Abstract
This paper presents the design of a wearable electroencephalography device and signal processing algorithm for early detection and forecasting of the epileptiform activity. The availability of the examination of functional brain activity for a prolonged period, outside of the hospital facilities, can provide new advantages in early diagnosis and intervention systems. In this study, the low-cost five-channel device is presented. The system consists of two main parts: the data acquisition and transmission units and processing algorithms. In order to create the robust epileptiform pattern recognition approach the application of statistical sampling and signal processing techniques are performed. The discrete wavelet and Hilbert- Huang transforms with principal component analysis are used in order to extract and select a low-dimension feature vector.
Go to article
Bibliography
[1] Stacey, William C. ”Seizure Prediction Is Possible–Now Let’s Make It Practical.”, EBioMedicine, No. 27,2018,pp. 3-4.
[2] Federico, P., Abbott, D. F., Briellmann, R. S., Harvey, A. S. ”Functional MRI of the pre-ictal state”, Brain vol. 128, 2005, pp. 1811 - 1817.
[3] Smith S. J. M. ”EEG in the diagnosis, classification, and management of patients with epilepsy”, Journal of Neurology, Neurosurgery & Psychiatry. no. 76, 2005, pp. 112 - 117.
[4] V. Mihajlovi´c, B. Grundlehner, R. Vullers and J. Penders ”Wearable, Wireless EEG Solutions in Daily Life Applications: What are we Missing?”, Journal of Biomedical and Health Informatics vol. 19, no. 1, 2015, pp. 6-21.
[5] Malmivuo, Plonsey, Jakko Malmivuo, Plonsey Robert, ”Bioelectromagnetism: principles and applications of bioelectric and biomagnetic fields”, Oxford University Press, USA, 1995.
[6] Sudakov O., Kriukova G.,Natarov R. et al., ”Distributed System for Sampling and Analysis of Electroencephalograms”, in Proc. 2017 IEEE 9th International conference IDAACS 2017, Bucharest, 21-23 September 2017, pp. 306-310
[7] Direito B. et al. ”A realistic seizure prediction study based on multiclass SVM.” International Journal of Neural Systems, vol. 27, no. 3 , 2017.
[8] Federico P., Abbott, D. F., Briellmann, R. S., Harvey, A. S. ”Functional MRI of the pre-ictal state”, Brain, vol. 128., 2005, pp. 1811-1817
[9] Obermaier B. et al. ”Hidden Markov models for online classification of single trial EEG data.”, Pattern recognition letters, No. 12, 2001, pp.1299-1309.
[10] Zaena J.V. ”Adaptive tracking of EEG oscilattiond”, Neuroscience Methods, 2010.
[11] Dilran S.W., Lakshitha P.W, Sudaraka M. ”Seizure prediction using Hilbert-Huang transform on field programmable gate array”, IEEE Global conference on signal and information processing, Orlando, 2015.
[12] Jin-De Zhu, Chin-Feng L. et al. ”Analysis of spike waves in epilepsy using Hilbert-Huang transform”, Journal of Medical Systems, 2015.
[13] Kshischang F. R.”The Hilbert transform”, University of Toronto, 2006.
[14] Herrmann C.S., Grigutsch M., Bush N.A. ”EEG oscillations and wavelet analysis”, Event-related potencial,2005.
[15] Shaiens J.”A tutorial on Principal Analysis”, arXiv preprint, Cornell University, 2014.
Go to article
en
pl
