Abstract
Epilepsy is a persistent neurological disorder impacting over 50 million people around the world. It is characterized by repeated seizures defined as brief episodes of involuntary movement that might entail the human body. Electroencephalography (EEG) signals are usually used for the detection of epileptic seizures. This paper introduces a new feature extraction method for the classification of seizure and seizure-free EEG time segments. The proposed method relies on the empirical mode decomposition (EMD), statistics and autoregressive (AR) parameters. The EMD method decomposes an EEG time segment into a finite set of intrinsic mode functions (IMFs) from which statistical coefficients and autoregressive parameters are computed. Nevertheless, the calculated features could be of high dimension as the number of IMFs increases, the Student’s t-test and the Mann–Whitney U test were thus employed for features ranking in order to withdraw lower significant features. The obtained features have been used for the classification of seizure and seizure-free EEG signals by the application of a feed-forward multilayer perceptron neural network (MLPNN) classifier. Experimental results carried out on the EEG database provided by the University of Bonn, Germany, demonstrated the effectiveness of the proposed method which performance assessed by the classification accuracy (CA) is compared to other existing performances reported in the literature.
-
Research funding: This research did not receive any kind of funding.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The author declares that there is no conflict of interest.
References
1. World Health Organization. 2017. http://www.who.int/en/news-room/fact-sheets/detail/epilepsy.Search in Google Scholar
2. Kang, JH, Chung, YG, Kim, SP. An efficient detection of epileptic seizure by differentiation and spectral analysis of electroencephalograms. Comput Biol Med 2015;66:352–6. https://doi.org/10.1016/j.compbiomed.2015.04.034.Search in Google Scholar PubMed
3. Kocadagli, O, Langari, R. Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations. Expert Syst Appl 2017;88:419–4. https://doi.org/10.1016/j.eswa.2017.07.020.Search in Google Scholar
4. Direito, B, Teixeira, C, Bandarabadi, M, Sales, F, Dourado, A. Automatic warning of epileptic seizures by SVM: The long road ahead to success. In: Proceedings, 19th IFAC world congress 2014;47:1158–63. https://doi.org/10.3182/20140824-6-ZA-1003.00658.Search in Google Scholar
5. Chua, KC, Chandran, V, Acharya, UR, Lim, CM. Application of higher order spectra to identify epileptic EEG. J Med Syst 2011;35:1563–71. https://doi.org/10.1007/s10916-010-9433-z.Search in Google Scholar PubMed
6. Del-Rincon, JM, Santofimia, MJ, Del Toro, X, Barba, J, Romero, F, Navas, P. et al.Non-linear classifiers applied to EEG analysis for epilepsy seizure detection. Expert Syst Appl 2017;86:99–112. https://doi.org/10.1016/j.eswa.2017.05.052.Search in Google Scholar
7. Altunay, S, Telatar, Z, Erogul, O. Epileptic EEG detection using the linear prediction error energy. Expert Syst Appl 2010;37:5661–5. https://doi.org/10.1016/j.eswa.2010.02.045.Search in Google Scholar
8. Polat, K, Günes, S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast fourier transform. Appl Math Comput 2007;187:1017–26. https://doi.org/10.1016/j.amc.2006.09.022.Search in Google Scholar
9. Tzallas, AT, Tsipouras, MG, Fotiadis, DI. Epileptic seizure detection in eegs using time-frequency analysis. IEEE Trans Inf Technol Biomed 2009;13:703–10.10.1109/TITB.2009.2017939Search in Google Scholar PubMed
