EEG Seizure Detection from Compressive Measurements

  • Meenu RaniEmail author
  • S. B. Dhok
  • R. B. Deshmukh
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 587)


Electroencephalogram (EEG) signal is a measure of electrical activity across the brain. For patients suffering from brain disorders like epilepsy, coma, sleep disorders, etc., this electrical activity is continuously monitored. For this, a minimum of 21 electrodes are required, which are placed across the scalp. These electrodes generate a lot of data to be processed for diagnosing the brain disease. Compressive sensing (CS), which is a newer sensing modality, has proved itself to be a better candidate for handling large amount of data to be as compared to the traditional sampling mechanism. CS generates far fewer samples than that suggested by Nyquist rate and still allows faithful reconstruction. The CS reconstruction employs complex nonlinear methods, which are very costly. Compressed signal processing (CSP), which is an advancement over CS, gives a direction to solve certain signal processing tasks from compressive measurements itself, without the need for reconstructing the original signal at all. In this paper, CSP has been used for detecting the presence or absence of epileptic seizure in the EEG signal. For this purpose, a feature extraction method is proposed for extracting the features from compressed EEG measurements. The performance of proposed method has been found to be surprisingly effective in this regard. All the experiments are done on the EEG database taken from physionet CHB-MIT using MATLAB.


Compressive sensing Compressed signal processing EEG monitoring Random demodulator Feature extraction SVM 


  1. 1.
    Aviyente, S.: Compressed Sensing Framework for EEG Compression. IEEE/SP 14th Workshop on Stat. Sig. Proc., Madison, WI, USA, pp. 181-184, 2007. DOI:
  2. 2.
    Zhang, Z., et al.: Compressed Sensing of EEG for Wireless Telemonitoring With Low Energy Consumption and Inexpensive Hardware. IEEE Trans. on Biomed. Engg. 60(1), 221–224 (2013). Scholar
  3. 3.
    Abdulghani, A.M., et al.: Compressive sensing scalp EEG signals: implementations and practical performance. E. Med Biol Eng Comp 50, 1137–1145 (2012). Scholar
  4. 4.
    Candès, E.J., et al.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. on Inf. Theory 52(2), 489–509 (2006). Scholar
  5. 5.
    Donoho, D.L.: Compressed sensing. IEEE Trans. on Inf. Theory 52(4), 1289–1306 (2006). Scholar
  6. 6.
    Baraniuk, R.G.: Compressive Sensing [Lecture Notes]. IEEE Signal Process. Mag. 24(4), 118–121 (2007). Scholar
  7. 7.
    Candès, E.J., Wakin, M.B.: An Introduction to Compressive Sampling. IEEE Sig. Process. Mag. 25(2), 21–30 (2008). Scholar
  8. 8.
    Baraniuk, R., et al.: An Introduction to Compressive Sensing. OpenStax-CNX. April 2, 2011.
  9. 9.
    Rani, M., et al.: A Systematic Review of Compressive Sensing: Concepts. Implementations and Applications. IEEE Access 6, 4875–4894 (2018). Scholar
  10. 10.
    Haupt, J., et al.: Compressive Sampling for Signal Classification. Fortieth Asilomar Conf. on Sig., Sys. and Comp., Pacific Grove, CA, pp. 1430-1434, 2006Google Scholar
  11. 11.
    Duarte, M. F., et al.: Sparse Signal Detection from Incoherent Projections. IEEE Int. Conf. on Acou., Speech and Sig. Process. Proceed., Toulouse, 2006, pp. III-IIIGoogle Scholar
  12. 12.
    Haupt, J. and Nowak, R.: Compressive Sampling for Signal Detection. IEEE Int. Conf. on Acou., Speech and Sig. Process. - ICASSP07, Honolulu, HI, pp. III-1509- III-1512, 2007Google Scholar
  13. 13.
    Davenport, M. A., et al.: Signal Processing With Compressive Measurements. IEEE J. of Sel. Top. in Sig. Proces., vol. 4, no. 2, pp. 445-460, April 2010CrossRefGoogle Scholar
  14. 14.
    Park, J.Y., et al.: Modal Analysis With Compressive Measurements. IEEE Trans. on Sig. Process. 62(7), 1655–1670 (2014)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Goldberger AL, et al.: PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23):e215-e220 [Circulation Electronic Pages;]; 2000 (June 13)
  16. 16.
    Tropp, J.A., et al.: Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals. IEEE Trans. on Inf. Theory 56(1), 520–544 (2010). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Visvesvaraya National Institute of TechnologyNagpurIndia

Personalised recommendations