A combination of statistical parameters for epileptic seizure detection and classification using VMD and NLTWSVM

• Autorzy: Zhang Shang , Liu Guangda , Xiao Ruolan , Cui Wenjie , Cai Jing , Hu Xinlei , Sun Yubing , Qiu Jiqing , Qi Yuan

Identyfikatory

DOI

10.1016/j.bbe.2022.02.004

• Języki publikacji: EN

Abstrakty

EN

The epileptic seizure detection and classification is of great significance for clinical diagnosis and treatment. To realize the detection and classification of epileptic seizure, this paper proposes a method based on the combination of signal decomposition and statistical methods. First, the algorithm of variational mode decomposition (VMD) is applied to extract the components of intrinsic mode functions (IMFs) by decomposing the EEG signals. Then the statistical method is utilized to calculate the eight features of maximum, minimum, average, variance, skewness, kurtosis, coefficient of variation and volatility index for each extracted IMF component. Finally, the best combinations of extracted features are fed into the non-linear twin support vector machine (NLTWSVM) to classify the epileptic signals. The EEG database from University of Bonn is used to confirm the effectiveness of the proposed method for epileptic seizure detection. The final experimental results demonstrate that the classification accuracy can reach 98.86%, 98.37%, 99.02%, 99.41% and 99.57% for the database of C-E, D-E, CD-E, ABCD-E and AB-CD-E, respectively. The TUSZ corpus in the TUH EEG corpus is also used to classify epileptic seizure types using the method in this article. The result is expressed by the confusion matrix and the weighted F 1 score is 0.923, which shows this method has potential to help experienced neurophysiologists classify epileptic seizure types in the clinic.

Słowa kluczowe

EN

epileptic seizure detection; variational mode decomposition; nonlinear twin support vector machine; feature extraction; seizure type classification

PL

wykrywanie napadu padaczkowego; dekompozycja w trybie wariacyjnym; maszyna wektorów wsparcia; ekstrakcja cech

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 1
• Strony: 258--272
• Opis fizyczny: Bibliogr. 74 poz., rys., tab., wykr.

