A machine learning approach to epileptic seizure prediction using Electroencephalogram (EEG) Signal

• Autorzy: Savadkoohi Marzieh , Oladunni Timothy , Thompson Lara

Identyfikatory

DOI

10.1016/j.bbe.2020.07.004

• Języki publikacji: EN

Abstrakty

EN

This study investigates the properties of the brain electrical activity from different recording regions and physiological states for seizure detection. Neurophysiologists will find the work useful in the timely and accurate detection of epileptic seizures of their patients. We explored the best way to detect meaningful patterns from an epileptic Electroencephalogram (EEG). Signals used in this work are 23.6 s segments of 100 single channel surface EEG recordings collected with the sampling rate of 173.61 Hz. The recorded signals are from five healthy volunteers with eyes closed and eyes open, and intracranial EEG recordings from five epilepsy patients during the seizure-free interval as well as epileptic seizures. Feature engineering was done using; i) feature extraction of each EEG wave in time, frequency and time-frequency domains via Butterworth filter, Fourier Transform and Wavelet Transform respectively and, ii) feature selection with T-test, and Sequential Forward Floating Selection (SFFS). SVM and KNN learning algorithms were applied to classify preprocessed EEG signal. Performance comparison was based on Accuracy, Sensitivity and Specificity. Our experiments showed that SVM has a slight edge over KNN.

Słowa kluczowe

EN

electroencephalogram; epileptic seizure; k-nearest neighbors; support vector machine; time domain; frequency domain; wavelet transform

PL

elektroencefalogram; napad padaczkowy; maszyna wektorów wsparcia; transformata falkowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1328--1341
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Savadkoohi Marzieh

• School of Engineering and Applied Sciences, University of District of Columbia, Washington DC, USA

autor

Oladunni Timothy

• Department of Computer Science, University of District of Columbia, Washington DC, USA

autor

Thompson Lara

• Department of Mechanical Engineering, Biomedical Engineering Program, University of the District of Columbia, Washington DC