10. Chen, LL, Zhang, J, Zou, JZ, Zhao, CJ, Wang, GS. A framework on wavelet-based nonlinear features and extreme learning machine for epileptic seizure detection. Biomed Signal Process Contr 2014;10:1–10. https://doi.org/10.1016/j.bspc.2013.11.010.Search in Google Scholar
11. Patidar, S, Panigrahi, T. Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals. Biomed Signal Process Contr 2017;34:74–80. https://doi.org/10.1016/j.bspc.2017.01.001.Search in Google Scholar
12. Übeyli, ED. Lyapunov exponents/probabilistic neural networks for analysis of EEG signals. Expert Syst Appl 2010;37:985–92. https://doi.org/10.1016/j.eswa.2009.05.078.Search in Google Scholar
13. Tiwari, AK, Pachori, RB, Kanhangad, V, Panigrahi, BK. Automated diagnosis of epilepsy using key-point-based local binary pattern of eeg signals. IEEE J Biomed Health Inf 2017;21:4. https://doi.org/10.1109/jbhi.2016.2589971.Search in Google Scholar
14. Bajaj, V., Pachori, RB. Classification of seizure and nonseizure eeg signals using empirical mode decomposition. IEEE Trans Inf Technol Biomed 2017;16:1135–42. https://doi.org/10.1109/titb.2011.2181403.Search in Google Scholar
15. Bhattacharyya, A, Pachori, RB. A multivariate approach for patient-specific eeg seizure detection using empirical wavelet transform. IEEE Trans Biomed Eng 2017;4:2003–15.10.1109/TBME.2017.2650259Search in Google Scholar PubMed
16. Bhattacharyya, A, Singh, L, Pachori, RB. Fourier–Bessel series expansion based empirical wavelet transform for analysis of non-stationary signals. Digit Signal Process 2018;78:185–96. https://doi.org/10.1016/j.dsp.2018.02.020.Search in Google Scholar
17. Bajaj, V, Pachori, RB. Epileptic seizure detection based on the instantaneous area of analytic intrinsic mode functions of EEG signals. Biomed Eng Lett 2013;3:17–21. https://doi.org/10.1007/s13534-013-0084-0.Search in Google Scholar
18. Sharma, M, Pachori, RB. A novel approach to detect epileptic seizures using a combination of tunable-q wavelet transform and fractal dimension. J Mech Med Biol 2017;7:17400003. https://doi.org/10.1142/S0219519417400036.Search in Google Scholar
19. 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 Roy Soc Lond Math Phys Sci 1998;454:903–95.10.1098/rspa.1998.0193Search in Google Scholar
20. Pachori, RB, Bajaj, V. Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition. Comput Methods Progr Biomed 2011;104:373–81. https://doi.org/10.1016/j.cmpb.2011.03.009.Search in Google Scholar PubMed
21. Babu, TN, Devendiran, S, Aravind, A, Rakesh, A, Jahzan, M. Fault diagnosis on journal bearing using empirical mode decomposition. Mater Today Proc 2018;5:12993–3002. https://doi.org/10.1016/j.matpr.2018.02.284.Search in Google Scholar
22. Rojas, A, Gorriz, JM, Ramirez, J, Illàn, IA, Martinez-Murcia, FJ, Ortiz, A. et al.Application of empirical mode decomposition (EMD) on DaTSCAN SPECT images to explore Parkinson disease. Expert Syst Appl 2013;40:2756–66. https://doi.org/10.1016/j.eswa.2012.11.017.Search in Google Scholar
23. Luo, Z, Liu, T, Yan, S, Qian, M. Revised empirical wavelet transform based on auto-regressive power spectrum and its application to the mode decomposition of deployable structure. J Sound Vib 2018;431:70–87. https://doi.org/10.1016/j.jsv.2018.06.001.Search in Google Scholar
24. Pachori, RB. Discrimination between ictal and seizure-free eeg signals using empirical mode decomposition. Res Lett Signal Process 2008;2008. https://doi.org/10.1155/2008/293056.Search in Google Scholar
25. Djemili, R, Bourouba, H, Amara Korba, M. Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals. Biocybern Biomed Eng 2016;36:285–91. https://doi.org/10.1016/j.bbe.2015.10.006.Search in Google Scholar