Twórcy

autor

Zhang Shang

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Liu Guangda

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, China

autor

Xiao Ruolan

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Cui Wenjie

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Cai Jing

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Hu Xinlei

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Sun Yubing

• College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China

autor

Qiu Jiqing

• The First Hospital of Jilin University, Changchun, China

autor

Qi Yuan

• The First Hospital of Jilin University, Changchun, China

Bibliografia

• [1] Moshe SL, Perucca E, Ryvlin P, Tomson T. Epilepsy: new advances. Lancet 2015;385(9971):884–98. https://doi.org/ 10.1016/s0140-6736(14)60456-6.
• [2] Franco AC, Parreira S, Bentes C, Pimentel J. Management of a first unprovoked epileptic seizure in adolescence and adulthood. Epileptic Disord 2021;23(4):537–51. https://doi.org/ 10.1684/epd.2021.1296.
• [3] WHO, Epilepsy: Fact Sheets, detail, World Health Organization, 2019. Available at: https://www.who.int/newsroom/fact-sheets/detail/epilepsy.
• [4] van Win OA, Barnes JG, Ferrier CF, Booth F, Prasad AN, Kasteleijn-Nolst Trenite DGA. A study of the significance of photoparoxysmal responses and spontaneous epileptiform discharges in the EEG in childhood epilepsy. Epilepsy Behav 2020;107:107046. https://doi.org/10.1016/j.yebeh.2020.107046.
• [5] Sen A, Jette N, Husain M, Sander JW. Epilepsy in older people. Lancet 2020;395(10225):735–48. https://doi.org/10.1016/S0140-6736(19)33064-8.
• [6] Mariam Bee MK, Vidhya K. An automated methodology for the classification of focal and nonfocal EEG signals using a hybrid classification approach. Int J Imaging Syst Technol 2020;30(1):147–53. https://doi.org/10.1002/ima.22360.
• [7] Kural MA, Duez L, Sejer Hansen V, Larsson PG, Rampp S, Schulz R, et al. Criteria for defining interictal epileptiform discharges in EEG: A clinical validation study. Neurology 2020;94(20):e2139–47.
• [8] Geng D, Alkhachroum A, Melo Bicchi MA, Jagid JR, Cajigas I, Chen ZS. Deep learning for robust detection of interictal epileptiform discharges. J Neural Eng 2021;18(5):056015. https://doi.org/10.1088/1741-2552/abf28e.
• [9] Swami P, Gandhi TK, Panigrahi BK, Tripathi M, Anand S. A novel robust diagnostic model to detect seizures in electroencephalography. Expert Syst Appl 2016;56:116–30. https://doi.org/10.1016/j.eswa.2016.02.040.
• [10] Yao X, Li X, Ye Q, Huang Y, Cheng Q, Zhang G-Q. A robust deep learning approach for automatic classification of seizures against non-seizures. Biomed Signal Process Control 2021;64:102215. https://doi.org/10.1016/j.bspc.2020.102215.
• [11] Khosla A, Khandnor P, Chand T. A comparative analysis of signal processing and classification methods for different applications based on EEG signals. Biocybern Biomed Eng 2020;40(2):649–90. https://doi.org/10.1016/j.bbe.2020.02.002.
• [12] Zhang Q, Ding Ji, Kong W, Liu Y, Wang Q, Jiang T. Epilepsy prediction through optimized multidimensional sample entropy and Bi-LSTM. Biomed Signal Process Control 2021;64:102293. https://doi.org/10.1016/j.bspc.2020.102293.
• [13] Madhavan S, Tripathy RK, Pachori RB. Time-frequency domain deep convolutional neural network for the classification of focal and non-focal EEG signals. IEEE Sens J 2020;20(6):3078–86.
• [14] Mursalin M, Zhang Y, Chen YH, Chawla NV. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier. Neurocomputing 2017;241:204–14. https://doi.org/10.1016/j. Neucom.2017.02.053.
• [15] Aileni RM, Pasca S, Florescu A. EEG-brain activity monitoring and predictive analysis of signals using artificial neural networks. Sensors 2020;20(12):3346. https://doi.org/10.3390/ s20123346.
• [16] Dodia S, Edla DR, Bablani A, Ramesh D, Kuppili V. An efficient EEG based deceit identification test using wavelet packet transform and linear discriminant analysis. J Neurosci Methods 2019;314:31–40. https://doi.org/10.1016/j. Jneumeth.2019.01.007.