Bibliografia

• [1] Pannese E. Neurocytology: fine structure of neurons, nerve processes, and neuroglial cells: 2nd fully revised and updated edition. Springer International Publishing; 2015. http://dx.doi.org/10.1007/978-3-319-06856-5.
• [2] Lent R, Azevedo FAC, Andrade-Moraes CH, Pinto AVO. How many neurons do you have? Some dogmas of quantitative neuroscience under revision. Eur J Neurosci 2012;35:1–9. http://dx.doi.org/10.1111/j.1460-9568.2011.07923.x.
• [3] Abbott LF, DePasquale B, Memmesheimer RM. Building functional networks of spiking model neurons. Nat Neurosci 2016;19:350–5. http://dx.doi.org/10.1038/nn.4241.
• [4] Michel CM, Murray MM. Towards the utilization of EEG as a brain imaging tool. Neuroimage 2012;61:371–85. http://dx.doi.org/10.1016/j.neuroimage.2011.12.039.
• [5] Sharanreddy M, Kulkarni PK. Automated EEG signal analysis for identification of epilepsy seizures and brain tumour. J Med Eng Technol 2013;37:511–9. http://dx.doi.org/10.3109/03091902.2013.837530.
• [6] Spruston N. Pyramidal neurons: dendritic structure and synaptic integration. Nat Rev Neurosci 2008;9:206–21. http://dx.doi.org/10.1038/nrn2286.
• [7] Uldry L., Ferrez P.W., Millán J.D.R. (PDF) Feature Selection Methods on Distributed Linear Inverse Solutions for a Non- Invasive Brain-Machine Interface n.d. https://www. researchgate.net/publication/41387051_Feature_ Selection_Methods_on_Distributed_Linear_Inverse_ Solutions_for_a_Non-Invasive_Brain-Machine_ Interface (accessed February 2, 2020).
• [8] Adjamian P. The application of electro- and magneto- encephalography in tinnitus research-methods and interpretations. Front Neurol 2014;5. http://dx.doi.org/10.3389/fneur.2014.00228.
• [9] Strobbe G. Advanced forward models for EEG source imaging; 2014.
• [10] Fort GG, Ferri FF. Ferri's clinical advisor 2019: 5 books in 1. 1st ed. Elsevier; 2018.
• [11] Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 2003;123:69–87. http://dx.doi.org/10.1016/S0165-0270(02)00340-0.
• [12] Polat K, Günes S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl Math Comput 2007;187:1017–26. http://dx.doi.org/10.1016/j.amc.2006.09.022.
• [13] Srinivasan V, Eswaran C, Sriraam AN. Artificial neural network based epileptic detection using time-domain and frequency-domain features. J Med Syst 2005;29:647–60. http://dx.doi.org/10.1007/s10916-005-6133-1.
• [14] Übeyli ED, Güler I. Features extracted by eigenvector methods for detecting variability of EEG signals. Pattern Recognit Lett 2007;28:592–603. http://dx.doi.org/10.1016/j.patrec.2006.10.004.
• [15] Bell MA, Cuevas K. Using EEG to study cognitive development: issues and practices. J Cogn Dev 2012;13:281–94. http://dx.doi.org/10.1080/15248372.2012.691143.
• [16] Thatcher RW, Biver CJ, North DM. Z score EEG biofeedback: technical foundations; 2004.
• [17] Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Physical Review E - Statistical Physics Plasmas Fluids and Related Interdisciplinary Topics 2001;64:8. http://dx.doi.org/10.1103/PhysRevE.64.061907.
• [18] Epileptologie Bonn / Forschung / AG Lehnertz / EEG Data Download n.d. http://epileptologie-bonn.de/cms/front_ content.php?idcat=193&lang=3 (accessed February 3, 2020).
• [19] Oweis RJ, Abdulhay EW. Seizure classification in EEG signals utilizing Hilbert-Huang transform. Biomed Eng Online 2011;10:38. http://dx.doi.org/10.1186/1475-925X-10-38.
• [20] Sharma M, Pachori RB, Rajendra Acharya U. A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recognit Lett 2017;94:172–9. http://dx.doi.org/10.1016/j.patrec.2017.03.023.
• [21] Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 2018. http://dx.doi.org/10.1016/j.compbiomed.2017.09.017.
• [22] Guha A, Ghosh S, Roy A. Chatterjee S Epileptic seizure recognition using deep neural network Advances in intelligent systems and computing, vol. 937. Springer Verlag; 2020. p. 21–8. http://dx.doi.org/10.1007/978-981-13-7403-6_3.
• [23] Patidar S, Panigrahi T. Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals. Biomed Signal Process Control 2017. http://dx.doi.org/10.1016/j.bspc.2017.01.001.
• [24] Zahra A, Kanwal N, ur Rehman N, Ehsan S, McDonald- Maier KD. Seizure detection from EEG signals using multivariate empirical mode decomposition. Comput Biol Med 2017. http://dx.doi.org/10.1016/j.compbiomed.2017.07.010.
• [25] Bhattacharyya A, Pachori R, Upadhyay A, Acharya U. Tunable-q wavelet transform based multiscale entropy measure for automated classification of epileptic EEG signals. Appl Sci 2017;7:385. http://dx.doi.org/10.3390/app7040385.
