Efficient epileptic seizure detection based on electroencephalography signal

Ying Mei Qin, Chun Xiao Han, Yanqiu Che, Hui Yan Li

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

Abstract

We investigate the detection of epileptic seizure onset based on electroencephalography (EEG) signal in short-time sessions (less than one second) from various samples from epilepsy and healthy people. Wavelet transform methods are applied to extract the features embedded in the high-dimensional epileptic EEG signal. It is found that results of wavelet transform play significant roles in dimensional reduction process. Then, machine learning pipeline is built based on support vector machine (SVM) algorithm. It is found that epileptic seizure state in the test data set could be predicted with high precision (98.1%) based only on mini-segments of EEG signal (0.6 second). Predictions based on 0.1 second mini-segments of EEG signal are also investigated. This research may be significant to the clinical treatment of epileptic seizure, because efficient methods could be applied to interrupt the process of epileptic seizure very fast (in less than one second).

Original languageEnglish (US)
Title of host publicationProceedings of the 36th Chinese Control Conference, CCC 2017
EditorsTao Liu, Qianchuan Zhao
PublisherIEEE Computer Society
Pages5324-5327
Number of pages4
ISBN (Electronic)9789881563934
DOIs
StatePublished - Sep 7 2017
Event36th Chinese Control Conference, CCC 2017 - Dalian, China
Duration: Jul 26 2017Jul 28 2017

Publication series

NameChinese Control Conference, CCC
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Other

Other36th Chinese Control Conference, CCC 2017
CountryChina
CityDalian
Period7/26/177/28/17

Fingerprint

Electroencephalography
Wavelet transforms
Wavelet Transform
Epilepsy
Dimensional Reduction
Support vector machines
Learning systems
Support Vector Machine
Machine Learning
High-dimensional
Pipelines
Prediction

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Control and Systems Engineering
  • Applied Mathematics
  • Modeling and Simulation

Cite this

Qin, Y. M., Han, C. X., Che, Y., & Li, H. Y. (2017). Efficient epileptic seizure detection based on electroencephalography signal. In T. Liu, & Q. Zhao (Eds.), Proceedings of the 36th Chinese Control Conference, CCC 2017 (pp. 5324-5327). [8028198] (Chinese Control Conference, CCC). IEEE Computer Society. https://doi.org/10.23919/ChiCC.2017.8028198
Qin, Ying Mei ; Han, Chun Xiao ; Che, Yanqiu ; Li, Hui Yan. / Efficient epileptic seizure detection based on electroencephalography signal. Proceedings of the 36th Chinese Control Conference, CCC 2017. editor / Tao Liu ; Qianchuan Zhao. IEEE Computer Society, 2017. pp. 5324-5327 (Chinese Control Conference, CCC).
@inproceedings{d041405b2c3f41788266424195e639fb,
title = "Efficient epileptic seizure detection based on electroencephalography signal",
abstract = "We investigate the detection of epileptic seizure onset based on electroencephalography (EEG) signal in short-time sessions (less than one second) from various samples from epilepsy and healthy people. Wavelet transform methods are applied to extract the features embedded in the high-dimensional epileptic EEG signal. It is found that results of wavelet transform play significant roles in dimensional reduction process. Then, machine learning pipeline is built based on support vector machine (SVM) algorithm. It is found that epileptic seizure state in the test data set could be predicted with high precision (98.1{\%}) based only on mini-segments of EEG signal (0.6 second). Predictions based on 0.1 second mini-segments of EEG signal are also investigated. This research may be significant to the clinical treatment of epileptic seizure, because efficient methods could be applied to interrupt the process of epileptic seizure very fast (in less than one second).",
author = "Qin, {Ying Mei} and Han, {Chun Xiao} and Yanqiu Che and Li, {Hui Yan}",
year = "2017",
month = "9",
day = "7",
doi = "10.23919/ChiCC.2017.8028198",
language = "English (US)",
series = "Chinese Control Conference, CCC",
publisher = "IEEE Computer Society",
pages = "5324--5327",
editor = "Tao Liu and Qianchuan Zhao",
booktitle = "Proceedings of the 36th Chinese Control Conference, CCC 2017",
address = "United States",

