Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature

Yingmei Qin, Chunxiao Han, Meili Lu, Ruofan Wang, Li Yang, Yanqiu Che

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

Abstract

Automatic seizure detection is of great importance in clinical practice of epilepsy. This paper presents a classification system based on discrete wavelet transform (DWT) and the extreme learning machine (ELM) for epileptic seizure detection by distinguishing ictal and interictal electroencephalogram (EEG) signals. The original EEG signal is first decomposed by Daubechies order 4 wavelet into several sub-bands. Then, standard deviation, log of amplitude, and quartiles are calculated for the original and decomposed signals to construct feature vectors. Different combination of these features are fed into ELM and support vector machine (SVM). After comparing different combination strategies, we find that, using ELM, even with a single feature (standard deviation) from a single sub-band signal (4-8Hz), one can obtain a satisfactory classification result, which remarkably reduce the computational complexity and make the detection system more practical.

Original languageEnglish (US)
Title of host publicationProceedings of the 37th Chinese Control Conference, CCC 2018
EditorsXin Chen, Qianchuan Zhao
PublisherIEEE Computer Society
Pages4430-4433
Number of pages4
ISBN (Electronic)9789881563941
DOIs
StatePublished - Oct 5 2018
Event37th Chinese Control Conference, CCC 2018 - Wuhan, China
Duration: Jul 25 2018Jul 27 2018

Publication series

NameChinese Control Conference, CCC
Volume2018-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Other

Other37th Chinese Control Conference, CCC 2018
CountryChina
CityWuhan
Period7/25/187/27/18

Fingerprint

Extreme Learning Machine
Learning systems
Electroencephalography
Standard deviation
Discrete wavelet transforms
Quartile
Epilepsy
Support vector machines
Computational complexity
Feature Vector
Wavelet Transform
Support Vector Machine
Computational Complexity
Wavelets
Electroencephalogram

All Science Journal Classification (ASJC) codes

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

Cite this

Qin, Y., Han, C., Lu, M., Wang, R., Yang, L., & Che, Y. (2018). Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature. In X. Chen, & Q. Zhao (Eds.), Proceedings of the 37th Chinese Control Conference, CCC 2018 (pp. 4430-4433). [8483638] (Chinese Control Conference, CCC; Vol. 2018-July). IEEE Computer Society. https://doi.org/10.23919/ChiCC.2018.8483638
Qin, Yingmei ; Han, Chunxiao ; Lu, Meili ; Wang, Ruofan ; Yang, Li ; Che, Yanqiu. / Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature. Proceedings of the 37th Chinese Control Conference, CCC 2018. editor / Xin Chen ; Qianchuan Zhao. IEEE Computer Society, 2018. pp. 4430-4433 (Chinese Control Conference, CCC).
@inproceedings{a1a5558700fe45658e63f32fc8345aed,
title = "Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature",
abstract = "Automatic seizure detection is of great importance in clinical practice of epilepsy. This paper presents a classification system based on discrete wavelet transform (DWT) and the extreme learning machine (ELM) for epileptic seizure detection by distinguishing ictal and interictal electroencephalogram (EEG) signals. The original EEG signal is first decomposed by Daubechies order 4 wavelet into several sub-bands. Then, standard deviation, log of amplitude, and quartiles are calculated for the original and decomposed signals to construct feature vectors. Different combination of these features are fed into ELM and support vector machine (SVM). After comparing different combination strategies, we find that, using ELM, even with a single feature (standard deviation) from a single sub-band signal (4-8Hz), one can obtain a satisfactory classification result, which remarkably reduce the computational complexity and make the detection system more practical.",
author = "Yingmei Qin and Chunxiao Han and Meili Lu and Ruofan Wang and Li Yang and Yanqiu Che",
year = "2018",
month = "10",
day = "5",
doi = "10.23919/ChiCC.2018.8483638",
language = "English (US)",
series = "Chinese Control Conference, CCC",
publisher = "IEEE Computer Society",
pages = "4430--4433",
editor = "Xin Chen and Qianchuan Zhao",
booktitle = "Proceedings of the 37th Chinese Control Conference, CCC 2018",
address = "United States",