• [26] Richhariya B, Tanveer M. EEG signal classification using universum support vector machine. Expert Syst Appl 2018. http://dx.doi.org/10.1016/j.eswa.2018.03.053.
• [27] Kaya D. The mRMR-CNN based influential support decision system approach to classify EEG signals. Measurement 2020. http://dx.doi.org/10.1016/j.measurement.2020.107602.
• [28] Roohi-Azizi M, Azimi L, Heysieattalab S, Aamidfar M. Changes of the brain's bioelectrical activity in cognition, consciousness, and some mental disorders. Med J Islam Repub Iran 2017;31:307–12. http://dx.doi.org/10.14196/mjiri.31.53.
• [29] Al-Fahoum AS, Al-Fraihat AA. Methods of EEG signal features extraction using linear analysis in frequency and time-frequency domains. ISRN Neurosci 2014;2014:1–7. http://dx.doi.org/10.1155/2014/730218.
• [30] Amin HU, Mumtaz W, Subhani AR, Saad MNM, Malik AS. Classification of EEG signals based on pattern recognition approach. Front Comput Neurosci 2017;11. http://dx.doi.org/10.3389/fncom.2017.00103.
• [31] Saini M, Chhikara R. Performance evaluation of DCT and DWT features for blind image steganalysis using neural networks. Int J Comput Appl 2015;114:20–3. http://dx.doi.org/10.5120/19974-1868.
• [32] Westfall PH. Kurtosis as Peakedness, 1905–2014. R.I.P. Am Stat 2014;68:191–5. http://dx.doi.org/10.1080/00031305.2014.917055.
• [33] Garrett D, Peterson DA, Anderson CW, Thaut MH. Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. Ieee Trans Neural Syst Rehabil Eng 2003;11. http://dx.doi.org/10.1109/TNSRE.2003.814441.
• [34] Sloss AN, Dominic Symes, Wright C. ARM system developer's guide : designing and optimizing system software. Elsevier/ Morgan Kaufman; 2004.
• [35] Tan L, Jiang J. Infinite impulse response filter design. Digital Signal Processing, Elsevier; 2019. p. 315–419. http://dx.doi.org/10.1016/b978-0-12-815071-9.00008-7.
• [36] Signals and Systems/Fourier Series - Wikibooks, open books for an open world n.d. https://en.wikibooks.org/wiki/Signals_ and_Systems /Fourier_Series (accessed February 3, 2020).
• [37] Weisstein EW. Fourier Series – from Wolfram MathWorld n.d. http://mathworld.wolfram.com/FourierSeries.html (accessed February 3, 2020).
• [38] Winter R. Symmetry: even, odd, real, imaginary functions: Advanced Techniques : Rudi Winter's web space n.d. http:// users.aber.ac.uk/ruw/teach/340/ft_symmetry.php (accessed February 3, 2020).
• [39] Chun-lin L. A tutorial of the wavelet transform; 2010.
• [40] Subasi A. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 2007;32:1084–93. http://dx.doi.org/10.1016/j.eswa.2006.02.005.
• [41] Hsu KC, Yu SN. Detection of seizures in EEG using subband nonlinear parameters and genetic algorithm. Comput Biol Med 2010;40:823–30. http://dx.doi.org/10.1016/j.compbiomed.2010.08.005.
• [42] Krzywinski M, Altman N. Significance, P values and t-tests. Nat Methods 2013;10:1041–2. http://dx.doi.org/10.1038/nmeth.2698.
• [43] Ostertagová E, Ostertag O, Kovác J. Methodology and application of the Kruskal-Wallis test. Appl Mech Mater 2014;611:115–20. http://dx.doi.org/10.4028/www.scientific.net/AMM.611.115.
• [44] Baker MC, Kerr AS, Hames E, Akrofi K. An SFFS technique for EEG feature classification to identify sub-groups. Proceedings - IEEE symposium on Computer-Based Medical Systems; 2012. http://dx.doi.org/10.1109/CBMS.2012.6266361.
• [45] Peng Y, Wu Z, Jiang J. A novel feature selection approach for biomedical data classification. J Biomed Inform 2010. http://dx.doi.org/10.1016/j.jbi.2009.07.008.
• 46] Sequential Feature Selector - mlxtend n.d. http://rasbt. github.io/mlxtend/user_guide/feature_selection/ SequentialFeatureSelector/#sequential-feature-selector (accessed February 20, 2020).
• [47] Hu L-Y, Huang M-W, Ke S-W, Tsai C-F. The distance function effect on k-nearest neighbor classification for medical datasets. SpringerPlus 2016;5:1304. http://dx.doi.org/10.1186/s40064-016-2941-7.
• [48] Zhang T, Chen W. LMD based features for the automatic seizure detection of EEG signals using SVM. Ieee Trans Neural Syst Rehabil Eng 2017;25:1100–8. http://dx.doi.org/10.1109/TNSRE.2016.2611601.
• [49] Hernández DE, Trujillo L, Z-Flores E, Villanueva OM, Romo- Fewell O. Detecting epilepsy in EEG signals using time, frequency and time-frequency domain features. Studies in Systems Decision and Control 2018;143:167–82. http://dx.doi.org/10.1007/978-3-319-74060-7_9.
• [50] Martis RJ, Acharya UR, Tan JH, Petznick A, Yanti R, Chua CK, et al. Application of empirical mode decomposition (EMD) for automated detection of epilepsy using EEG signals. Int J Neural Syst 2012;22. http://dx.doi.org/10.1142/S012906571250027X.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).