}

Qin, YM, Han, CX, Che, Y & Li, HY 2017, Efficient epileptic seizure detection based on electroencephalography signal. in T Liu & Q Zhao (eds), Proceedings of the 36th Chinese Control Conference, CCC 2017., 8028198, Chinese Control Conference, CCC, IEEE Computer Society, pp. 5324-5327, 36th Chinese Control Conference, CCC 2017, Dalian, China, 7/26/17. https://doi.org/10.23919/ChiCC.2017.8028198

Efficient epileptic seizure detection based on electroencephalography signal. / Qin, Ying Mei; Han, Chun Xiao; Che, Yanqiu; Li, Hui Yan.

Proceedings of the 36th Chinese Control Conference, CCC 2017. ed. / Tao Liu; Qianchuan Zhao. IEEE Computer Society, 2017. p. 5324-5327 8028198 (Chinese Control Conference, CCC).

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

TY - GEN

T1 - Efficient epileptic seizure detection based on electroencephalography signal

AU - Qin, Ying Mei

AU - Han, Chun Xiao

AU - Che, Yanqiu

AU - Li, Hui Yan

PY - 2017/9/7

Y1 - 2017/9/7

N2 - We investigate the detection of epileptic seizure onset based on electroencephalography (EEG) signal in short-time sessions (less than one second) from various samples from epilepsy and healthy people. Wavelet transform methods are applied to extract the features embedded in the high-dimensional epileptic EEG signal. It is found that results of wavelet transform play significant roles in dimensional reduction process. Then, machine learning pipeline is built based on support vector machine (SVM) algorithm. It is found that epileptic seizure state in the test data set could be predicted with high precision (98.1%) based only on mini-segments of EEG signal (0.6 second). Predictions based on 0.1 second mini-segments of EEG signal are also investigated. This research may be significant to the clinical treatment of epileptic seizure, because efficient methods could be applied to interrupt the process of epileptic seizure very fast (in less than one second).

AB - We investigate the detection of epileptic seizure onset based on electroencephalography (EEG) signal in short-time sessions (less than one second) from various samples from epilepsy and healthy people. Wavelet transform methods are applied to extract the features embedded in the high-dimensional epileptic EEG signal. It is found that results of wavelet transform play significant roles in dimensional reduction process. Then, machine learning pipeline is built based on support vector machine (SVM) algorithm. It is found that epileptic seizure state in the test data set could be predicted with high precision (98.1%) based only on mini-segments of EEG signal (0.6 second). Predictions based on 0.1 second mini-segments of EEG signal are also investigated. This research may be significant to the clinical treatment of epileptic seizure, because efficient methods could be applied to interrupt the process of epileptic seizure very fast (in less than one second).

UR - http://www.scopus.com/inward/record.url?scp=85032177221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032177221&partnerID=8YFLogxK

U2 - 10.23919/ChiCC.2017.8028198

DO - 10.23919/ChiCC.2017.8028198

M3 - Conference contribution

AN - SCOPUS:85032177221

T3 - Chinese Control Conference, CCC

SP - 5324

EP - 5327

BT - Proceedings of the 36th Chinese Control Conference, CCC 2017

A2 - Liu, Tao

A2 - Zhao, Qianchuan

PB - IEEE Computer Society

ER -

Qin YM, Han CX, Che Y, Li HY. Efficient epileptic seizure detection based on electroencephalography signal. In Liu T, Zhao Q, editors, Proceedings of the 36th Chinese Control Conference, CCC 2017. IEEE Computer Society. 2017. p. 5324-5327. 8028198. (Chinese Control Conference, CCC). https://doi.org/10.23919/ChiCC.2017.8028198