• [17] Samiee K, Kovacs P, Gabbouj M. Epileptic seizure classification of EEG time-series using rational discrete shorttime Fourier Transform. IEEE Trans Biomed Eng 2015;62 (2):541–52. https://doi.org/10.1109/tbme.2014.2360101.
• [18] Kumar Y, Dewal ML, Anand RS. Epileptic seizure detection using DWT based fuzzy approximate entropy and support vector machine. Neurocomputing 2014;133:271–9. https://doi. org/10.1016/j.neucom.2013.11.009.
• [19] Zhang T, Chen W. LMD based features for the automatic seizure detection of EEG signals using SVM. IEEE Trans Neural Syst Rehabil Eng 2017;25(8):1100–8.
• [20] Sharma M, Pachori RB, Acharya UR. A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recognit Lett 2017;94:172–9. https://doi.org/10.1016/ j.patrec.2017.03.023.
• [21] Alickovic E, Kevric J, Subasi A. Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction. Biomed Signal Process Control 2018;39:94–102. https://doi.org/10.1016/j. Bspc.2017.07.022.
• [22] Kalbkhani H, Shayesteh MG. Stockwell transform for epileptic seizure detection from EEG signals. Biomed Signal Process Control 2017;38:108–18. https://doi.org/10.1016/j. Bspc.2017.05.008.
• [23] Bajaj V, Rai K, Kumar A, Sharma D. Time-frequency image based features for classification of epileptic seizures from EEG signals. Biomed Phys Eng Express 2017;3(1). https://doi. org/10.1088/2057-1976/aa5199.
• [24] Seo JH, Tsuda I, Lee YJ, Ikeda A, Matsuhashi M, Matsumoto R, Kikuchi T, Kang H. Pattern recognition in epileptic EEG signals via dynamic mode decomposition. Mathematics 2020;8(4):481. https://doi.org/10.3390/math8040481.
• [25] Cura OK, Akan A. Analysis of epileptic EEG signals by using dynamic mode decomposition and spectrum. Biocybern Biomed Eng 2021;41(1):28–44. https://doi.org/10.1016/j. Bbe.2020.11.002.
• [26] Song Y, Crowcroft J, Zhang J. Automatic epileptic seizure detection in EEGs based on optimized sample entropy and extreme learning machine. J Neurosci Methods 2012;210 (2):132–46. https://doi.org/10.1016/j.jneumeth.2012.07.003.
• [27] Aarabi A, He B. Seizure prediction in patients with focal hippocampal epilepsy. Clin Neurophysiol 2017;128 (7):1299–307. https://doi.org/10.1016/j.clinph.2017.04.026.
• [28] Bari MF, Anowarul Fattah S. Epileptic seizure detection in EEG signals using normalized IMFs in CEEMDAN domain and quadratic discriminant classifier. Biomed Signal Process Control 2020;58:101833. https://doi.org/10.1016/j.bspc.2019.101833.
• [29] Beeraka SM, Kumar A, Sameer M, Ghosh S, Gupta B. Accuracy enhancement of epileptic seizure detection: A deep learning approach with hardware realization of STFT. Circuits Syst Signal Process 2022;41(1):461–84.
• [30] Panda S, Das A, Mishra S, Mohanty MN. Epileptic seizure detection using deep ensemble network with empirical wavelet transform. Meas Sci Rev 2021;21(4):110–6. https://doi. org/10.2478/msr-2021-0016.
• [31] Praveena HD, Subhas C, Naidu KR. Automatic epileptic seizure recognition using reliefF feature selection and long short term memory classifier. J Ambient Intell Humaniz Comput 2021;12(6):6151–67. https://doi.org/10.1007/s12652- 020-02185-7.
• [32] Kaur C, Bisht A, Singh P, Joshi G. EEG Signal denoising using hybrid approach of Variational Mode Decomposition and wavelets for depression. Biomed Signal Process Control 2021;65:102337. https://doi.org/10.1016/j.bspc.2020.102337.
• [33] Li MY, Chen WZ, Zhang T. Application of MODWT and lognormal distribution model for automatic epilepsy identification. Biocybern Biomed Eng 2017;37(4):679–89. https://doi.org/10.1016/j.bbe.2017.08.003.
• [34] Sameer M, Gupta B. Detection of epileptical seizures based on alpha band statistical features. Wirel Pers Commun 2020;115 (2):909–25. https://doi.org/10.1007/s11277-020-07542-5.
• [35] Siuly S, Alcin OF, Bajaj V, Sengur A, Zhang Y. Exploring Hermite transformation in brain signal analysis for the detection of epileptic seizure. IET Sci Meas Technol 2019;13 (1):35–41. https://doi.org/10.1049/iet-smt.2018.5358.
• [36] Zhang T, Chen W-Z, Li M-Y. Automatic seizure detection of electroencephalogram signals based on frequency slice wavelet transform and support vector machine. Acta Phys Sin 2016;65(3):038703. https://doi.org/10.7498/aps.65.038703.
