AUTHORS: Radu Matei, Daniela Matei
Download as PDF
ABSTRACT: In this paper we apply some signal processing methods to detect and classify specific patterns present in EEG signal, which give information about the inset of brain disorders, in particular epileptic activity. We analyze EEG signals using spectral analysis methods, namely Short-Time Fourier Transform and Discrete Wavelet Transform, applied to several sets of EEG recordings. The spectrograms and wavelet decompositions and spectra are shown for a few EEG sequences with typical pathological patterns, to prove the possibility of classification based on EEG spectrum.
KEYWORDS: EEG analysis, epileptic activity, wavelet transform, spectrogram
REFERENCES:
[1] D. Moretti, The Contribution of EEG to the Diagnosis of Dementia, Journal of Biomedical Science and Engineering, 7, 2014, pp. 546-562
[2] S. Sanei, J.A. Chambers, EEG Signal Processing, Wiley-Interscience, 2007
[3] N.V. Thakor, S. Tong, Quantitative EEG Analysis Methods and Clinical Applications, Artech House, 2009
[4] M. Mustafa et al., EEG Spectrogram Classification Employing ANN for IQ Application, Int. Conf. on Technological Table 1. Classification of EEG rhythms by the dominant relative energy band Type of EEG rhythm Dominant component RA5/S (%) RD5/S (%) RD4/S (%) RD3/S (%) RD2/S (%) Spike-wave complex A5 54.7 ± 11.4 16.5 ± 6.7 15.1 ± 6.7 14.2 ± 4.9 3.3 ± 2.9 - rhythm, spikes D5 14.5 ± 8.7 42.2 ± 7.2 29.7 ± 5.6 12.2 ± 5.1 1.4 ± 0.7 Simple wave D4 7.4 ± 6.9 21.3 ± 7.5 51.6 ± 9.1 18.4 ± 7.7 2.1 ± 1.4 High-frequency bursts D3 9.4 ± 4.2 18.9 ± 6.9 21.3 ± 8.3 43.4 ± 9.4 6.7 ± 2.4 Advances in Electrical, Electronics and Computer Engineering 2013, Konya, Turkey
[5] I. Daubechies, Ten Lectures on Wavelets, Philadelphia: Society for Industrial and Applied Mathematics, 1992
[6] S.J. Schiff, A. Aldroubi, M. Unser, S. Sato, Fast Wavelet Transform of EEG, Electroencephalogr. and Clin. Neurophysiol. 91, 1994, pp. 442–455
[7] C. Yamaguchi, Fourier and Wavelet Analyses of Normal and Epileptic Electroencephalogr. (EEG), Proc. 1st IEEE EMBS Conf. on Neural Engineering, Italy, 2003, pp. 406-409
[8] A. Subasi, EEG Signal Classification Using Wavelet Feature Extraction and a Mixture of Expert Model, Expert Systems with Applications, 32, 2007, pp. 1084–1093
[9] L.S. Vidyaratne, K.M. Iftekharuddin, RealTime Epileptic Seizure Detection Using EEG, IEEE Transactions on Neural Systems and Rehabilitation Engineering, PP (99), 2017
[10] A. Şengür, Y. Guo, Y. Akbulut, Time– Frequency Texture Descriptors of EEG Signals for Efficient Detection of Epileptic Seizure, Brain Informatics, 3(2), 2016, pp. 101–108
[11] D. Chen, S. Wan, J. Xiang, F.S. Bao, A HighPerformance Seizure Detection Algorithm Based on Discrete Wavelet Transform (DWT) and EEG, IEEE Trans. on Neural Systems and Rehabilitation Engineering, 25 (5), 2017, pp. 413 – 425
[12] Z. Zhang, K.K. Parhi, Low-Complexity Seizure Prediction from iEEG/sEEG Using Spectral Power and Ratios of Spectral Power, IEEE Trans. Biomedical Circuits and Systems, 10(3), 2016, pp. 693-706
[13] C. Lainscsek, M.E. Hernandez, H. Poizner; T.J. Sejnowski, Delay Differential Analysis of Electroencephalographic Data, Neural Computation, 27 (3), 2015
[14] I. Omerhodzic et al., Energy Distribution of EEG Signals: EEG Signal Wavelet-Neural Network Classifier, World Academy of Science, Engineering and Technology, 61, 2010, pp. 1190-1195
[15] R.G. Andrzejak, K. Lehnertz, C. Rieke, F. Mormann, P. David, C.E. Elger, Indications of Nonlinear Deterministic and Finite Dimensional Structures in Time Series of Brain Electrical Activity: Dependence on Recording Region and Brain State, Physical review. E, Statistical, nonlinear, and soft matter physics, 64, 2001