Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis

Handayani Tjandrasa; Supeno Djanali

doi:10.1007/978-3-319-32213-1_23

Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis

Handayani Tjandrasa^*, Supeno Djanali

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

Epilepsy is a neurological disorder of the brain that can generate epileptic seizures when abnormal excessive activity occurs in the brain. The seizure is marked by brief episodes of involuntary movement of the body, and sometimes followed by unconsciousness. In this study, the EEG classification system was performed to predict whether EEG signals belong to normal individuals, epileptic patients in seizure free or seizure condition. The EEG dataset contains 5 sets of 100 EEG segments which is referred to as set A to set E. The classification system consisted of three scenarios. One of the scenarios involved the methods of Single Channel Independent Component Analysis (SCICA), power spectrum, and a neural network. The results were compared to the results without implementing SCICA. The last experiment showed the effect of using Linear Discriminant Analysis (LDA) to reduce the features of power spectrum. The results gave the accuracies for 3, 4, and 5 classes. By applying SCICA, all the accuracies were improved significantly with the maximum accuracy of 94 % for 3 classes.

Original language	English
Title of host publication	Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015
Editors	Wai Lok Woo, Ping Jack Soh, Hamzah Asyrani Sulaiman, Mohd Azlishah Othman, Mohd Shakir Saat
Publisher	Springer Verlag
Pages	259-268
Number of pages	10
ISBN (Print)	9783319322124
DOIs	https://doi.org/10.1007/978-3-319-32213-1_23
Publication status	Published - 2016
Event	International Conference on Machine Learning and Signal Processing, MALSIP 2015 - Melaka, Malaysia Duration: 12 Jun 2015 → 14 Jun 2015

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	387
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Machine Learning and Signal Processing, MALSIP 2015
Country/Territory	Malaysia
City	Melaka
Period	12/06/15 → 14/06/15

Keywords

Electroencephalogram (EEG) signals
Linear discriminant analysis (LDA)
Multilayer perceptron network (MLP)
Power spectrum
Radial basis function network (RBFN)
Single channel ICA (SCICA)

Access to Document

10.1007/978-3-319-32213-1_23

Cite this

Tjandrasa, H., & Djanali, S. (2016). Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis. In W. L. Woo, P. J. Soh, H. A. Sulaiman, M. A. Othman, & M. S. Saat (Eds.), Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015 (pp. 259-268). (Lecture Notes in Electrical Engineering; Vol. 387). Springer Verlag. https://doi.org/10.1007/978-3-319-32213-1_23

Tjandrasa, Handayani ; Djanali, Supeno. / Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis. Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015. editor / Wai Lok Woo ; Ping Jack Soh ; Hamzah Asyrani Sulaiman ; Mohd Azlishah Othman ; Mohd Shakir Saat. Springer Verlag, 2016. pp. 259-268 (Lecture Notes in Electrical Engineering).

@inproceedings{518ffda8ab3042cba613b7e7b6f30f70,

title = "Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis",

abstract = "Epilepsy is a neurological disorder of the brain that can generate epileptic seizures when abnormal excessive activity occurs in the brain. The seizure is marked by brief episodes of involuntary movement of the body, and sometimes followed by unconsciousness. In this study, the EEG classification system was performed to predict whether EEG signals belong to normal individuals, epileptic patients in seizure free or seizure condition. The EEG dataset contains 5 sets of 100 EEG segments which is referred to as set A to set E. The classification system consisted of three scenarios. One of the scenarios involved the methods of Single Channel Independent Component Analysis (SCICA), power spectrum, and a neural network. The results were compared to the results without implementing SCICA. The last experiment showed the effect of using Linear Discriminant Analysis (LDA) to reduce the features of power spectrum. The results gave the accuracies for 3, 4, and 5 classes. By applying SCICA, all the accuracies were improved significantly with the maximum accuracy of 94 % for 3 classes.",

keywords = "Electroencephalogram (EEG) signals, Linear discriminant analysis (LDA), Multilayer perceptron network (MLP), Power spectrum, Radial basis function network (RBFN), Single channel ICA (SCICA)",

author = "Handayani Tjandrasa and Supeno Djanali",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; International Conference on Machine Learning and Signal Processing, MALSIP 2015 ; Conference date: 12-06-2015 Through 14-06-2015",

year = "2016",

doi = "10.1007/978-3-319-32213-1_23",

language = "English",

isbn = "9783319322124",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "259--268",

