Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine

Yingmei Qin; Hailing Zheng; Wei Chen; Qing Qin; Chunxiao Han; Yanqiu Che

doi:10.23919/CCC50068.2020.9189578

Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine

Yingmei Qin, Hailing Zheng, Wei Chen, Qing Qin, Chunxiao Han, Yanqiu Che

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

8 Scopus citations

Abstract

Seizure prediction can allow timely preventive measures for patients with epilepsy. In this study, we propose a hybrid model consisting of convolutional neural networks (CNNs) and an extreme learning machine (ELM) to predict seizures using scalp EEG. We first covert the EEG time series on 30-s windows into 2D spectrograms using the short-time Fourier transform. Then we apply CNNs to these images to extract features automatically. Finally, we use the ELM to classify preictal and interictal segments. The proposed method achieves sensitivity of 95.85% and a false prediction rate of 0.045/h on the Boston Children's Hospital-MIT scalp EEG dataset.

Original language	English (US)
Title of host publication	Proceedings of the 39th Chinese Control Conference, CCC 2020
Editors	Jun Fu, Jian Sun
Publisher	IEEE Computer Society
Pages	7622-7625
Number of pages	4
ISBN (Electronic)	9789881563903
DOIs	https://doi.org/10.23919/CCC50068.2020.9189578
State	Published - Jul 2020
Event	39th Chinese Control Conference, CCC 2020 - Shenyang, China Duration: Jul 27 2020 → Jul 29 2020

Publication series

Name	Chinese Control Conference, CCC
Volume	2020-July
ISSN (Print)	1934-1768
ISSN (Electronic)	2161-2927

Conference

Conference	39th Chinese Control Conference, CCC 2020
Country/Territory	China
City	Shenyang
Period	7/27/20 → 7/29/20

All Science Journal Classification (ASJC) codes

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

Access to Document

10.23919/CCC50068.2020.9189578

Cite this

Qin, Y., Zheng, H., Chen, W., Qin, Q., Han, C., & Che, Y. (2020). Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine. In J. Fu, & J. Sun (Eds.), Proceedings of the 39th Chinese Control Conference, CCC 2020 (pp. 7622-7625). Article 9189578 (Chinese Control Conference, CCC; Vol. 2020-July). IEEE Computer Society. https://doi.org/10.23919/CCC50068.2020.9189578

@inproceedings{dac5361210db404aba629927607a1a4e,

title = "Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine",

abstract = "Seizure prediction can allow timely preventive measures for patients with epilepsy. In this study, we propose a hybrid model consisting of convolutional neural networks (CNNs) and an extreme learning machine (ELM) to predict seizures using scalp EEG. We first covert the EEG time series on 30-s windows into 2D spectrograms using the short-time Fourier transform. Then we apply CNNs to these images to extract features automatically. Finally, we use the ELM to classify preictal and interictal segments. The proposed method achieves sensitivity of 95.85% and a false prediction rate of 0.045/h on the Boston Children's Hospital-MIT scalp EEG dataset.",

author = "Yingmei Qin and Hailing Zheng and Wei Chen and Qing Qin and Chunxiao Han and Yanqiu Che",

note = "Publisher Copyright: {\textcopyright} 2020 Technical Committee on Control Theory, Chinese Association of Automation.; 39th Chinese Control Conference, CCC 2020 ; Conference date: 27-07-2020 Through 29-07-2020",

year = "2020",

month = jul,

doi = "10.23919/CCC50068.2020.9189578",

language = "English (US)",

series = "Chinese Control Conference, CCC",

publisher = "IEEE Computer Society",

pages = "7622--7625",

editor = "Jun Fu and Jian Sun",

booktitle = "Proceedings of the 39th Chinese Control Conference, CCC 2020",

address = "United States",

}

Qin, Y, Zheng, H, Chen, W, Qin, Q, Han, C & Che, Y 2020, Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine. in J Fu & J Sun (eds), Proceedings of the 39th Chinese Control Conference, CCC 2020., 9189578, Chinese Control Conference, CCC, vol. 2020-July, IEEE Computer Society, pp. 7622-7625, 39th Chinese Control Conference, CCC 2020, Shenyang, China, 7/27/20. https://doi.org/10.23919/CCC50068.2020.9189578

Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine. / Qin, Yingmei; Zheng, Hailing; Chen, Wei et al.
Proceedings of the 39th Chinese Control Conference, CCC 2020. ed. / Jun Fu; Jian Sun. IEEE Computer Society, 2020. p. 7622-7625 9189578 (Chinese Control Conference, CCC; Vol. 2020-July).

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

TY - GEN

T1 - Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine

AU - Qin, Yingmei

AU - Zheng, Hailing

AU - Chen, Wei

AU - Qin, Qing

AU - Han, Chunxiao

AU - Che, Yanqiu

PY - 2020/7

Y1 - 2020/7

N2 - Seizure prediction can allow timely preventive measures for patients with epilepsy. In this study, we propose a hybrid model consisting of convolutional neural networks (CNNs) and an extreme learning machine (ELM) to predict seizures using scalp EEG. We first covert the EEG time series on 30-s windows into 2D spectrograms using the short-time Fourier transform. Then we apply CNNs to these images to extract features automatically. Finally, we use the ELM to classify preictal and interictal segments. The proposed method achieves sensitivity of 95.85% and a false prediction rate of 0.045/h on the Boston Children's Hospital-MIT scalp EEG dataset.

AB - Seizure prediction can allow timely preventive measures for patients with epilepsy. In this study, we propose a hybrid model consisting of convolutional neural networks (CNNs) and an extreme learning machine (ELM) to predict seizures using scalp EEG. We first covert the EEG time series on 30-s windows into 2D spectrograms using the short-time Fourier transform. Then we apply CNNs to these images to extract features automatically. Finally, we use the ELM to classify preictal and interictal segments. The proposed method achieves sensitivity of 95.85% and a false prediction rate of 0.045/h on the Boston Children's Hospital-MIT scalp EEG dataset.

UR - http://www.scopus.com/inward/record.url?scp=85091397496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85091397496&partnerID=8YFLogxK

U2 - 10.23919/CCC50068.2020.9189578

DO - 10.23919/CCC50068.2020.9189578

M3 - Conference contribution

AN - SCOPUS:85091397496

T3 - Chinese Control Conference, CCC

SP - 7622

EP - 7625

BT - Proceedings of the 39th Chinese Control Conference, CCC 2020

A2 - Fu, Jun

A2 - Sun, Jian

PB - IEEE Computer Society

T2 - 39th Chinese Control Conference, CCC 2020

Y2 - 27 July 2020 through 29 July 2020

ER -

Qin Y, Zheng H, Chen W, Qin Q, Han C, Che Y. Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine. In Fu J, Sun J, editors, Proceedings of the 39th Chinese Control Conference, CCC 2020. IEEE Computer Society. 2020. p. 7622-7625. 9189578. (Chinese Control Conference, CCC). doi: 10.23919/CCC50068.2020.9189578

Patient-specific Seizure Prediction with Scalp EEG Using Convolutional Neural Network and Extreme Learning Machine

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this