{"title":"From Electroencephalogram to Epileptic Seizures Detection by Using Artificial Neural Networks","authors":"Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone","volume":152,"journal":"International Journal of Health and Medical Engineering","pagesStart":359,"pagesEnd":366,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10010656","abstract":"
Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.<\/p>\r\n","references":"[1]\tWorld Health Organization, 2018, http:\/\/www.who.int\/news-room\/fact-sheets\/detail\/epilepsy.\r\n[2]\tC. E. Elger and C. Hoppe, \u201cDiagnostic challenges in epilepsy: seizure under-reporting and seizure detection,\u201d Lancet Neurol, 2018 Mar, 17(3), pp. 279-288.\r\n[3]\tAmerican Clinical Neurophysiology Society. Guideline twelve: guidelines for long-term monitoring for epilepsy, Journal of Clinical Neurophysiology, Vol. 25, N. 3, June 2008.\r\n[4]\tR. K. Maganti and P. Rutecki, \u201cEEG and epilepsy monitoring,\u201d Continuum (Minneap Minn), 2013 Jun, 19 (3 Epilepsy), pp. 598-622.\r\n[5]\tY. Li et al, \u201cEpileptic Seizure Detection Based on Time-Frequency Images of EEG Signals Using Gaussian Mixture Model and Gray Level Co-Occurrence Matrix Features,\u201d Int J Neural Syst., 2018, 28(7).\r\n[6]\tA. \u015eeng\u00fcr, Y. Guo, and Y. Akbulut, \u201cTime-frequency texture descriptors of EEG signals for efficient detection of epileptic seizure,\u201d Brain Inform 3(2), 2016, pp. 101-108.\r\n[7]\tY. Li et al., \u201cEpileptic Seizure Classification of EEGs Using Time-Frequency Analysis Based Multiscale Radial Basis Functions,\u201d IEEE J Bio. Health Inf. 22(2), 2017, pp. 386-397.\r\n[8]\tS. Raghu, N. Sriraam, G.P. Kumar, and A. S. Hegde, \u201cA Novel Approach for Real-Time Recognition of Epileptic Seizures Using Minimum Variance Modified Fuzzy Entropy,\u201d IEEE Trans Biomed Eng 65(11), 2018, pp. 2612-2621.\r\n[9]\tS. Raghu S, N. Sriraam N, and G. P. Kumar, \u201cClassification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier,\u201d Cogn Neurodyn, 11(1), 2017, pp. 51-66.\r\n[10]\tA. Sharmila, P. Mahalakshmi, \u201cWavelet-based feature extraction for classification of epileptic seizure EEG signal,\u201d J Med Eng Technol. 41(8), 2017, pp. 670-680.\r\n[11]\tQ. Yuan et al., \u201cEpileptic seizure detection based on imbalanced classification and wavelet packet transform,\u201d Seizure 50, 2017, pp. 99-108.\r\n[12]\tN. Mahmoodian, A. Boese, M. Friebe, and J. Haddadnia, \u201cEpileptic seizure detection using cross-bispectrum of electroencephalogram signal,\u201d Seizure 66, 2019, pp. 4-11.\r\n[13]\tG. Ouyang, X. Li, C. Dang, and D. A. Richards, \u201cUsing recurrence plot for determinism analysis of EEG recordings in genetic absence epilepsy rats,\u201d Clin Neurophys. 119, 2008, pp. 1747-1755.\r\n[14]\tA. Emami et al., \u201cSeizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images,\u201d Neuroimage Clin. 22, 101684, 2019.\r\n[15]\tA. H. Ansari et al., \u201cNeonatal Seizure Detection Using Deep Convolutional Neural Networks,\u201d Int J Neural Syst., 1850011, 2018.\r\n[16]\tS. Kusmakar et al., \u201cImproved Detection and Classification of Convulsive Epileptic and Psychogenic Non-epileptic Seizures Using FLDA and Bayesian Inference,\u201d Conf Proc IEEE Eng Med Biol Soc., 2018, pp. 3402-3405.\r\n[17]\tR. Hussein et al., \u201cOptimized deep neural network architecture for robust detection of epileptic seizures using EEG signals,\u201d Clin Neurophysiol 130(1), 2019, pp. 25-37.