Wavelet Analysis Applied on EEG Signals for Identification of Preictal States in Epileptic Patients / Análise wavelet aplicada em sinais de EEG para identificação de estados pré-letais em pacientes epilépticos

Jade Barbosa Kill, Patrick Marques Ciarelli, Klaus Fabian Côco, Mariane Lima de Souza


The discrimination of the interictal and preictal states in epilepsy contributes to the construction of an efficient system of seizure prediction. Here, we performed the classification of the interictal and preictal states for EEG signals of the scalp. The energies of the levels obtained by the signal decomposition of the Wavelet Discrete Transform were used as features for classification. The kNN and SVM classifiers were used in the analysis of the individual EEG channels, which gave indications that the occipital lobe region channels are the most relevant to differentiate between the interictal and preictal states. Using these channels, the classification into two states achieved accuracy of 97.29%, sensitivity of 96.25% and specificity of 98.33%. In addition, the different frequency ranges obtained by Wavelet for the classification were analyzed, and it was observed that the range of 32 Hz to 128 Hz presented greater relevance in the task.


Epilepsy; Electroencephalogram; Wavelet; Prediction; Preictal; Interictal.

Texto completo:



Adur, R. (2008). Biomedical signal processing system: Electroencephalogram teaching module. Thesis (Master's degree). Florianópolis, SC.

Alotaiby, T.; El-Samie, F. E. A.; Alshebeili, S. A.; Ahmad, I. (2015). A review of channel selection algorithms for eeg signal processing. EURASIP Journal on Advances in Signal Processing, Springer, v. 2015, n. 1, p. 66–87.

Burges, C. J.c. (1998). A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining And Knowledge Discovery, v. 2, p.121-167.

Büyükçakir, B.; Elmaz, F.; Mutlu, A. Y. (2020). Hilbert vibration decomposition-based epileptic seizure prediction with neural network. Computers in Biology and Medicine, Elsevier, p. 103665–103680.

CHB-MIT. CHB-MIT Scalp EEG Database. 2010. Available at: .

Chu, H. et al. (2017). Predicting epileptic seizures from scalp EEG based on attractor state analysis. Computer Methods And Programs In Biomedicine, v. 143, p.75-87.

Cover, T., Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, v. 13, p. 21–27.

Costa, F.; Souza, B.; Brito, N.; Silva, K. (2010). Discrete wavelet transform applied to the diagnosis of disorders. Simpósio Brasileiro de Sistemas Elétricos-SBSE, p. 94–99.

Epilepsy Foundation of America (2019). Interictal Problems. Available at: .

Faust, O. et al. (2015). Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. Seizure, v. 26, p.56-64.

Fisher, R. S. et al. (2005). Epileptic seizures and epilepsy: definitions proposed by the international leagueagainst epilepsy (ilae) and the international bureau for epilepsy (ibe). Epilepsia, WileyOnline Library, v. 46, n. 4, p. 470–472.

Freestone, D.R., Karoly, P.J., Cook, M.J. (2017). A forward- looking review of seizure prediction. Current Opinion In Neurology, v. 30, p.167-173.

Gadhoumi, K., Lina, J., Gotman, J. (2012). Discriminating preictal and interictal states in patients with temporal lobe epilepsy using wavelet analysis of intracerebral EEG. Clinical Neurophysiology, v. 123, p.1906-1916.

Gomes, M. da M. Physiological bases of the electroencephalogram. Brazilian Journal of Neurology, v. 51, n. 1, p. 12–17, 2015.

Gubner, J. A., Chang, W. (1995). Wavelet transforms for discrete-time periodic signals. Signal Processing, v. 42, p.167-180.

Kaleem, M., Guergachi, A., Krishnan, S. (2018). Patient- specific seizure detection in long-term EEG using wavelet decomposition. Biomedical Signal Processing And Control, v. 46, p.157-165.

Kanashiro, A. L. A. N. (2006). Epilepsia: prevalência, características epidemiológicas e lacuna de tratamento farmacológico. PhD thesis — Faculdade de Ciências Médicas da Universidade Estadual de Campinas. Available in: .

