Jump to ContentJump to Main Navigation
Show Summary Details
More options …

Merhof, Dorit

Biomedical Engineering / Biomedizinische Technik

Joint Journal of the German Society for Biomedical Engineering in VDE and the Austrian and Swiss Societies for Biomedical Engineering and the German Society of Biomaterials

Editor-in-Chief: Dössel, Olaf

Editorial Board: Augat, Peter / Habibović, Pamela / Haueisen, Jens / Jahnen-Dechent, Wilhelm / Jockenhoevel, Stefan / Knaup-Gregori, Petra / Leonhardt, Steffen / Plank, Gernot / Radermacher, Klaus M. / Schkommodau, Erik / Stieglitz, Thomas / Boenick, Ulrich / Jaramaz, Branislav / Kraft, Marc / Lenarz, Thomas / Lenthe, Harry / Lo, Benny / Mainardi, Luca / Micera, Silvestro / Penzel, Thomas / Robitzki, Andrea A. / Schaeffter, Tobias / Snedeker, Jess G. / Sörnmo, Leif / Sugano, Nobuhiko / Werner, Jürgen /

IMPACT FACTOR 2018: 1.007
5-year IMPACT FACTOR: 1.390

CiteScore 2018: 1.24

SCImago Journal Rank (SJR) 2018: 0.282
Source Normalized Impact per Paper (SNIP) 2018: 0.831

See all formats and pricing
More options …
Ahead of print


Volume 57 (2012)

Evaluation of potential auras in generalized epilepsy from EEG signals using deep convolutional neural networks and time-frequency representation

Hasan Polat
  • Corresponding author
  • Department of Electrical and Electronics Engineering, Mus Alparslan University, Farabi Ofisleri. Oda No: 303, 49250 Güzeltepe/Muş, Turkey
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Mehmet Ufuk Aluçlu / Mehmet Siraç Özerdem
Published Online: 2019-12-11 | DOI: https://doi.org/10.1515/bmt-2019-0098


The general uncertainty of epilepsy and its unpredictable seizures often affect badly the quality of life of people exposed to this disease. There are patients who can be considered fortunate in terms of prediction of any seizures. These are patients with epileptic auras. In this study, it was aimed to evaluate pre-seizure warning symptoms of the electroencephalography (EEG) signals by a convolutional neural network (CNN) inspired by the epileptic auras defined in the medical field. In this context, one-dimensional EEG signals were transformed into a spectrogram display form in the frequency-time domain by applying a short-time Fourier transform (STFT). Systemic changes in pre-epileptic seizure have been described by applying the CNN approach to the EEG signals represented in the image form, and the subjective EEG-Aura process has been tried to be determined for each patient. Considering all patients included in the evaluation, it was determined that the 1-min interval covering the time from the second minute to the third minute before the seizure had the highest mean and the lowest variance to determine the systematic changes before the seizure. Thus, the highest performing process is described as EEG-Aura. The average success for the EEG-Aura process was 90.38 ± 6.28%, 89.78 ± 8.34% and 90.47 ± 5.95% for accuracy, specificity and sensitivity, respectively. Through the proposed model, epilepsy patients who do not respond to medical treatment methods are expected to maintain their lives in a more comfortable and integrated way.

Keywords: deep learning; EEG; epilepsy; epileptic aura; time-frequency representation


  • [1]

    Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 2003;123:69–87.CrossrefGoogle Scholar

  • [2]

    World Health Organization. Epilepsy. [cited 2019 April 10]. Available from: http//www.who.int/mediacentre/factsheets/fs999/en/.

  • [3]

    Fisher RS, Van Emde Boas W, Blume W, Elper C, Genton P, Lee P, et al. Epileptic seizures and epilepsy: definitions proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE). Epilepsia 2005;46:470–2.PubMedCrossrefGoogle Scholar

  • [4]

    Nakken KO, Solaas MH, Kjeldsen MJ, Friis ML, Pellock JM, Corey LA. The occurrence and characteristics of auras in a large epilepsy cohort. Acta Neurol Scand 2009;119:88–93.CrossrefGoogle Scholar

  • [5]