editor = "Woo, {Wai Lok} and Soh, {Ping Jack} and Sulaiman, {Hamzah Asyrani} and Othman, {Mohd Azlishah} and Saat, {Mohd Shakir}",

booktitle = "Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015",

address = "Germany",

}

Tjandrasa, H & Djanali, S 2016, Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis. in WL Woo, PJ Soh, HA Sulaiman, MA Othman & MS Saat (eds), Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015. Lecture Notes in Electrical Engineering, vol. 387, Springer Verlag, pp. 259-268, International Conference on Machine Learning and Signal Processing, MALSIP 2015, Melaka, Malaysia, 12/06/15. https://doi.org/10.1007/978-3-319-32213-1_23

Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis. / Tjandrasa, Handayani; Djanali, Supeno.
Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015. ed. / Wai Lok Woo; Ping Jack Soh; Hamzah Asyrani Sulaiman; Mohd Azlishah Othman; Mohd Shakir Saat. Springer Verlag, 2016. p. 259-268 (Lecture Notes in Electrical Engineering; Vol. 387).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis

AU - Tjandrasa, Handayani

AU - Djanali, Supeno

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2016

Y1 - 2016

N2 - Epilepsy is a neurological disorder of the brain that can generate epileptic seizures when abnormal excessive activity occurs in the brain. The seizure is marked by brief episodes of involuntary movement of the body, and sometimes followed by unconsciousness. In this study, the EEG classification system was performed to predict whether EEG signals belong to normal individuals, epileptic patients in seizure free or seizure condition. The EEG dataset contains 5 sets of 100 EEG segments which is referred to as set A to set E. The classification system consisted of three scenarios. One of the scenarios involved the methods of Single Channel Independent Component Analysis (SCICA), power spectrum, and a neural network. The results were compared to the results without implementing SCICA. The last experiment showed the effect of using Linear Discriminant Analysis (LDA) to reduce the features of power spectrum. The results gave the accuracies for 3, 4, and 5 classes. By applying SCICA, all the accuracies were improved significantly with the maximum accuracy of 94 % for 3 classes.

AB - Epilepsy is a neurological disorder of the brain that can generate epileptic seizures when abnormal excessive activity occurs in the brain. The seizure is marked by brief episodes of involuntary movement of the body, and sometimes followed by unconsciousness. In this study, the EEG classification system was performed to predict whether EEG signals belong to normal individuals, epileptic patients in seizure free or seizure condition. The EEG dataset contains 5 sets of 100 EEG segments which is referred to as set A to set E. The classification system consisted of three scenarios. One of the scenarios involved the methods of Single Channel Independent Component Analysis (SCICA), power spectrum, and a neural network. The results were compared to the results without implementing SCICA. The last experiment showed the effect of using Linear Discriminant Analysis (LDA) to reduce the features of power spectrum. The results gave the accuracies for 3, 4, and 5 classes. By applying SCICA, all the accuracies were improved significantly with the maximum accuracy of 94 % for 3 classes.

KW - Electroencephalogram (EEG) signals

KW - Linear discriminant analysis (LDA)

KW - Multilayer perceptron network (MLP)

KW - Power spectrum

KW - Radial basis function network (RBFN)

KW - Single channel ICA (SCICA)

UR - http://www.scopus.com/inward/record.url?scp=84975832576&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-32213-1_23

DO - 10.1007/978-3-319-32213-1_23

M3 - Conference contribution

AN - SCOPUS:84975832576

SN - 9783319322124

T3 - Lecture Notes in Electrical Engineering

SP - 259

EP - 268

BT - Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015

A2 - Woo, Wai Lok

A2 - Soh, Ping Jack

A2 - Sulaiman, Hamzah Asyrani

A2 - Othman, Mohd Azlishah

A2 - Saat, Mohd Shakir

PB - Springer Verlag

T2 - International Conference on Machine Learning and Signal Processing, MALSIP 2015

Y2 - 12 June 2015 through 14 June 2015

ER -

Tjandrasa H, Djanali S. Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis. In Woo WL, Soh PJ, Sulaiman HA, Othman MA, Saat MS, editors, Advances in Machine Learning and Signal Processing - Proceedings of MALSIP 2015. Springer Verlag. 2016. p. 259-268. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-3-319-32213-1_23

Classification of EEG signals using single channel independent component analysis, power spectrum, and linear discriminant analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this