Kang, Yumei; Liu, Hongyuan; Aziz, Md Maniruzzaman A.; Kassim, Khairul Anuar (2019). A wavelet transform method for studying the energy distribution characteristics of microseismicities associated rock failure. Journal Of Traffic And Transportation Engineering (english Edition), v. 6, n. 6, p. 631-646.

Khan, Y., Gotman, J. (2003). Wavelet based automatic seizure detection inintracerebral electroencephalogram. Clinical Neurophysiology, v. 114, p.898-908.

Kiral-Kornek, I. et al. (2018) Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System. Ebiomedicine, v. 27, p.103-111.

Kocadagli, O., Langari, R. (2017). Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations. Expert Systems With Applications, v. 88, p.419-434.

Kohavi, R. (1995). A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. Proceedings of the 14th International Joint Conference on Artificial Intelligence, v. 2, p. 1137-1145.

Li, M., Chen, W., Zhang, T. (2017). Classification of epilepsy EEG signals using DWT-based envelope analysis and neural network ensemble. Biomedical Signal Processing And Control, v. 31, p.357-365.

Meisel, C.; Loddenkemper, T. (2019). Seizure prediction and intervention. Neuropharmacology, Elsevier, p. 107898–107906.

Michel, C. M.; Koenig, T. (2018). Eeg microstates as a tool for studying the temporaldynamics of whole-brain neuronal networks: a review.Neuroimage, Elsevier, v. 180, p.577–593, 2018.

Mormann, F. et al. (2007) Seizure prediction: the long and winding road. Brain, v. 130, p.314-333.

Morrish, P.; Duncan, S.; Cock, H. (2019). Epilepsy deaths: Learning from health servicedelivery and trying to reduce risk.Epilepsy&Behavior, Elsevier, p. 106473–106481.

Mula, M., Monaco, F. (2011). Ictal and Peri-Ictal Psychopathology. Behavioural Neurology. 24(1): 21–25.

Richhariya, B., Tanveer, M. (2018). EEG signal classification using universum support vector machine. Expert Systems With Applications, v. 106, p.169-182.

Saab, M.e.; Gotman, J. (2005). A system to detect the onset of epileptic seizures in scalp EEG. Clinical Neurophysiology, v. 116, p.427-442.

Sayeid, M.I.E. et. al. (2016). Statistical analysis of EEG signals in wavelet domain for efficient seizure prediction, American Journal of Biomedical Engineering, v. 6, p. 32-41.

Sharif, B., Jafari, A.H. Prediction of epileptic seizures from EEG using analysis of ictal rules on Poincaré plane. (2017). Computer Methods and Programs in Biomedicine, v. 145, p.11-22.

Shoeb, A. et al. (2004). Patient-specific seizure onset detection. Epilepsy & Behavior, v. 5, p.483-498.

Shoeb, A. (2009) Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. PhD Thesis of Massachusetts Institute of Technology, p.1-162.

Song, Y., Zhang, J. (2016). Discriminating preictal and interictal brain states in intracranial EEG by sample entropy and extreme learning machine. Journal Of Neuroscience Methods, v. 257, p.45-54.

Sun, Z., Shi, L. and Zhou, Y.-H. (2014). Relaxing CFL limit of FDTD by DWT. Electronics Letters, v. 50, p. 486–488.

Truong, N.D. et al. (2018). Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Networks, v. 105, p.104- 111.

Tsiouris, Κ. Μ. et al. (2018). A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals. Computers In Biology And Medicine, v. 99, p.24-37.

Usman, S.M., Usman, M., Fong, S. (2017). Epileptic Seizures Prediction Using Machine Learning Methods. Computational and Mathematical Methods in Medicine, v. 2017, p.1-10.

Williamson, J.R. et al. (2012). Seizure prediction using EEG spatiotemporal correlation structure. Epilepsy & Behavior, v. 25, p.230-238.

WHO - World Health Organization. (2019). Epilepsy. Available at: https://www.who.int/news-room/fact- sheets/detail/epilepsy (accessed 4 April 2019).

Yalçin, A. D., Kaymaz, A., Forta, H. (2000). Reflex occipital lobe epilepsy. Seizure, v. 9, p.436-441.

DOI: https://doi.org/10.34115/basrv4n3-079


  • Não há apontamentos.