    Van Donselaar CA, Geerts AT, Schimsheimer RJ. Usefulness of an aura for classification of a first generalized seizure. Epilepsia 1990;31:529–35.CrossrefPubMedGoogle Scholar

  • [6]

    Tokay T, Komsuoglu SS. Epileptic Auras. Dusunen Adam 2004;17:162–7.Google Scholar

  • [7]

    Tokay T, Selekler M, Komsuoglu SS. A case with gustatory aura associated complex partial epileptic seizure. Bull Clin Psychopharmacol 2004;14:213–5.Google Scholar

  • [8]

    Spencer D. Auras are frequent in patients with generalized epilepsy. Epilepsy Curr 2015;15:75–7.PubMedCrossrefGoogle Scholar

  • [9]

    Lohse A, Kjaer TW, Sabers A, Wolf P. Epileptic aura and perception of self-control. Epilepsy Behav 2015;45:191–4.PubMedCrossrefGoogle Scholar

  • [10]

    Sanei S, Chambers JA. EEG signal processing. UK: John Wiley and Sons Ltd; 2007.Google Scholar

  • [11]

    Alkan A, Koklukaya E, Subasi A. Automatic seizure detection in EEG using logistic regression and artificial neural network. J Neurosci Methods 2005;148:167–76.PubMedCrossrefGoogle Scholar

  • [12]

    Pillai J, Sperling MR. Interictal EEG and the diagnosis of epilepsy. Epilepsia 2006;47:14–22.CrossrefGoogle Scholar

  • [13]

    Khamis H, Mohamed A, Simpson S. Frequency–moment signatures: a method for automated seizure detection from scalp EEG. Clin Neurophysiol 2013;124:2317–27.CrossrefPubMedGoogle Scholar

  • [14]

    Nigam VP, Graupe D. A neural-network-based detection of epilepsy. Neurol Res 2004;26:55–60.CrossrefPubMedGoogle Scholar

  • [15]

    Mousavi SR, Niknazar M, Vahdat BV. Epileptic seizure detection using AR model on EEG signals. CIBEC 2008;2008:1–4.Google Scholar

  • [16]

    Subasi A, Gursoy I. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 2010;37:8659–66.CrossrefGoogle Scholar

  • [17]

    Zainuddin Z, Huong LK, Pauline O. On the use of wavelet neural networks in the task of epileptic seizure detection from electroencephalography signals. Procedia Comput Sci 2012;11:149–59.CrossrefGoogle Scholar

  • [18]

    Subaşı A, Erçelebi E. Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 2005;78:87–99.PubMedCrossrefGoogle Scholar

  • [19]

    Ocak H. Optimal classification of epileptic seizures in EEG using wavelet analysis and genetic algorithm. Signal Process 2008;88:1858–67.CrossrefGoogle Scholar

  • [20]

    Subaşı A. Signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 2007;32:1084–93.CrossrefGoogle Scholar

  • [21]

    Yang Y, Zhou M, Niu Y, Li C, Cao R, Wang B, et al. Epileptic seizure prediction based on permutation entropy. Front Comput Neurosci 2018; 12:55.CrossrefPubMedGoogle Scholar

  • [22]

    Schiff SJ, Colella D, Jacyna GM, Hughes E, Creekmore JW, Marshall A, et al. Brain chirps: spectrographic signatures of epileptic seizures. Clin Neurophysiol 2000;111:953–8.CrossrefPubMedGoogle Scholar

  • [23]

    Netoff T, Park Y, Parhi K. Seizure prediction using cost-sensitive support vector machine. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Minneapolis, MN, USA: IEEE; 2009:3322–5.Google Scholar

  • [24]

    Park Y, Luo L, Parhi KK, Netoff T. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 2011;52:1761–70.CrossrefPubMedGoogle Scholar

  • [25]

    Teixeira CA, Direito B, Bandarabadi M, Quyen MLV, Valderrama M, Schelter B, et al. Epileptic seizure predictors based on computational intelligence techniques: a comparative study with 278 patients. Comput Methods Programs Biomed 2017;114:324–36.Google Scholar

  • [26]

    Mormann F, Kreuz T, Rieke C, Andrzejak RG, Kraskov A, David P, et al. On the predictability of epileptic seizures. Clin Neurophysiol 2005;116:569–87.PubMedCrossrefGoogle Scholar