26. Shafiul Alam, SM, Bhuiyan, MIH. Detection of seizure and epilepsy using higher order statistics in the EMD domain. IEEE J Biomed Health Inf 2013;17:312–8. https://doi.org/10.1109/jbhi.2012.2237409.Search in Google Scholar PubMed
27. 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 Contr 2018;39:94–102. https://doi.org/10.1016/j.bspc.2017.07.022.Search in Google Scholar
28. Zhang, T, Chen, W, Li, M. AR based quadratic feature extraction in the VMD domain for the automated seizure detection of EEG using random forest classifier. Biomed Signal Process Contr 2017;31:550–9. https://doi.org/10.1016/j.bspc.2016.10.001.Search in Google Scholar
29. Bijoy Das, A, Bhuiyan, MI. Discrimination and classification of focal and non focal EEG signals using entropy based features in the EMD-DWT domain. Biomed Signal Process Contr 2016;29:11–21. https://doi.org/10.1016/j.bspc.2016.05.004.Search in Google Scholar
30. Qingfang, M, Shanshan, C, Haihong, L, Yunxia, L, Dong, W. Detection of epileptic seizure in EEG using sparse representation and EMD. In Advances in Neural Networks-ISNN 2017. 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II.Search in Google Scholar
31. Sivasankari, K, Thanushkodi, K. An improved EEG signal classification using neural network with the consequence of ICA and STFT. J Electr Eng Technol 2014;9:1060–71. https://doi.org/10.5370/jeet.2014.9.3.1060.Search in Google Scholar
32. Zhang, T, Chen, W, Li, M. Recognition of epilepsy electroencephalography based on AdaBoost algorithm. Acta Phys Sin 2015;64:128701. https://doi.org/10.7498/aps.64.128701.Search in Google Scholar
33. Acharya, UR, Sree, SV, Alvin, AP, Yanti, R, Suri, JS. Application of non-linear and wavelet based features for the automated identification of epileptic EEG signals. Int J Neural Syst 2012;22:565–79. https://doi.org/10.1142/S0129065712500025.Search in Google Scholar PubMed
34. Subasi, A. Selection of optimal AR spectral estimation method for EEG signals using Cramer–Rao bound. Comput Biol Med 20074;37:183–94. https://doi.org/10.1016/j.compbiomed.2005.12.001.10.1016/j.compbiomed.2005.12.001Search in Google Scholar PubMed
35. Andrzejak, RG, Lehnertz, K, Monmann, 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 2001;64:061907. https://doi.org/10.1103/PhysRevE.64.061907.Search in Google Scholar PubMed
36. Burg, JP. A new analysis technique for time series data. In: Childers, DG, editor. NATO Adv. Study Inst. on Signal Processing with Emphasis on Underwater Acoustics. Enschede, The Netherlands: Aug. 1968 , reprinted in Modern Spectrum Analysis. IEEE; 1978:42–8 pp.Search in Google Scholar
37. Fay, MP, Proschan, AM. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Stat Surv 2010;4:1–39. https://doi.org/10.1214/09-SS051.Search in Google Scholar PubMed PubMed Central
38. Young, A. Handbook of pattern recognition and image processing, 1st ed. Academic Press; 1986.Search in Google Scholar
39. Fagerland, MW. t-tests, non-parametric tests, and large studies—a paradox of statistical practice?. BioMed Central Med Res Meth 2012;12:12–78. https://doi.org/10.1186/1471-2288-12-78.Search in Google Scholar PubMed PubMed Central
40. Acharya, UR, Faust, O, Kadri, NA, Suri, JA, Yu, W. Automated identification of normal and diabetes heart rate signals using nonlinear measures. Comput Biol Med 2013;43:1523–29. https://doi.org/10.1016/j.compbiomed.2013.05.024.Search in Google Scholar PubMed
41. Padma Shri, TK, Sriraam, N. Comparison of t-test ranking with PCA and SEPCOR feature selection for wake and stage 1 sleep pattern recognition in multichannel electroencephalograms. Biomed Signal Process Contr 2017;31:499–512. https://doi.org/10.1016/j.bspc.2016.09.016.Search in Google Scholar
