess the highest classification accuracy of 89.39 % with a NN classifier of 9 hidden layers. Whereas, a classification accuracy of 94.86 % was achieved when the features were arranged and cascaded horizontally in form of a dataset as input to a NN classifier of 5 hidden layers.

KW - Classsifciation

KW - EEG

KW - Feature extraction

KW - Motor Imagery signals

KW - Wavelet decomposition

UR - http://www.scopus.com/inward/record.url?scp=85015636375&partnerID=8YFLogxK

U2 - 10.1109/IECBES.2016.7843474

DO - 10.1109/IECBES.2016.7843474

M3 - Conference proceeding

T3 - IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences

SP - 360

EP - 364

BT - IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences

PB - Institute of Electrical and Electronics Engineers Inc.

ER -