• [37] Song J-L, Zhang R. Application of extreme learning machine to epileptic seizure detection based on lagged Poincare plots. Multidimens Syst Signal Process 2017;28(3):945–59. https:// doi.org/10.1007/s11045-016-0419-y.
• [38] Jia J, Goparaju B, Song J, Zhang R, Westover MB. Automated identification of epileptic seizures in EEG signals based on phase space representation and statistical features in the CEEMD domain. Biomed Signal Process Control 2017;38:148–57. https://doi.org/10.1016/j.bspc.2017.05.015.
• [39] Li Y, Wang X-D, Luo M-L, Li Ke, Yang X-F, Guo Qi. Epileptic seizure classification of EEGs using time-frequency analysis based multiscale radial basis functions. IEEE J Biomed Health Inform 2018;22(2):386–97.
• [40] Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A 1998;454(1971):903–95.
• [41] Muñoz-Gutiérrez PA, Giraldo E, Bueno-López M, Molinas M. Localization of active brain sources from EEG signals using empirical mode decomposition: A comparative study. Front Integr Neurosci 2018;12:55. https://doi.org/10.3389/ fnint.2018.00055.
• [42] Wu Z, Huang NE. Ensemble empirical mode decomposition: A noise-assisted data analysis method. Adv Adapt Data Anal 2009;01(01):1–41. https://doi.org/10.1142/s1793536909000047.
• [43] Hassan AR, Subasi A, Zhang Y. Epilepsy seizure detection using complete ensemble empirical mode decomposition with adaptive noise. Knowl-Based Syst 2020;191:105333. https://doi.org/10.1016/j.knosys.2019.105333.
• [44] Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Trans Signal Process 2014;62(3):531–44. https://doi.org/ 10.1109/tsp.2013.2288675.
• [45] Rout SK, Sahani M, Dash PK, Biswal PK. Multifuse multilayer multikernel RVFLN plus of process modes decomposition and approximate entropy data from iEEG/sEEG signals for epileptic seizure recognition. Comput Biol Med 2021;132. https://doi.org/10.1016/j.compbiomed.2021.104299 104299.
• [46] Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. 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 2001;64(6). https://doi.org/10.1103/PhysRevE.64.061907.
• [47] Shah V, von Weltin E, Lopez S, McHugh JR, Veloso L, Golmohammadi M, et al. The Temple University Hospital Seizure Detection Corpus. Front Neuroinf 2018;12(83). https:// doi.org/10.3389/fninf.2018.00083.
• [48] Yadav VP, Sharma KK. Variational mode decomposition-based seizure classification using Bayesian regularized shallow neural network. Biocybern Biomed Eng 2021;41 (2):402–18. https://doi.org/10.1016/j.bbe.2021.02.003.
• [49] Carvalho VR, Moraes MFD, Braga AP, Mendes EMAM. Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification. Biomed Signal Process Control 2020;62:102073. https://doi.org/ 10.1016/j.bspc.2020.102073.
• [50] Rezvani S, Wang X, Pourpanah F. Intuitionistic fuzzy twin support vector machines. IEEE Trans Fuzzy Syst 2019;27 (11):2140–51.
• [51] Guan S, Zhao K, Wang F. Multiclass motor imagery recognition of single joint in upper limb based on NSGA- II OVO TWSVM. Comput Intell Neurosci 2018;2018:1–11. https:// doi.org/10.1155/2018/6265108.
• [52] Sukriti, Chakraborty M, Mitra D. Mitra, Epilepsy seizure detection using kurtosis based VMD’s parameters selection and bandwidth features. Biomed Signal Process Control 2021;64:102255. https://doi.org/10.1016/j.bspc.2020.102255.
• [53] Zeng W, Yuan J, Yuan C, Wang Q, Liu F, Wang Y. Classification of myocardial infarction based on hybrid feature extraction and artificial intelligence tools by adopting tunable-Q wavelet transform (TQWT), variational mode decomposition (VMD) and neural networks. Artif Intell Med 2020;106:101848. https://doi.org/10.1016/j.artmed.2020.101848.
• [54] Zhou DM, Li XM. Epilepsy EEG signal classification algorithm based on improved RBF. Front Neurosci 2020;14:7. https://doi. org/10.3389/fnins.2020.00606.
• [55] Raghu S, Sriraam N. Optimal configuration of multilayer perceptron neural network classifier for recognition of intracranial epileptic seizures. Expert Syst Appl 2017;89:205–21. https://doi.org/10.1016/j.eswa.2017.07.029.
