Epileptic Seizure Prediction Using CSP and LDA for Scalp EEG Signals

Computational Intelligence and Neuroscience - Tập 2017 - Trang 1-11 - 2017
Turky N. Alotaiby1, Saleh A. Alshebeili2, Faisal M. Alotaibi1, Saud R. Alrshoud1
1KACST, Riyadh, Saudi Arabia
2KACST-TIC in Radio Frequency and Photonics for the e-Society (RFTONICS), Electrical Engineering Department, King Saud University, Riyadh, Saudi Arabia

Tóm tắt

This paper presents a patient-specific epileptic seizure predication method relying on the common spatial pattern- (CSP-) based feature extraction of scalp electroencephalogram (sEEG) signals. Multichannel EEG signals are traced and segmented into overlapping segments for both preictal and interictal intervals. The features extracted using CSP are used for training a linear discriminant analysis classifier, which is then employed in the testing phase. A leave-one-out cross-validation strategy is adopted in the experiments. The experimental results for seizure prediction obtained from the records of 24 patients from the CHB-MIT database reveal that the proposed predictor can achieve an average sensitivity of 0.89, an average false prediction rate of 0.39, and an average prediction time of 68.71 minutes using a 120-minute prediction horizon.

Từ khóa


Tài liệu tham khảo

2000

10.1016/S1474-4422(02)00003-0

2003, IEEE Engineering in Medicine and Biology Magazine, 22, 57

10.1016/j.yebeh.2010.05.008

10.1016/S0920-1211(00)00126-1

2004

2014

1998, Journal of Nuclear Medicine, 39, 978

10.3171/jns.1997.86.2.0226

10.1111/j.1528-1157.1999.tb02030.x

10.1093/brain/awp017

10.1093/brain/awh533

10.1007/BF02345960

10.1016/S0165-1838(99)00044-2

1975, Electroencephalography and Clinical Neurophysiology, 39, 435

10.1109/TBME.2012.2237399

10.1016/j.clinph.2012.01.014

10.1109/TNSRE.2013.2282153

10.1142/S0129065716500465

10.1142/S0218127416501868

10.1007/BF00335153

10.1007/BF02524422

10.1016/j.clinph.2013.09.047

10.1016/j.yebeh.2012.07.007

10.1016/j.eplepsyres.2010.07.014

10.1097/00004691-200612000-00003

10.1016/j.bspc.2012.12.001

10.1016/j.clinph.2004.10.013

10.1016/j.eplepsyres.2005.03.009

2004, Mathematical Programming, 101, 365

10.1046/j.1460-9568.1998.00090.x

10.1016/j.clinph.2004.08.025

10.1109/TBME.2009.2038990

10.1016/j.clinph.2013.04.006

10.1109/TKDE.2013.151

10.1007/978-3-540-85565-1_35

10.1016/j.clinph.2014.05.022

10.1142/S0129065715500288

10.3389/fnhum.2016.00080

10.1111/j.1528-1167.2011.03138.x

10.1371/journal.pone.0099334

10.1016/j.clinph.2009.09.002

10.1016/j.jneumeth.2014.05.019

10.1142/S012906571750006X

10.1016/j.cmpb.2017.03.002

10.1016/j.clinph.2013.10.051

10.1186/1687-6180-2014-183

10.1016/j.jneumeth.2015.06.010

10.1016/j.bspc.2017.02.001

10.1109/TBME.2012.2188799

10.1109/TPAMI.2014.2330598

10.1109/TBME.2014.2358536

10.1016/j.yebeh.2015.06.002

10.1007/BF01129656

10.1016/0013-4694(94)90119-8

10.1109/tbme.2010.2082539

2005, 3

10.1109/tkde.2008.239

10.1145/1007730.1007733

10.1093/brain/awl241