42. Mann, HB, Whitney, DR. On a test of whether one of two random variables is stochastically larger than the other. Ann Math Statist 1947;18:50–60. https://doi.org/10.1214/aoms/1177730491.Search in Google Scholar
43. McKight, PE, Najab, J. Kruskal-Wallis test, the Corsini encyclopedia of psychology . John Wiley & Sons; 2010. https://doi.org/10.1002/9780470479216.corpsy0491.Search in Google Scholar
44. Sharma, R, Pachori, RB. Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions. Expert Syst Appl 2015;42:1106–17. https://doi.org/10.1016/j.eswa.2014.08.030.Search in Google Scholar
45. Khan, SA, Hussain, A, Nasit, A, Akram, S. Kruskal-Wallis based computationally efficient feature selection for face recognition. Sci World J 2014;2014:672630. https://doi.org/10.1155/2014/672630.Search in Google Scholar PubMed PubMed Central
46. Varma, S, Simon, R. Bias in error estimation when using cross-validation for model selection. BMC Bioinf 2006;7:9. https://doi.org/10.1186/1471-2105-7-91.Search in Google Scholar PubMed PubMed Central
47. Willis, BH, Riley, RD. Measuring the statistical validity of summary meta-analysis and meta-regression results for use in clinical practice. Stat Med 2017;36:3283–301. https://doi.org/10.1002/sim.7372.Search in Google Scholar PubMed PubMed Central
48. Kaya, Y, Uyar, M, Tekin, R, Yildirim, S. 1D-local binary pattern based feature extraction for classification of epileptic EEG signals. Appl Math Comput 2014;243:2009–19. https://doi.org/10.1016/j.amc.2014.05.128.Search in Google Scholar
49. Orhan, U, Hekim, M, Ozer, M. EEG signals classification using the K-means clustering and a multilayer perceptron neural network model. Expert Syst Appl 2011;35:13475–81. https://doi.org/10.1016/j.eswa.2011.04.149.Search in Google Scholar
50. Siuly, S, Li, Y, Wen, P. Clustering technique-based least square support vector machine for EEG signal classification. Comput Methods Progr Biomed 2011;104:358–72. https://doi.org/10.1016/j.cmpb.2010.11.014.Search in Google Scholar PubMed
51. Hassan, AR, Siuly, S, Zhang, Y. Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating. Comput Methods Progr Biomed 2016;137:247–59. https://doi.org/10.1016/j.cmpb.2016.09.008.Search in Google Scholar PubMed
52. Nicolaou, N, Georgiou, J. Detection of epileptic electroencephalogram based on permutation entropy and support vector machine. Expert Syst Appl 2012;39:202–9. https://doi.org/10.1016/j.eswa.2011.07.008.Search in Google Scholar
53. Song, JL, Hu, W, Zhang, R. Automated detection of epileptic EEGs using a novel fusion feature and extreme learning machine. Neurocomputing 2016;175:383–91. https://doi.org/10.1016/j.neucom.2015.10.070.Search in Google Scholar
54. Joshi, V, Pachori, RB, Vijesh, A. Classification of ictal and seizure-free EEG signals using fractional linear prediction. Biomed Signal Process Contr 2014;9:1–5. https://doi.org/10.1016/j.bspc.2013.08.006.Search in Google Scholar
55. Kumar, Y, Dewal, ML, Anand, RS. Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network. SIViP 2012. https://doi.org/10.1007/s11760-012-0362-9.Search in Google Scholar
56. Sharmila, A, Geethanjali, P. DWT based detection of epileptic seizure from EEG Signals using Naïve Bayes and k-NN Classifiers. IEEE Access 2016;4:7716–27. https://doi.org/10.1109/access.2016.2585661.Search in Google Scholar
57. 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;26:925–35. https://doi.org/10.1109/tnsre.2018.2818123.Search in Google Scholar PubMed
58. Raghu, S, Sriraam, N. Optimal configuration of multilayer perceptron neural network classier for recognition of intracranial epileptic seizures. Expert Syst Appl 2017;89:205–21. https://doi.org/10.1016/j.eswa.2017.07.029.Search in Google Scholar
