Browse > Article
http://dx.doi.org/10.4218/etrij.2018-0118

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals  

Lee, Miran (Graduate School of Information Science and Engineering, Ritsumeikan University)
Ryu, Jaehwan (Technical Research Institute, Sammi Information System)
Kim, Deok-Hwan (Department of Electronic Engineering, Inha University)
Publication Information
ETRI Journal / v.42, no.2, 2020 , pp. 217-229 More about this Journal
Abstract
Long-term electroencephalography (EEG) monitoring is time-consuming, and requires experts to interpret EEG signals to detect seizures in patients. In this paper, we propose a novel automated method called adaptive slope of wavelet coefficient counts over various thresholds (ASCOT) to classify patient episodes as seizure waveforms. ASCOT involves extracting the feature matrix by calculating the mean slope of wavelet coefficient counts over various thresholds in each frequency subband. We validated our method using our own database and a public database to avoid overtuning. The experimental results show that the proposed method achieved a reliable and promising accuracy in both our own database (98.93%) and the public database (99.78%). Finally, we evaluated the performance of the method considering various window sizes. In conclusion, the proposed method achieved a reliable seizure detection performance with a short-term window size. Therefore, our method can be utilized to interpret long-term EEG results and detect momentary seizure waveforms in diagnostic systems.
Keywords
discrete wavelet transform; electroencephalography; feature extraction; machine learning; Seizure detection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 K. P. Indiradevi et al., A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram, Comput. Biol. Med. 38 (2008), no. 7, 805-816.   DOI
2 R. W. Wall, Simple methods for detecting zero crossing, in Proc. Ann. Conf. Industrial Elect. Soc., Roanoke, VA, USA, 2004, pp. 2477-2481.
3 M. Z. Uddin, D. H. Kim, and T. S. Kim, A human activity recognition system using HMMs with GDA on enhanced independent component features, Int. Arab J. Inf. Technol. 12 (2015), no. 3, 304-310.
4 M. H. Abdullah, J. M. Abullah, and M. Z. Abdullah, Seizure detection by means of hidden Markov model and stationary wavelet transform of electroencephalograph signals, in Proc. Biomed. Health Informatics, Hong Kong, China, 2012, pp. 62-65.
5 R. Sharma and R. B. Pachori, Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions, Expert Syst. Applicat. 42 (2015), no. 3, 1106-1117.   DOI
6 R. R. Sharma and R. B. Pachori, Time-frequency representation using IEVDHM-HT with application to classification of epileptic EEG signals, IET Sci. Meas. Technol. 12 (2017), no. 1, 72-82.
7 M. Peker, B. Sen, and D. Delen, A novel method for automated diagnosis of epilepsy using complex‐valued classifiers, IEEE J. Biomed. Health Inform. 20 (2015), no. 1, 108-118.   DOI
8 K. Samiee, P. Kovacs, and M. Gabboouj, Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform, IEEE Trans. Biomed. Eng. 62 (2014), no. 2, 541-552.   DOI
9 T. S. Kumar, Classification of seizure and seizure‐free EEG signals using local binary patterns, Biomed. Signal Process. Contr. 15 (2015), 33-40.   DOI
10 Y. Kaya et al., 1D-local binary pattern based feature extraction for classification of epileptic EEG signals, Appl. Math. Comput. 243 (2014), 209-219.   DOI
11 T. S. Kumar et al., Classification of seizure and seizure-free EEG signals using multi-level local patterns, in Proc. Int. Conf. Digit. Signal Process., Hong Kong, China, Aug. 2014, pp. 646-650.
12 A. K. Jaiswal and H. Banka, Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals, Biomed. Signal Process. Contr. 34 (2017), 81-92.   DOI
13 A. K. Jaiswal and H. Banka, Epileptic seizure detection in EEG signal with GModPCA and support vector machine, Biomed. Mater. Eng. 28 (2017), no. 2, 141-157.
14 A. K. Jaiswal and H. Banka, Epileptic seizure detection in EEG signal using machine learning techniques, Australas. Phys. Eng. Sci. Med. 41 (2018), no. 1, 81-94.   DOI
15 T. Gandhi et al., Expert model for detection of epileptic activity in EEG signature, Expert Syst. Appl. 37 (2010), no. 4, 3513-3520.   DOI
16 N. J. Sairamya et al., Detection of epileptic EEG signal using improved local pattern transformation methods, Circ. Syst. Signal Process. 37 (2018), no. 12, 1-22.   DOI
17 J. L. Song and R. Zhang, Automatic seizure detection using a novel EEG feature based on nonlinear complexity, in Proc. Int. Joint Conf. Neural Netw., Vancouver, Canada, 2016, pp. 1686-1695.
18 Y. Kumar, M. L. Dewal, and R. S. Anand, Epileptic seizure detection using DWT based fuzzy approximate entropy and support vector machine, Neurocomput. 133 (2014), 271-279.   DOI
19 F. Mormann et al., Seizure prediction: the long and winding road, Brain 130 (2006), no. 2, 314-333.   DOI
20 B. Litt and K. Lehnertz, Seizure prediction and the preseizure period, Curr. Opin. Neurol. 14 (2002), no. 2. 173-177.
21 V. Joshi, R. B. Pachori, and A. Vijesh, Classification of ictal and seizure‐free EEG signals using fractional linear prediction, Biomed. Signal Process. Contr. 9 (2013), 1-5.   DOI
22 L. Guo et al., Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks, J. Neurosci. Methods 191 (2010), no. 1, 101-109.   DOI
23 A. Subasi and M. I. Gursoy, EEG signal classification using PCA, ICA, LDA and support vector machines, Expert Syst. Applicat. 37 (2010), no. 12, 8659-8666.   DOI
24 S. Xie et al., Feature extraction via dynamic PCA for epilepsy diagnosis and epileptic seizure detection, in Proc. IEEE Int. Work. Machine Lear. Signal Process., Kittila, Finland, 2010, pp. 337-342.
