A Convolutional Gated Recurrent Neural Network for Epileptic Seizure Prediction

被引：29

作者：

Affes, Abir ^{[1
]}

Mdhaffar, Afef ^{[1
,2
]}

Triki, Chahnez ^{[3
]}

Jmaiel, Mohamed ^{[1
,2
]}

Freisleben, Bernd ^{[4
]}

机构：

[1] Univ Sfax, ReDCAD Lab, ENIS, BP 1173, Sfax, Tunisia

[2] Digital Res Ctr Sfax, Sfax 3021, Tunisia

[3] Hosp Hedi Chaker, Dept Child Neurol, Sfax 3029, Tunisia

[4] Philipps Univ Marburg, Dept Math & Comp Sci, Marburg, Germany

来源：

HOW AI IMPACTS URBAN LIVING AND PUBLIC HEALTH, ICOST 2019 | 2019年 / 11862卷

关键词：

Epilepsy; Elecroencephalogram; Spectrogram; STFT; CNN; GRU; Seizure prediction; INTERNATIONAL-LEAGUE; ILAE;

D O I：

10.1007/978-3-030-32785-9_8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a convolutional gated recurrent neural network (CGRNN) to predict epileptic seizures based on features extracted from EEG data that represent the temporal aspect and the frequency aspect of the signal. Using a dataset collected in the Children's Hospital of Boston, CGRNN can predict epileptic seizures between 35 min and 5 min in advance. Our experimental results indicate that the performance of CGRNN varies between patients. We achieve an average sensitivity of 89% and a mean accuracy of 75.6% for the patients in the data set, with a mean False Positive Rate (FPR) of 1.6 per hour.

引用

页码：85 / 96

页数：12

共 22 条

[1]

[Anonymous], 2018, ARXIV180200308

[2]

Bashivan P., 2016, 4 INT C LEARN REPR I

[3]

Choi G., 2019, 2019 IEEE INT C CONS, P1

[4] Operational classification of seizure types by the International League Against Epilepsy: Position Paper of the ILAE Commission for Classification and Terminology [J].

Fisher, Robert S. ;

Cross, J. Helen ;

French, Jacqueline A. ;

Higurashi, Norimichi ;

Hirsch, Edouard ;

Jansen, Floor E. ;

Lagae, Lieven ;

Moshe, Solomon L. ;

Peltola, Jukka ;

Roulet Perez, Eliane ;

Scheffer, Ingrid E. ;

Zuberi, Sameer M. .

EPILEPSIA, 2017, 58 (04) :522-530

[5] Epileptic seizures and epilepsy: Definitions proposed by the International League against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) [J].

Fisher, RS ;

Boas, WV ;

Blume, W ;

Elger, C ;

Genton, P ;

Lee, P ;

Engel, J .

EPILEPSIA, 2005, 46 (04) :470-472

[6]

Fukumori K, 2019, INT CONF ACOUST SPEE, P2772, DOI [10.1109/ICASSP.2019.8682196, 10.1109/icassp.2019.8682196]

[7] PhysioBank, PhysioToolkit, and PhysioNet - Components of a new research resource for complex physiologic signals [J].

Goldberger, AL ;

Amaral, LAN ;

Glass, L ;

Hausdorff, JM ;

Ivanov, PC ;

Mark, RG ;

Mietus, JE ;

Moody, GB ;

Peng, CK ;

Stanley, HE .

CIRCULATION, 2000, 101 (23) :E215-E220

[8]

Golmohammadi M, 2017, ROUTL STUD NEW MEDIA

[9] On the Class Imbalance Problem [J].

Guo, Xinjian ;

Yin, Yilong ;

Dong, Cailing ;

Yang, Gongping ;

Zhou, Guangtong .

ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 4, PROCEEDINGS, 2008, :192-201

[10]

Hosseini MP, 2016, IEEE GLOB CONF SIG, P1151, DOI 10.1109/GlobalSIP.2016.7906022

← 1 2 3 →