Epilepsy detection in electroencephalogram using reduced convolutional neural networks
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1279Keywords:
Deep Learning, Electroencephalography, EpilepsyAbstract
Objective: Creation and comparison of deep learning models based on electroencephalogram (EEG) segments represented in time and frequency domain for the detection of epilepsy. Method: Two Convolutional Neural Network models were implemented and evaluated, each fed by electroencephalography data in different domains (time and frequency). Results: The models evaluated showed average accuracy between 73.37% and 82.08%. The model trained from EEG represented in the frequency domain achieved higher values for all metrics. By applying the Mann-Whitney U hypothesis statistical test, considering a significance level of 5%, a statistically significant difference was evidenced between the models. Conclusion: The results indicate that the model trained with EEG segments represented in frequency had promising performance in detecting epileptic seizures. Additionally, even though the architecture of the developed models is simpler compared to related works, competitive results were achieved.
References
World Health Organization. Epilepsy: a public health imperative. 2019.
Shin HW, Jewells V, Hadar E, Fisher T, Hinn A. Review of epilepsy-etiology, diagnostic evaluation and treatment. Int J Neurorehabilitation. 2014;1(130):2376-0281.
Freeman W, Quiroga RQ. Imaging brain function with EEG: advanced temporal and spatial analysis of electroencephalographic signals. Springer Science & Business Media; 2012 Oct 28.
Oliva JT, Rosa JL. Classification for EEG report generation and epilepsy detection. Neurocomputing. 2019 Mar 28;335:81-95.
Alotaiby TN, Alshebeili SA, Alshawi T, Ahmad I, Abd El-Samie FE. EEG seizure detection and prediction algorithms: a survey. Journal on Advances in Signal Processing. 2014:1-21.
Craik A, He Y, Contreras-Vidal JL. Deep learning for electroencephalogram (EEG) classification tasks: a review. Journal of neural engineering. 2019 Apr 9;16(3):031001.
Li Z, Liu F, Yang W, Peng S, Zhou J. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems. 2021 Jun 10;33(12):6999-7019.
Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation. 2019 Jul 1;31(7):1235-70.
Xu C, Zhao P, Liu Y, Xu J, S. Sheng VS, Cui Z, Zhou X, Xiong H. Recurrent convolutional neural network for sequential recommendation. In The world wide web conference 2019 (pp. 3398-3404).
Jana R, Mukherjee I. Deep learning based efficient epileptic seizure prediction with EEG channel optimization. Biomedical Signal Processing and Control. 2021 Jul 1;68:102767.
Sharan RV, Berkovsky S. Epileptic seizure detection using multi-channel EEG wavelet power spectra and 1-D convolutional neural networks. In2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 Jul 20 (pp. 545-548).
Brigham EO. The fast Fourier transform and its applications. Prentice-Hall, Inc.; 1988 Jul 1.
Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory. 1990 Sep;36(5):961-1005.
Yao X, Li X, Ye Q, Huang Y, Cheng Q, Zhang GQ. A robust deep learning approach for automatic classification of seizures against non-seizures. Biomedical Signal Processing and Control. 2021 Feb 1;64:102215.
Thodoroff P, Pineau J, Lim A. Learning robust features using deep learning for automatic seizure detection. In Machine learning for healthcare conference 2016 Dec 10 (pp. 178-190).
Guttag J. CHB-MIT Scalp EEG Database. PhysioNet. 2010. doi: 10.13026/C2K01R.
Monard MC, Baranauskas JA. Conceitos sobre aprendizado de máquina. Sistemas inteligentes-Fundamentos e aplicações. 2003;1(1):32.
Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Information processing & management. 2009 Jul 1;45(4):427-37.
Xu QS, Liang YZ. Monte Carlo cross validation. Chemometrics and Intelligent Laboratory Systems. 2001 Apr 16;56(1):1-1.
Mann HB, Whitney DR. On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics. 1947 Mar 1:50-60.
Günther F, Fritsch S. Neuralnet: training of neural networks. The R Journal. 2010 Jun 2(1):30-38.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