25 S. Ghosh‐Dastidar, H. Adeli, and N. Daddmehr, Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection, IEEE Trans. Biomed. Eng. 55 (2008), no. 2, 512-518.   DOI
26 J. Kevric and A. Subasi, The effect of multiscale PCA de-noising in epileptic seizure detection, J. Med. Syst. 38 (2014), no. 10, 131-143.   DOI
27 Y. Kumar, M. L. Dewal, and R. S. Anand, Epileptic seizures detection in EEG using DWT‐based ApEn and artificial neural network, Signal Image Video Process 8 (2012), no. 7, 1323-1334.   DOI
28 M. Sharmar, R. B. Pachori, and U. R. Acharya, A new approach to characterize epileptic seizures using analytic time‐frequency flexible wavelet transform and fractal dimension, Pattern Recogn. Lett. 94 (2017), 172-179.   DOI
29 D. Bhati, R. B. Pachori, and V. M. Gadre, Time-frequency localized three-band biorthogonal wavelet filter bank using semidefinite relaxation and nonlinear least squares with epileptic seizure EEG signal classification, Digit. Signal Process. 62 (2017), 259-273.   DOI
30 H. Ocak, Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy, Expert Syst. Applicat. 36 (2009), no. 2, 2027-2036.   DOI
31 S. Nasehi and H. Pourghassem, Automatic prediction of epileptic seizure using kernel fisher discriminant classifiers, in Proc. Int. Compt. Bio-Med. Instrum., Wuhan, China, 2011, pp. 200-203.
32 A. K. Tiwari et al., Automated diagnosis of epilepsy using keypoints based local binary pattern of EEG signals, IEEE J. Biomed. Health. 21 (2017), no. 4, 888-896.   DOI
33 A. Bhattacharyya et al., Tunable-Q wavelet transform based multiscale entropy measure for automated classification of epileptic EEG signals, Appl. Sci. 7 (2017), no. 4, 385-402.   DOI
34 R. B. Pachori and S. Patidar, Epileptic seizure classification in EEG signals using second‐order difference plot of intrinsic mode functions, Comput. Methods Programs Biomed. 113 (2014), no. 2, 494-502.   DOI
35 V. Bajaj and R. B. Pachori, Epileptic seizure detection based on the instantaneous area of analytic intrinsic mode functions of EEG signals, Biomed. Eng. Lett. 3 (2013), no. 1, 17-21.   DOI
36 V. Bajaj and R. B. Pachori, Classification of seizure and nonseizure EEG signals using empirical mode decomposition, IEEE Trans. Inf. Technol. Biomed. 16 (2012), no. 6, 1135-1142.   DOI
37 R. B. Pachori and V. Bajaj, Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition, Comput. Methods Programs Biomed. 104 (2011), no. 3, 373-381.   DOI
38 R. B. Pachori, Discrimination between ictal and seizure‐free EEG signals using empirical mode decomposition, Res. Lett. Signal Process. 2008 (2008), no. 14, 1-5.   DOI
39 I. Conradsen et al., Automated algorithm for generalised tonicclonic epileptic seizure onset detection based on sEMG zero‐crossing rate, IEEE Trans. Biomed. Eng. 59 (2012), no. 2, 579-585.   DOI
40 S. Elgohary, S. Eldawlathly, and M. I. Khalil, Epileptic seizure prediction using zero‐crossings analysis of EEG wavelet detail coefficients, in Proc. IEEE Conf. Comput. Intell. Bioinformatics. Comput. Biol., Chiang, Thailand, Oct. 2016, pp. 1-6.
41 A. S. Zandi et al., Predicting epileptic seizures in scalp EEG based on a variational bayesian faussian mixture model of zero‐crossing intervals, IEEE Trans. Biomed. Eng. 60 (2013), no. 5, 1401-1413.   DOI
42 A. S. Zandi et al., Predicting temporal lobe epileptic seizures based on zero-crossing interval analysis in scalp EEG, in Proc. Ann. Int. Conf. Eng. Medi. Biol. Soc., Buenos Aires, Argentina, 2010, pp. 5537-5540.
43 A. Subasi, Application of adaptive neuro‐fuzzy inference system for epileptic seizure detection using wavelet feature extraction, Comput. Biol. Med. 37 (2007), no. 2, 227-244.   DOI
44 M. R. Lee et al., Classification of both seizure and non‐seizure based on EEG signals using hidden markov model, in Proc. Int. Conf. BIGCOMP., Shanghai, China, 2018, pp. 469-474.
45 R. Oostenveld and P. Praamstra, The five percent electrode system for high‐resolution EEG and ERP measurements, Clin. Neurophysiol. 112 (2001), no. 4, 713-719.   DOI
46 M. R. Lee et al., A novel R peak detection method for mobile environments, IEEE Access 6 (2018), 51227-51237.   DOI
47 R. G. Andrzejak et al., Indications of nonlinear deterministic and finite dimensional structures in time series of brain electrical activity: dependence on recording region and brain state, Phys. Rev. E. 64 (2001), no. 6, 061907:1-8.   DOI