• [56] Gupta A, Singh P, Karlekar M. A novel signal modeling approach for classification of seizure and seizure-free EEG signals. IEEE Trans Neural Syst Rehabil Eng 2018;26(5):925–35.
• [57] Raghu S, Sriraam N, Hegde AS, Kubben PL. A novel approach for classification of epileptic seizures using matrix determinant. Expert Syst Appl 2019;127:323–41. https://doi. org/10.1016/j.eswa.2019.03.021.
• [58] Mathur P, Chakka VK, Shah SB. Ramanujan periodic subspace based epileptic EEG signals classification. IEEE Sens Lett 2021;5(7):1–4.
• [59] Hassan AR, Subasi A. Automatic identification of epileptic seizures from EEG signals using linear programming boosting. Comput Meth Programs Biomed 2016;136:65–77. https://doi.org/10.1016/j.cmpb.2016.08.013.
• [60] Sharma M, Bhurane AA, Acharya UR. MMSFL-OWFB: A novel class of orthogonal wavelet filters for epileptic seizure detection. Knowl-Based Syst 2018;160:265–77. https://doi.org/ 10.1016/j.knosys.2018.07.019.
• [61] Jaiswal AK, Banka H. Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals. Biomed Signal Process Control 2017;34:81–92. https://doi.org/10.1016/j.bspc.2017.01.005.
• [62] Patidar S, Panigrahi T. Detection of epileptic seizure using Kraskov entropy applied on tunable -Q wavelet transform of EEG signals. Biomed Signal Process Control 2017;34:74–80. https://doi.org/10.1016/j.bspc.2017.01.001.
• [63] Mandhouj B, Cherni MA, Sayadi M. An automated classification of EEG signals based on spectrogram and CNN for epilepsy diagnosis. Analog Integr Circuits Process 2021;108(1):101–10. https://doi.org/10.1007/s10470-021-01805- 2.
• [64] Zhao W, Wang W. SeizureNet: a model for robust detection of epileptic seizures based on convolutional neural network. Cogn Comput Syst 2020;2(3):119–24. https://doi.org/10.1049/ ccs.2020.0011.
• [65] Murugavel ASM, Ramakrishnan S. Hierarchical multi-class SVM with ELM kernel for epileptic EEG signal classification. Med Biol Eng Comput 2016;54(1):149–61. https://doi.org/ 10.1007/s11517-015-1351-2.
• [66] Jiang Y, Chen W, Li M, Zhang T, You Y. Synchroextracting chirplet transform-based epileptic seizures detection using EEG. Biomed Signal Process Control 2021;68:102699. https:// doi.org/10.1016/j.bspc.2021.102699.
• [67] Ahmedt-Aristizabal D, Fernando T, Denman S, Petersson L, Aburn MJ, Fookes C. Neural memory networks for seizure type classification. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. p. 569–75. https://doi.org/10.1109/ EMBC44109.2020.9175641.
• [68] McCallan N, Davidson S, Ng KY, Biglarbeigi P, Finlay D, Lan BL, et al. Seizure classification of EEG based on wavelet signal denoising using a novel channel selection algorithm (In Press). 13th Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2021.
• [69] Asif U, Roy S, Tang J, Harrer S, SeizureNet: Multi-spectral deep feature learning for seizure type classification, arXiv e-prints (2019) arXiv:1903.03232.
• [70] Fukumori K, Yoshida N, Tanaka T, Epileptic spike detection by recurrent neural networks with self-attention mechanism, bioRxiv (2021.06.17) 448793, https://dx.doi.org/10.1101/ 2021.06.17.448793.
• [71] Lourenco C, Tjepkema-Cloostermans MC, Teixeira LF, van Putten M. Deep learning for interictal epileptiform discharge detection from scalp EEG recordings. In: 15th Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON). Coimbra, Portugal: Springer International Publishing Ag, UNESCO World Heritage Univ; 2019. p. 1984–97.
• [72] Baud MO, Schindler K, Rao VR. Under-sampling in epilepsy: Limitations of conventional EEG. Clin Neurophys Pract 2021;6:41–9. https://doi.org/10.1016/j.cnp.2020.12.002.
• [73] Proix T, Truccolo W, Leguia MG, Tcheng TK, King-Stephens D, Rao VR, et al. Forecasting seizure risk in adults with focal epilepsy: a development and validation study. Lancet Neurol 2021;20(2):127–35.
• [74] Turco F, Bonanni E, Milano C, Pizzanelli C, Steinwurzel C, Morganti R, et al. Prolonged epileptic discharges predict seizure recurrence in JME: Insights from prolonged ambulatory EEG. Epilepsia 2021;62(5):1184–92. https://doi.org/10.1111/epi.16875.