}

Qin, Y, Han, C, Lu, M, Wang, R, Yang, L & Che, Y 2018, Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature. in X Chen & Q Zhao (eds), Proceedings of the 37th Chinese Control Conference, CCC 2018., 8483638, Chinese Control Conference, CCC, vol. 2018-July, IEEE Computer Society, pp. 4430-4433, 37th Chinese Control Conference, CCC 2018, Wuhan, China, 7/25/18. https://doi.org/10.23919/ChiCC.2018.8483638

Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature. / Qin, Yingmei; Han, Chunxiao; Lu, Meili; Wang, Ruofan; Yang, Li; Che, Yanqiu.

Proceedings of the 37th Chinese Control Conference, CCC 2018. ed. / Xin Chen; Qianchuan Zhao. IEEE Computer Society, 2018. p. 4430-4433 8483638 (Chinese Control Conference, CCC; Vol. 2018-July).

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

TY - GEN

T1 - Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature

AU - Qin, Yingmei

AU - Han, Chunxiao

AU - Lu, Meili

AU - Wang, Ruofan

AU - Yang, Li

AU - Che, Yanqiu

PY - 2018/10/5

Y1 - 2018/10/5

N2 - Automatic seizure detection is of great importance in clinical practice of epilepsy. This paper presents a classification system based on discrete wavelet transform (DWT) and the extreme learning machine (ELM) for epileptic seizure detection by distinguishing ictal and interictal electroencephalogram (EEG) signals. The original EEG signal is first decomposed by Daubechies order 4 wavelet into several sub-bands. Then, standard deviation, log of amplitude, and quartiles are calculated for the original and decomposed signals to construct feature vectors. Different combination of these features are fed into ELM and support vector machine (SVM). After comparing different combination strategies, we find that, using ELM, even with a single feature (standard deviation) from a single sub-band signal (4-8Hz), one can obtain a satisfactory classification result, which remarkably reduce the computational complexity and make the detection system more practical.

AB - Automatic seizure detection is of great importance in clinical practice of epilepsy. This paper presents a classification system based on discrete wavelet transform (DWT) and the extreme learning machine (ELM) for epileptic seizure detection by distinguishing ictal and interictal electroencephalogram (EEG) signals. The original EEG signal is first decomposed by Daubechies order 4 wavelet into several sub-bands. Then, standard deviation, log of amplitude, and quartiles are calculated for the original and decomposed signals to construct feature vectors. Different combination of these features are fed into ELM and support vector machine (SVM). After comparing different combination strategies, we find that, using ELM, even with a single feature (standard deviation) from a single sub-band signal (4-8Hz), one can obtain a satisfactory classification result, which remarkably reduce the computational complexity and make the detection system more practical.

UR - http://www.scopus.com/inward/record.url?scp=85056080558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056080558&partnerID=8YFLogxK

U2 - 10.23919/ChiCC.2018.8483638

DO - 10.23919/ChiCC.2018.8483638

M3 - Conference contribution

AN - SCOPUS:85056080558

T3 - Chinese Control Conference, CCC

SP - 4430

EP - 4433

BT - Proceedings of the 37th Chinese Control Conference, CCC 2018

A2 - Chen, Xin

A2 - Zhao, Qianchuan

PB - IEEE Computer Society

ER -

Qin Y, Han C, Lu M, Wang R, Yang L, Che Y. Automatic Detection of Seizures Using Extreme Learning Machine with a Single Feature. In Chen X, Zhao Q, editors, Proceedings of the 37th Chinese Control Conference, CCC 2018. IEEE Computer Society. 2018. p. 4430-4433. 8483638. (Chinese Control Conference, CCC). https://doi.org/10.23919/ChiCC.2018.8483638