Epileptic Seizure Prediction from EEG Signals Using Unsupervised Learning and a Polling-Based Decision Process

Carregando...
Imagem de Miniatura
Citações na Scopus
20
Tipo de produção
conferenceObject
Data de publicação
2018
Título da Revista
ISSN da Revista
Título do Volume
Editora
SPRINGER INTERNATIONAL PUBLISHING AG
Autores
KITANO, Lucas Aparecido Silva
SOUSA, Miguel Angelo Abreu
SANTOS, Sara Dereste
PIRES, Ricardo
CAMPO, Alexandre Brincalepe
Citação
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT II, v.11140, p.117-126, 2018
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Epilepsy is a central nervous system disorder defined by spontaneous seizures and may present a risk to the physical integrity of patients due to the unpredictability of the seizures. It affects millions of people worldwide and about 30% of them do not respond to anti-epileptic drugs (AEDs) treatment. Therefore, a better seizure control with seizures prediction methods can improve their quality of life. This paper presents a patient-specific method for seizure prediction using a preprocessing wavelet transform associated to the Self-Organizing Maps (SOM) unsupervised learning algorithm and a polling-based method. Only 20 min of 23 channels scalp electroencephalogram (EEG) has been selected for the training phase for each of nine patients for EEG signals from the CHB-MIT public database. The proposed method has achieved up to 98% of sensitivity, 88% of specificity and 91% of accuracy. For each subsequence of EEG data received, the system takes less than one second to estimate the patient state, regarding the possibility of an impending seizure.
Palavras-chave
Seizure prediction, Self-Organizing Maps, Polling-based decision process
Referências
  1. Alawieh H, 2016, 2016 IEEE 18 INT C E, P1
  2. Chisci L, 2010, IEEE T BIO-MED ENG, V57, P1124, DOI 10.1109/TBME.2009.2038990
  3. D'Alessandro M, 2003, IEEE T BIO-MED ENG, V50, P603, DOI 10.1109/TBME.2003.810706
  4. Elgohary S, 2016, IEEE C COMP INT BIOI, P1
  5. Goldberger AL, 2000, CIRCULATION, V101, pE215, DOI 10.1161/01.CIR.101.23.e215
  6. Haykin S. S., 2009, NEURAL NETWORKS LEAR, V3
  7. Hoyos-Osorio K, 2016, SYMP IMAG SIG PROC A
  8. Kaggle, AM EP SOC SEIZ PRED
  9. Kohonen T, 1998, NEUROCOMPUTING, V21, P1, DOI 10.1016/S0925-2312(98)00030-7
  10. Li SF, 2013, IEEE T NEUR SYS REH, V21, P880, DOI 10.1109/TNSRE.2013.2282153
  11. Liang J, 2016, 2016 IEEE INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI), P184, DOI 10.1109/ICHI.2016.27
  12. Mallat S., 1999, WAVELET TOUR SIGNAL
  13. Park Y, 2011, EPILEPSIA, V52, P1761, DOI 10.1111/j.1528-1167.2011.03138.x
  14. Parvez MZ, 2016, IEEE T NEUR SYS REH, V24, P158, DOI 10.1109/TNSRE.2015.2458982
  15. Polla M, 2009, NEURAL COMPUTING SUR
  16. Shoeb A. H., 2009, THESIS
  17. Tafreshi AK, 2008, ISSPIT: 8TH IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, P275, DOI 10.1109/ISSPIT.2008.4775729
  18. Ultsch A., 1993, INFORM CLASSIFICATIO, P307
  19. World Health Organization, EPILEPSY