A Statistical Seizure Prediction Approach Based on Savitzky-Golay Smoothing

Document Type : Original Article

Authors

1 Dept. of Electronics and Communications Engineering, Faculty of Engineering, Tanta University.

2 King Abdalziz City for Science and Technology, Riyadh City, KSA

3 king saud university, Riyadh City

4 Dept. of Electronics and Electrical Communications, Faculty of Engineering, Menoufia University

Abstract

"> This paper presents an enhanced seizure prediction technique based on a statistical approach for channel selection depending on amplitude, median, mean, variance, and derivative of processed EEG signals. The EEG pre-processing depends on Savitzky Golay (S-G) digital filter for smoothing of the signals, while maintaining the signal peaks. This technique consists of two phases; training, by randomly selected hours from normal, ictal and pre-ictal periods, and then estimating five Probability Density Functions (PDFs), and testing, by discrimination between normal and pre-ictal periods, and then the determination of a discrimination count threshold to predict the epilepsy seizure. Applying this approach on patients’ data taken by MIT shows that we can achieve high prediction accuracy (93.5%) with low false alarm rate (0.148/h) and a good prediction time (51.8166 min).

References

-width: 0px; "> <[1] H. Berger , “Über des Elekrenkephalogramm des Menschen, ” Archiv für
Psychiatrie und Nervenkrankheiten, Vol. 87, No. 1, pp 527-570, 1929.
[2] A T Tzallas, M G Tsipouras, D G. Tsalikakis, E C Karvounis, L Astrakas,
S Konitsiotis, M Tzaphlidou, Automated Epileptic Seizure Detection
Methods: A Review Study, Epilepsy - Histological,
Electroencephalographic and Psychological Aspects, Dr. Dejan Stevanovic
(Ed.), ISBN: 978-953-51-0082-9, InTech, (2012).
[3] T. Alotaiby, S. A. Alshebeili, T. Alshawi, I. Ahmad, F. E. Abd El-Samie,
“EEG Seizure Detection and Prediction Algorithms: A survey,” Accepted
for Publication in EURASIP Journal of Advances in Signal Processing.
[4] R. Scherer, G. Moitzi, I. Daly, G. R. Müller-Putz, “ On the Use of Games
for Noninvasive EEG-Based Functional Brain Mapping,” IEEE e-adjust: auto; -webkit-text-stroke-wiTransactions on Computational Intelligence and AI in Games, Vol. 5, No.
2, pp. 155-163, June, 2013.
[5] S. Makeig, C. Kothe, T. Mullen, N. Bigdely-Shamlo, Z. Zhang, K. KreutzDelgado, “ Evolving Signal Processing for Brain–Computer Interfaces, “
Proceedings of the IEEE, Vol. 100, pp. 1567-1584, May, 2012.
[6] D. J. Thurman, E. Beghi, C. E. Begley, A. T. Berg, J. R. Buchhalter, D.
Ding, D. C. Hesdorffer, W. A. Hauser, Lewis Kazis, Rosemarie
Kobau, Barbara Kroner, D. Labiner, K. Liow, G. Logroscino, M. T.
Medina, C. R. Newton, K. Parko, A. Paschal, P. Preux, J.W. Sander, A.
Selassie, W. Theodore, T. Tomson, and S.Wiebe for the ILAE Commission
on Epidemiology, “Standards for epidemiologic studies and surveillance of
epilepsy,” Vol. 52, Issue Supplement s7, pp. 1–26, September, 2011.
[7] S. H. Hung, C. F. Chao, S. K. Wang, B. S. Lin, C. T. Lin, “ VLSI
implementation for Epileptic Seizure Prediction System based on Wavelet
and Chaos Theory,” Proceedings of the IEEE TENCON, 2010.
[8] A. Aarabi, B. He, “A rule-based seizure prediction method for focal
neocortical epilepsy,” Clinical Neurophysiology Vol. 123, pp. 1111–1122,
2012.
[9] LI et al. “SEIZURE PREDICTION USING SPIKE RATE OF
INTRACRANIAL EEG” IEEE TRANSACTIONS ON NEURAL
SYSTEMS AND REHABILITATION ENGINEERING, VOL. 21, NO. 6,
NOVEMBER 2013.
[10] K. Gadhoumi, J. M. Lina, J. Gotman, “Seizure prediction in patients with
mesial temporal lobe epilepsy using EEG measures of state similarity,”
Clinical Neurophysiology, Vol. 124, pp. 1745-1754, 2013.
[11] M. Pezarv and M. Paul, “Epileptic Seizure Prediction by Exploiting
Spatiotemporal Relationship of EEG Signals using Phase Correlation”
IEEE Transactions on Neural Systems and Rehabilitation Engineering,
Vol. 10, No. 1109, pp. 2458982, 2015
[12] M. I. Khalid et al. “Online Adaptive Seizure Prediction Algorithm for
Scalp EEG” IEEE International Conference on Information and
Communication Technology Research, 2015
[13] Y. Qi, Y. Wang, X. Zheng, J. Zhang, J. Zhu, J. Guo,” Efficient Epileptic
Seizure Detection by a Combined IMF-VoE Feature,” Proceedings of the
International Conference of the IEEE EMBS, 2012.
[14] S. Xie, S. Krishnan, “Signal Decomposition by Multi-scale PCA and Its
Applications to Long-term EEG Signal Classification,” Proceedings of the
IEEE International Conference on Complex Medical Engineering, 2011.
[15] M. R. Miri, A. M. Nasrabadi, “A New Seizure Prediction Method Based
on Return Map,” Proceedings of the Iranian Conference on BioMedical
Engineering, 2011
kit-text-stroke-width: 0px; "> [16] J. R. Williamson, D. W. Bliss , D. W. Browne, J. T. Narayanan,” Seizure
prediction using EEG spatiotemporal correlation structure,” Epilepsy &
Behavior, Vol. 25 pp. 230–238, 2012.
[17] A. Savitzky, M.J.E. Golay, “Smoothing and differentiation of data by
simplified least square procedure”, Anal.Chem.36(8)(1964)1627–1639.
[18] J. Lue, K. Ying, J. Bai, “Savitzky–Golay smoothing and differentiation
filter for even number data”, Signal Process.85 (7) (2005)1429–1434.
[19] H. Hassanpour, “A time-frequency approach for noise reduction”,
Digit.Signal Process. 18(5) (2008)728–738.
[20] S. M. Kuo, B. H. Lee, W. Tian, Real-Time Digital Signal Processing,
Implementations and Applications, John Wiley & Sons, 2006.
[21] F. E. Abd El-Samie, Information Security for Automatic Speaker
Identification, 1st Edition, Springer, 2011.
[22] L. Yin, R. Yang, M. Gabbouj, Y. Neuvo, “Weighted Median Filters: A
Tutorial,” IEEE Transactions on Circuits and Systems-II: Analog and
Digital Signal Processing, Vol. 43, No. 3, pp. 157-192, 1996.
[23] http://physionet.org/pn6/chbmit/
 

Files

Share

How to cite

Statistics