  • [27]

    Gadhoumi K, Lina JM, Gotman J. Seizure prediction in patients with mesial temporal lobe epilepsy using EEG measures of state similarity. Clin Neurophysiol 2013;124:1745–54.PubMedCrossrefGoogle Scholar

  • [28]

    Chisci L, Mavino A, Perferi G, Sciandrone M, Anile C, Colicchio G, et al. Real-time epileptic seizure prediction using AR models and support vector machines. IEEE Trans Biomed Eng 2010;57:1124–32.PubMedCrossrefGoogle Scholar

  • [29]

    Assi EB, Nguyen DK, Rihana S, Sawan M. Towards accurate prediction of epileptic seizures: a review. Biomed Signal Process Control 2017;34:144–57.CrossrefGoogle Scholar

  • [30]

    Lehnertz K, Andrzejak RG, Arnhold J, Kreuz T, Mormann F, Rieke C, et al. Nonlinear EEG analysis in epilepsy: its possible use for interictal focus localization, seizure anticipation, and prevention. J Clin Neurophysiol 2001;18:209–22.PubMedCrossrefGoogle Scholar

  • [31]

    Whittaker RG. Video telemetry: current concepts and recent advances. Pract Neurol 2015;15:445–50.PubMedCrossrefGoogle Scholar

  • [32]

    Villanueva V, Gutierrez A, Garcia M, Beltran A, Palau J, Conde R, et al. Usefulness of video-EEG monitoring in patients with drug-resistant epilepsy. Neurologia 2011;26:6–12.PubMedGoogle Scholar

  • [33]

    Vale-Cardoso AS, Guimaraes HN. The effect of 50/60 Hz notch filter application on human and rat ECG recordings. Physiol Meas 2010;31:45–58.PubMedCrossrefGoogle Scholar

  • [34]

    Liu Y, Guo XM, Wu X, Li P, Wang WW. Clinical analysis of partial epilepsy with auras. Chin Med J (Engl) 2017;130:318–22.CrossrefPubMedGoogle Scholar

  • [35]

    Zhang J, Li S, Yin Z. Pattern classification of instantaneous mental workload using ensemble of convolutional neural networks. IFAC-Papers Online 2017;50:14896–901.CrossrefGoogle Scholar

  • [36]

    Yuan L, Cao J. Patients’ EEG data analysis via spectrogram image with a convolution neural network. Intell Decis Technol 2017;72:13–21.Google Scholar

  • [37]

    Guawan AAS, Surya K, Meiliana. Brainwave classification of visual stimuli based on low cost EEG spectrogram using DenseNet. Procedia Comput Sci 2018;135:128–39.CrossrefGoogle Scholar

  • [38]

    Lampert TA, O’Keefe SEM. A survey of spectrogram track detection algorithms. Appl Acoust 2010;71:87–100.CrossrefGoogle Scholar

  • [39]

    Başar E, Eroglu C, Karaka S, Schurmann M. Brain oscillations in perception and memory. Int J Psychophysiol 2000;35:95–124.CrossrefPubMedGoogle Scholar

  • [40]

    Crespel A, Gélisse P, Bureau M, Genton P. Atlas of electroencephalography. 3rd ed. Paris: J Libbey Eurotext; 2006.Google Scholar

  • [41]

    Arel I, Rose D, Karnowski T. Deep machine learning – a new frontier in artificial intelligence research. IEEE Comput Intell M 2010;5:13–8.CrossrefGoogle Scholar

  • [42]

    Fayek HM, Margaret L, Lawrence C. Evaluating deep learning architectures for speech emotion recognition. Neural Netw 2017;92:60–8.CrossrefPubMedGoogle Scholar

  • [43]

    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 2017;100:270–8.PubMedGoogle Scholar

  • [44]

    Bernal J, Kushibar K, Asfaw DS, Valverde S, Oliver A, Marti R, et al. Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review. Artif Intell Med 2019;95:64–81.CrossrefPubMedGoogle Scholar

  • [45]

    Boureau Y, Bach F, LeCun Y, Ponce J. Learning mid-level features for recognition. In: CVPR, 2010.Google Scholar

  • [46]

    LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436–44.PubMedCrossrefGoogle Scholar