\r\n[18]\tA. Aarabi, R. Fazel-Rezai, and Y. Aghakhani, \u201cA fuzzy rule-based system for epileptic seizure detection in intracranial EEG,\u201d Clin Neurophysiol 2009, 120, pp. 1648-57.\r\n[19]\tK. T. Tapani, S. Vanhatalo, and N. J. Stevenson, \u201cTime-Varying EEG Correlations Improve Automated Neonatal Seizure Detection,\u201d Int. J. Neural Syst., 2018 Jun 24:1850030. \r\n[20]\tF. Manzouri et al., \u201cA Comparison of Machine Learning Classifiers for Energy-Efficient Implementation of Seizure Detection,\u201d Front Syst Neurosci, 2018 Sep 20; 12:43.\r\n[21]\tY. Kassahun et al., \u201cAutomatic classification of epilepsy types using ontology-based and genetics-based machine learning,\u201d Artif Intell Med, 2014 Jun, 61(2), pp. 79-88.\r\n[22]\tP. Tan, M. Steinbach, and V. Kumar, \u201cIntroduction to Data Mining\u201d, Pearson Addison Wesley, 2005.\r\n[23]\tM. Hall, et al., \u201cThe WEKA Data Mining Software: An Update\u201d, SIGKDD Explorations, Volume 11, Issue 1, 2009.\r\n[24]\tI. H. Witten and E. Frank, \u201cData Mining. Practical Machine Learning Tools and Techniques\u201d, Morgan Kaufmann, 2005.\r\n[25]\tFSPEEG Website. Seizure prediction project Freiburg, University of Freiburg. http:\/\/epilepsy.uni-freiburg.de\/freiburg-seizure-prediction-project\/eeg-database\/ (accessed 8 May 2019).\r\n[26]\tFreiburger Zentrum fur Datenanalyse und Mollbildung: The Freiburg seizure prediction project. https:\/\/epilepsy.uni-freiburg.de\/freiburg-seizure-prediction-project\/eeg-database (accessed 8 May 2019).\r\n[27]\tJ. G. Proakis and D. G. Manolakis, \u201cDigital Signal Processing,\u201d Prentice Hall (4th Edition), 2006.\r\n[28]\tM. Gentile and B. Straughan, \u201cBidispersive thermal convection,\u201d International Journal of Heat and Mass Transfer Volume 114, November 2017, pages 837-840.\r\n[29]\tJ. Gama, \u201cKnowledge Discovery from Data Streams,\u201d Chapman & Hall\/CRC, 2010.\r\n[30]\tM. Last, A. Kandel, and H. Bunke, \u201cData Mining in Time Series Databases,\u201d World Scientific Publishing Co. Pte. Ltd., 2004.\r\n[31]\tA. Martone, G. Zazzaro, and L. Pavone, \u201cA Feature Extraction Framework for Time Series Analysis. An Application for EEG Signal Processing for Epileptic Seizures Detection,\u201d The 5th Int. Conf. on Big Data, Small Data, Linked Data and Open Data, March 2019, pp. 5-13.\r\n[32]\tE. Keogh, K. Chakrabarti, M. J. Pazzani, and S. Mehrotra, \u201cDimensionality reduction for fast similarity search in large time series databases,\u201d Knowledge and Info Sys 3(3), 2001, pp. 263\u2013286.\r\n[33]\tJ. Lin, E. Keogh, S. Lonardi, and B. Chiu, \u201cA symbolic representation of time series, with implications for streaming algorithms,\u201d 8th ACM W on Research Issues in DM and KDD, 2003.\r\n[34]\tG. Luo et al., \u201cPLA - Piecewise Linear Approximation,\u201d 31st Int Conf on Data Eng, 2015.\r\n[35]\tI. Osorio, H. P. Zaveri, M. G. Frei, and S. Arthurs, \u201cEpilepsy: The Intersection of Neurosciences, Biology, Mathematics, Engineering, and Physics,\u201d in Rationales for Analogy between Earthquakes, Financial Crashes, and Epileptic Seizures, CRC Press, Taylor & Francis G, 2011.\r\n[36]\tG. Zazzaro, F. M. Pisano, and G. Romano, \u201cBayesian Networks for Earthquake Magnitude Classification in a Early Warning System,\u201d International Journal of Environmental, Chemical, Ecological, Geological and Geophysical Engineering, Vol:6 No;4, 2012.\r\n[37]\tM. Zaharia, \u201cAn Architecture for Fast and General Data Processing on Large Clusters,\u201d PhD Dissertation, 2013.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 152, 2019"}