ABSTRACT
Epilepsy is a common brain disease, which can be predicted in advance by some methods. In this study, the epileptic EEG signal is processed by two-dimensional discrete wavelet transform. A algorithm of epileptic seizure prediction based on deep network transfer learning methods is proposed. The segments of EEG data containing epileptic seizure signals are grouped according to the ten-fold-cross validation methods. On the basis of classification by deep network transfer methods, combined with SPH/SOP rules and Kalman filtering algorithm, seizure prediction is carried out. The experimental results show that the longest prediction time is 24.25 minutes, the average prediction time is 18.50 minutes, the average SSP is 88.21%, and the average FPRmax is 0.31/h. The results of proposed approach show that the algorithm can accuracy predict epileptic seizures.
- Yang Zheng, Gang Wang, Kuo Li, Epileptic seizure prediction using phase synchronization based on bivariate empirical mode decomposition[J]. Clinical Neurophysiology, 2013, 1388: 2457.Google Scholar
- Haidar Khan, Lara Marcuse, Madeline Fields, . Focal onset seizure prediction using convolutional networks[J].Transactions on Biomedical Engineering, 2017, 0018-9294.Google Scholar
- Hisham Daoud, Magdy Bayoumi.Efficient Epileptic Seizure Prediction based on Deep Learning[J].Transactions on Biomedical Circuits and Systems, 2019, 1932 : 4545.Google Scholar
- Sriram Ramgopal, Sigride Thome-Souza, Michele Jackson,et al.Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy[J]. Epilepsy & Behavior, 2014, 291: 307.Google Scholar
- Thomas Maiwald, Matthias Winterhalder, Richard Aschenbrenner-Scheibe .Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic[J].Physica D, 2004, 357: 368.Google Scholar
- Ramy Hussein , Soojin Lee, Rabab Ward , .Semi-dilated convolutional neural networks for epileptic seizure prediction[J]. Neural Networks, 2021, 212:222.Google Scholar
- Krizhevsky, A., Sutskever, I., & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012, 25:1097–1105.Google ScholarDigital Library
- Khakon Das , Debashis Daschakladar, Partha Pratim Roy, . Epileptic seizure prediction by the detection of seizure waveform from the pre-ictal phase of EEG signal[J].Biomedical Signal Processing and Control, 2020, 57:101720.Google ScholarCross Ref
- Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.Google Scholar
- M. Ihle , “EPILEPSIAE - A European epilepsy database,” Computer Methods and Programs in Biomedicine, vol. 106, no. 3, pp. 127– 138, 2012Google ScholarDigital Library
- Wenbin Hu,Jiuwen Cao ,Xiaoping Lai,Junbiao Liu.Mean amplitude spectrum based epileptic state classification for seizure prediction using convolutional neural networks[J].Journal of Ambient Intelligence and Humanized Computing, 2019, https://doi.org/10.1007/s12652-019-01220-6Google ScholarCross Ref
- Williamson JR, Bliss DW, Browne DW (2011) Epileptic seizure prediction using the spatiotemporal correlation structure of intracranial EEG. In: Acoustics, speech and signal processing (ICASSP), pp 665-668Google ScholarCross Ref
- Song J, Zhang R (2017) Application of extreme learning machine to epileptic seizure detection based on lagged Poincaŕ e plots. Multidimens Syst Signal Process 28(3):945–959Google Scholar
- Gadhoumi K, Lina JM, Gotman J (2012) Discriminating preictal and interictal states in patients with temporal lobe epilepsy using wavelet analysis of intracerebral eeg. Clin Neurophysiol Of J Int Federat Clin Neurophysiol 123(10):1906–1916Google Scholar
- Liang Z, Bai Y, Ren Y, Li X (2016) Synchronization measures in EEG signals. Springer, Singapore, pp 167–202. https://doi.org/10.1007/978-981-10-1822-0_9Google ScholarCross Ref
- Dong W, Doutian R, Kuo L, Epileptic seizure detection in long-term EEG recordings by using wavelet-based directed transfer function[J]. IEEE transactions on bio-medical engineering, 2018, 65(11): 2591-2599.Google Scholar
- Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning[C]. Proceedings of the AAAIGoogle Scholar
- Namazi H, Kulish VV, Hussaini J, Hussaini J, Delaviz A, Delaviz F, Habibi S, Ramezanpoor S (2015) A signal processing based analysis and prediction of seizure onset in patients with epilepsy. Oncotarget 7(1):342–35Google Scholar
Index Terms
- Epileptic Seizure Prediction Using Deep Network with Transfer Learning
Recommendations
Semi-dilated convolutional neural networks for epileptic seizure prediction
AbstractEpilepsy is a neurological brain disorder that affects ∼75 million people worldwide. Predicting epileptic seizures holds great potential for improving the quality of life of people with epilepsy, but seizure prediction solely from the ...
Prediction of epileptic seizures using fNIRS and machine learning
Research to predict epileptic seizures has been mainly focused on the analysis of electroencephalography (EEG) signals; however, recent research efforts have encouraged the use of a relatively new optical signal modality, called functional Near-Infrared ...
A lightweight solution to epileptic seizure prediction based on EEG synchronization measurement
AbstractIt is critical to determine whether the brain state of an epilepsy patient is indicative of a possible seizure onset; thus, appropriate therapy or alarm may be delivered in time. Successful seizure prediction relies on the capability of accurately ...
Comments