  • [47]

    Asadi-Pooya AA, Nei M, Sharan A, Sperling MR. Auras in patients with temporal lobe epilepsy and mesial temporal sclerosis. J Neurol Sci 2016;364:24–6.PubMedCrossrefGoogle Scholar

  • [48]

    Schulz R, Luders HO, Hoppe M, Jokeit H, Moch A, TuxhornI, et al. Lack of aura experience correlates with bitemporal dysfunction in mesial temporal lobe epilepsy. Epilepsy Res 2001;43:201–10.CrossrefPubMedGoogle Scholar

  • [49]

    Bianchi MT, Dworetzky BA, Bromfield EB. Auditory auras in patients with postencephalitic epilepsy: case series. Epilepsy Behav 2009;14:250–2.CrossrefPubMedGoogle Scholar

  • [50]

    Hatipoglu N, Bilgin G. Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships. Med Biol Eng Comput 2017;55:1829–48.PubMedCrossrefGoogle Scholar

  • [51]

    Parihar AS. A study on brain tumor segmentation using convolution neural network. Inventive Computing and Informatics (ICICI). International Conference on IEEE 2017;2017:198–201.Google Scholar

  • [52]

    Tan JH, Acharya UR, Bhandary SV, Chua KC, Sivaprasad S. Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. J Comput Sci 2017;20:70–9.CrossrefGoogle Scholar

  • [53]

    Kim SK, Kang HB. An analysis of smartphone overuse recognition in terms of emotions using brainwaves and deep learning. Neurocomputing 2018;275:1393–406.CrossrefGoogle Scholar

  • [54]

    Tabar YR, Halici U. A novel deep learning approach for classification of EEG motor imagery signals. J Neural Eng 2017;14:016003.PubMedCrossrefGoogle Scholar

  • [55]

    Ayinala M, Parhi KK. Low complexity algorithm for seizure prediction using Adaboost. Conf Proc IEEE Eng Med Biol Soc. 2012;1061–1064.PubMedGoogle Scholar

  • [56]

    Bandarabadi M, Teixeira CA, Rasekhi J, Dourado A. Epileptic seizure prediction using relative spectral power features. Clin Neurophysiol 2015;126:237–48.PubMedCrossrefGoogle Scholar

  • [57]

    Abdel-Mannan O, Taylor H, Donner EJ, Sutcliffe AG. A systematic review of sudden unexpected death in epilepsy (SUDEP) in childhood. Epilepsy Behav 2019;90:99–106.PubMedCrossrefGoogle Scholar

  • [58]

    Tekin B. Epilepsy, pregnancy, and antiepileptic drugs. Epilepsy 2018;24:41–3.Google Scholar

  • [59]

    Kwan P, Brodie MJ. Early identification of refractory epilepsy. N Eng J Med 2000;342:314–9.CrossrefGoogle Scholar

  • [60]

    Donner EJ, Camfield P, Brooks L, Buchhalter J, Camfield C, Loddenkemper T, et al. Understanding death in children with epilepsy. Pediatr Neurol 2017;70:7–15.PubMedCrossrefGoogle Scholar

  • [61]

    Manolis TA, Manolis AA, Melita H, Manolis AS. Sudden unexpected death in epilepsy: the neuro-cardio-respiratory connection. Seizure 2018;64:65–73.PubMedGoogle Scholar

About the article

Received: 2019-04-27

Accepted: 2019-10-07

Published Online: 2019-12-11

Author statement

Research funding: Authors state no funding involved.

Conflict of interest: Authors declare no conflict of interest.

Informed Consent: Informed consent has been obtained from all patients by the Neurology Department of Dicle University.

Ethical approval: The research related to human use complied with all the relevant national regulations and institutional policies and was performed in accordance with the tenets of the Helsinki Declaration, and has been approved by the authors’ institutional review board.

Citation Information: Biomedical Engineering / Biomedizinische Technik, 20190098, ISSN (Online) 1862-278X, ISSN (Print) 0013-5585, DOI: https://doi.org/10.1515/bmt-2019-0098.

Export Citation

©2019 Walter de Gruyter GmbH, Berlin/Boston.Get Permission

Comments (0)

Please log in or register to comment.
Log in