Abstract
Ensemble empirical mode decomposition (EEMD) is a powerful algorithm to decompose non-linear and non-stationary signals into several components called intrinsic mode function (IMF). EEMD has been used in EEG signal analysis, where the extracted IMFs need to be chosen properly to ensure the unwanted signal is effectively excluded. However, the method of selecting IMF has not been discussed widely. For that reason, this paper presents a method for selecting an appropriate IMF based on peak frequency of power spectral density for EEG application. The IMF is selected if the peak frequency lies on the brainwave signals of interest. Then, the selected IMFs are reconstructed as a clean EEG signal. A two-class problem of EEG cognitive task database was demonstrated to observe the feasibility of the selected IMFs. Shannon entropy and kurtosis were calculated on theta, alpha, and beta subbands of the reconstructed EEG signal. Several established classifiers were employed in the classification process. Results show that the classification achieved an acceptable accuracy, which varied between 70 and 86%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Xu, J., Zhong, B.: Review on portable EEG technology in educational research. Comput. Hum. Behav. 81, 340–349 (2018). https://doi.org/10.1016/j.chb.2017.12.037
LaRocco, J., Le, M.D., Paeng, D.-G.: A systemic review of available low-cost EEG headsets used for drowsiness detection. Front. Neuroinformat. 14, 553352 (2020). https://doi.org/10.3389/fninf.2020.553352
Homan, R.W., Herman, J., Purdy, P.: Cerebral location of international 10–20 system electrode placement. Electroencephalogr. Clin. Neurophysiol. 66(4), 376–382 (1987). https://doi.org/10.1016/0013-4694(87)90206-9
James, C., Lowe, D.: Extracting information from multichannel versus single channel EEG data in epilepsy analysis. In: Hyder, A.K., Shahbazian, E., Waltz, E. (Eds.) Multisensor Fusion, vol. 1, pp. 889–895. Springer, Dordrecht (2002). https://doi.org/10.1007/978-94-010-0556-2_47
Troy M, L., Joseph T, G., Daniel P, F.: How many electrodes are really needed for EEG-based mobile brain imaging? J. Behav. Brain Sci. 2(3), 387–393 (2012). https://doi.org/10.4236/jbbs.2012.23044
So, W.K., Wong, S.W., Mak, J.N., Chan, R.H.: An evaluation of mental workload with frontal EEG. PloS ONE 12(4), e0174949 (2017). https://doi.org/10.1371/journal.pone.0174949
van Son, D., De Blasio, F.M., Fogarty, J.S., Angelidis, A., Barry, R.J., Putman, P.: Frontal EEG theta/beta ratio during mind wandering episodes. Biol. Psychol. 140, 19–27 (2019). https://doi.org/10.1016/j.biopsycho.2018.11.003
Islam, M.K., Rastegarnia, A., Yang, Z.: Methods for artifact detection and removal from scalp EEG: a review. Neurophysiologie Clinique/Clin. Neurophysiol. 46(4), 287–305 (2016). https://doi.org/10.1016/j.neucli.2016.07.002
Jiang, X., Bian, G.-B., Tian, Z.: Removal of artifacts from EEG signals: a review. Sensors 19(5), 987 (2019). https://doi.org/10.3390/s19050987
Chen, X., Xu, X., Liu, A., McKeown, M.J., Wang, Z.J.: The use of multivariate EMD and CCA for denoising muscle artifacts from few-channel EEG recordings. IEEE Trans. Instrum. Meas. 67(2), 359–370 (2017). https://doi.org/10.1109/TIM.2017.2759398
Wu, Z., Huang, N.E.: Ensemble empirical mode decomposition: a noise-assisted data analysis method. J. Adv. Adapt. Data Anal. 1(01), 1–41 (2009). https://doi.org/10.1142/S1793536909000047
Boutana, D., Benidir, M., Barkat, B.: On the selection of intrinsic mode function in EMD method: application on heart sound signal. In: 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies, pp. 1–5. IEEE (2010). https://doi.org/10.1109/ISABEL.2010.5702895
Cho, S., Shahriar, M. R., Chong, U.: Identification of significant intrinsic mode functions for the diagnosis of induction motor fault. J. Acoust. Soc. Am. 136(2), EL72-EL77 (2014). https://doi.org/10.1121/1.4885541
Kotan, S., Van Schependom, J., Nagels, G., Akan, A.: Comparison of IMF selection methods in classification of multiple sclerosis EEG data. In: Medical Technologies Congress, pp. 1–4. IEEE (2019). https://doi.org/10.1109/TIPTEKNO.2019.8895091
Junsheng, C., Dejie, Y., Yu, Y.: Research on the intrinsic mode function (IMF) criterion in EMD method. Mech. Syst. Signal Process. 20(4), 817–824 (2006). https://doi.org/10.1016/j.ymssp.2005.09.011
Peng, Z., Peter, W.T., Chu, F.: A comparison study of improved Hilbert-Huang transform and wavelet transform: application to fault diagnosis for rolling bearing. Mech. Syst. Signal Process. 19(5), 974–988 (2005). https://doi.org/10.1016/j.ymssp.2004.01.006
Kotan, S., Akan, A.: A new intrinsic mode function selection method based on power spectral density. In: Medical Technologies National Congress, pp. 1–4. IEEE (2018). https://doi.org/10.1109/TIPTEKNO.2018.8597127
Sha’abani, M.N.A.H., Fuad, N., Jamal, N., Marwan, M., Abd Wahab, M.H., Idrus, S. Z.S.: Development of cognitive and psychomotor task for EEG application with matlab-based GUI. In: IOP Conference Series: Materials Science and Engineering, pp. 012050. vol. 917, no. 1, IOP Publishing (2020). https://doi.org/10.1088/1757-899X/917/1/012050
Teplan, M.: Fundamentals of EEG measurement. Meas. Sci. Rev. 2(2), 1–11 (2002). https://www.measurement.sk/2002/S2/p2.html
Kim, D.-W., Im, C.-H.: EEG spectral analysis. In: Im, C.-H. (Ed.) Computational EEG Analysis: Methods and Applications, vol. 1, pp. 35–53. Springer, Singapore (2018). https://doi.org/10.1007/978-981-13-0908-3
Plechawska-Wójcik, M., Tokovarov, M., Kaczorowska, M., Zapała, D.: A three-class classification of cognitive workload based on EEG spectral data. J. Appl. Sci. 9(24), 5340 (2019). https://doi.org/10.3390/app9245340
Acknowledgements
The author would like to thank the Universiti Tun Hussein Onn Malaysia for awarding the author a PhD scholarship. An appreciation also goes to the Center for Diploma Studies and Faculty of Electrical Engineering for supporting the author.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sha’abani, M.N.A.H., Fuad, N., Jamal, N., Engku Mat Nasir, E.M.N. (2022). Selection of Intrinsic Mode Function in Ensemble Empirical Mode Decomposition Based on Peak Frequency of PSD for EEG Data Analysis. In: Kaiser, M.S., Ray, K., Bandyopadhyay, A., Jacob, K., Long, K.S. (eds) Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering. Lecture Notes in Networks and Systems, vol 348. Springer, Singapore. https://doi.org/10.1007/978-981-16-7597-3_17
Download citation
DOI: https://doi.org/10.1007/978-981-16-7597-3_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7596-6
Online ISBN: 978-981-16-7597-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)