An Advanced Machine Learning Approach to Generalised Epileptic Seizure Detection

  • Paul Fergus
  • David Hignett
  • Abir Jaffar Hussain
  • Dhiya Al-Jumeily
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8590)


Epilepsy is a chronic neurological condition that affects approximately 70 million people worldwide. Characterised by sudden bursts of excess electricity in the brain manifesting as seizures, epilepsy is still not well understood when compared with other neurological disorders. Seizures often happen unexpectedly and attempting to predict them has been a research topic for the last 20 years. Electroencephalograms have been integral to these studies, as they can capture the brain’s electrical signals. The challenge is to generalise the detection of seizures in different regions of the brain and across multiple subjects. This paper explores this idea further and presents a supervised machine learning approach that classifies seizure and non-seizure records using an open dataset containing 543 electroencephalogram segments. Our approach posits a new method for generalising seizure detection across different subjects without prior knowledge about the focal point of seizures. Our results show an improvement on existing studies with 88% for sensitivity, 88% for specificity and 93% for the area under the curve, with a 12% global error, using the k-NN classifier.


Seizure non-seizure machine learning classification Electroencephalogram oversampling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aarabi, A., Fazel-Rezai, R., Aghakhani, Y.: A Fuzzy Rule-Based System for Epileptic Seizure Detection in Intracranial EEG. Clinical Neurophysiology 2 120(9), 1648–1657 (2009)CrossRefGoogle Scholar
  2. 2.
    Abdul-Latif, A.A., Cosic, I., Kimar, D.K., Polus, B.: Power Changes of EEG Signals Associated With Muscle Fatigue: The Root Mean Square Analysis of EEG Bands. In: IEEE Proceedings of Intelligent Sensors, Sensor Networks and Information Processing Conference, pp. 531–534 (2004)Google Scholar
  3. 3.
    Carney, P.R., Myers, S., Deyer, J.D.: Seizure Prediction: Methods. Epilepsy Behaviour 22, S94–S101 (2011)Google Scholar
  4. 4.
    Diambra, L., De Figueiredo, J.C.B., Malta, C.P.: Epileptic Activity Recognition in EEG Recording. Physica A: Statical Mechanics and its Applications 273(3-4), 495–505 (1999)CrossRefGoogle Scholar
  5. 5.
    Engel, J.: Seizures and Epilepsy, p. 736 (2013)Google Scholar
  6. 6.
    Fazel, S., Wolf, A., Langstrom, N., Newton, C.R., Lichtenstein, P.: Premature Mortality in Epilepsy and the Role of Psychiatric Comorbidity: A Total Population Study. The Lancet 382(9905), 1646–1654 (2013)CrossRefGoogle Scholar
  7. 7.
    Greene, B.R., Faul, S., Marnane, W.P., Lightbody, G., Korotchikova, I., Boylan, G.B.: A Comparison of Quantitative EEG Features Fro Neonatal Seizure Detection. Clinical Neurophysiology 119(6), 1248–1261 (2008)CrossRefGoogle Scholar
  8. 8.
    Iasemidis, L.D.: Epileptic Seizure Prediction and Control. IEEE Transactions on Biomedical Engineering 50(5), 549–558 (2003)CrossRefGoogle Scholar
  9. 9.
    Kelly, K.M., Shiau, D.S., Kern, R.T., Chien, J.H., Yang, M.C.K., Yandora, K.A., Sackellares, J.C.: Assessment of a Scalp EEG-Based Automated Seizure Detection System. Clinical Neurophysiology 121(11), 1832–1843 (2010)CrossRefGoogle Scholar
  10. 10.
    Libenson, M.: Practical Approach to Electroencephalography, p. 464 (2009)Google Scholar
  11. 11.
    Maiwald, T., Winterhalder, M., Aschenbrenner-Scheibe, R., Voss, H.U., Shulze-Bonhage, A., Timmer, J.: Comparison of Three Nonlinear Seizure Prediction Methods by Means of the Seizure Prediction Characteristic. Physica D: Nonlinear Phenomena 194, 357–368 (2004)CrossRefzbMATHGoogle Scholar
  12. 12.
    Mormann, F., Andrzejak, R.G., Elgar, C.E., Lehnertz, K.: Seizure Prediction the Long and Winding Road. Brain 130, 314–333 (2007)CrossRefGoogle Scholar
  13. 13.
    Ning, W., Lyu, M.R.: Exploration of Instantaneous Amplitude and Frequency Features for Epileptic Seizure Prediction. In: 12th IEEE International Conference on Bioinformatics and Bioengineering, pp. 292–297 (2012)Google Scholar
  14. 14.
    Patel, K., Chern-Pin, C., Fau, S., Bleakley, C.J.: Low Power Real-Time Seizure Detection for Ambulatory EEG. In: 3rd International Conference on Pervasive Computing Technologies for Healthcare, pp. 1–7 (2009)Google Scholar
  15. 15.
    Sanei, S., Chambers, J.A.: EEG Signal Processing, p. 312 (2007)Google Scholar
  16. 16.
    Shoeb, A.H.: Application of Machine Learning to Epileptic Seizure Onset and Treatment (2009)Google Scholar
  17. 17.
    Van Der Heijde, F., Duin, R.P.W., De Ridder, D., Tax, D.M.J.: Classification, Parameter Estimation and State Estimation, p. 440 (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Paul Fergus
    • 1
  • David Hignett
    • 1
  • Abir Jaffar Hussain
    • 1
  • Dhiya Al-Jumeily
    • 1
  1. 1.Applied Computing Research GroupLiverpool John Moores UniversityLiverpoolUK

Personalised recommendations