59. Siuly, S, Li, Y, Wen, P. EEG signal classification based on simple random sampling technique with least square support vector machine. Int J Biomed Eng Technol 2011;7:390–409. https://doi.org/10.1504/ijbet.2011.044417.Search in Google Scholar
60. Patidar, S, Panigrahi, T. Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals. Biomed Signal Process Contr 2017;34:74–80. https://doi.org/10.1016/j.bspc.2017.01.001.Search in Google Scholar
61. Bhattacharyya, A, Pachori, RB, Upadhyay, A, Acharya, UR. Tunable-Q wavelet transform based multi-scale entropy measure for automated classification of epileptic EEG signals. Appl Sci 2017;7:1–18. https://doi.org/10.3390/app7040385.Search in Google Scholar
62. Sharma, M, Pachori, RB, Acharya, UR. A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recogn Lett 2017;94:172–9. https://doi.org/10.1016/j.patrec.2017.03.023.Search in Google Scholar
63. Jaiswal, AK, Banka, H. Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals. Biomed Signal Process Contr 2017;34:81–92. https://doi.org/10.1016/j.bspc.2017.01.005.Search in Google Scholar
64. Gupta, V, Pachori, RB. Epileptic seizure identification using entropy of FBSE based EEG rhythms. Biomed Signal Process Contr 2019;53:101569. https://doi.org/10.1016/j.bspc.2019.101569.Search in Google Scholar
65. Bathi, D, Sharma, M, Pachori, RB, Gadre, VM. Time–frequency localized three-band biorthogonal wavelet filter bank using semi definite relaxation and nonlinear least squares with epileptic seizure EEG signal classification. Digit Signal Process 2017;62:259–73. https://doi.org/10.1016/j.dsp.2016.12.004.Search in Google Scholar
66. Sharma, RR, Varshney, P, Pachori, RB, Vishvakarma, SK. Automated system for epileptic EEG detection using iterative filtering. Sensor Signal Process 2018;2:7001904. https://doi.org/10.1109/LSENS.2018.2882622.Search in Google Scholar
67. Sharma, RR, Pachori, RB. Time–frequency representation using IEVDHM–HT with application to classification of epileptic EEG signals. IET Sci Meas Technol 2018;12:72–82. https://doi.org/10.1049/iet-smt.2017.0058.Search in Google Scholar
68. Kumar, TS, Kanhangad, V, Pachori, RB. Classification of seizure and seizure-free EEG signals using local binary patterns. Biomed Signal Process Contr 2018;15:33–40. https://doi.org/10.1016/j.bspc.2014.08.014.Search in Google Scholar
69. Pachori, RB, Patidar, S. Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions. Comput Methods Progr Biomed 2014;113:494–502. https://doi.org/10.1016/j.cmpb.2013.11.014.Search in Google Scholar PubMed
70. Djemili, R, Boubchir, L. Autoregressive modeling based empirical mode decomposition (EMD) for epileptic seizures detection using EEG signals. Trait Du Signal 2019;36:273–9. https://doi.org/10.18280/ts.360311.Search in Google Scholar
71. Deriche, M, Arafat, S, Al-Insaif, S, Siddiqi, M. Eigenspace time frequency based features for accurate seizure detection from EEG data. IRBM 2019;40:122–32. https://doi.org/10.1016/j.irbm.2019.02.002.Search in Google Scholar
72. Raghu, S, Sriraam, N, Hedge, 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.Search in Google Scholar
73. Amin, HU, Yusoff, MZ, Ahmad, RF. A novel approach based on wavelet analysis and arithmetic coding forautomated detection and diagnosis of epileptic seizure in EEG signalsusing machine learning techniques. Biomed Signal Process Contr 2020;56:101707. https://doi.org/10.1016/j.bspc.2019.101707.Search in Google Scholar
74. Li, Y, Cui, W-G, Huang, H, Guo, YZ, Li, K, Tan, T. Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the Fisher vector approach. Knowl Base Syst 2019;164:96–106. https://doi.org/10.1016/j.knosys.2018.10.029.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
