Abstract
Many endogenous and external components may affect the physiological, mental and behavioral states in humans. Monitoring tools are required to evaluate biomarkers, identify biological events, and predict their outcomes. Being one of the valuable indicators, brain biomarkers derived from temporal or spectral electroencephalography (EEG) signals processing, allow for the classification of mental disorders and mental tasks. An EEG signal has a non-stationary nature and individual frequency feature, hence it can be concluded that each subject has peculiar timing and data to extract unique features. In order to classify data, which are collected by performing four mental task (reciting the alphabet backwards, imagination of rotation of a cube, imagination of right hand movements (open/close) and performing mathematical operations), discriminative features were extracted using four competitive time-frequency techniques; Wavelet Packet Decomposition (WPD), Morlet Wavelet Transform (MWT), Short Time Fourier Transform (STFT) and Wavelet Filter Bank (WFB), respectively. The extracted features using both time and frequency domain information were then reduced using a principal component analysis for subset reduction. Finally, the reduced subsets were fed into a multi-layer perceptron neural network (MP-NN) trained with back propagation (BP) algorithm to generate a predictive model. This study mainly focuses on comparing the relative performance of time-frequency feature extraction methods that are used to classify mental tasks. The real-time (RT) conducted experimental results underlined that the WPD feature extraction method outperforms with 92% classification accuracy compared to three other aforementioned methods for four different mental tasks.
Article PDF
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
M. Espinilla, J. Montero, J. Tinguaro, Computational intelligence in decision making, Int J Comput Intell Appl, 7(1) 2014, pp.1–5.
Seung-Hyeon O., Yu-Ri L., Hyoung-Nam K: A Novel EEG Feature Extraction Method Using Hjorth Parameter, Int J Electron Electric Eng, 2014, 2(2) pp.106–110.
Garrett, D., A.P. David, M.H. Thaut: Comparison of linear, non-linear, and feature selection methods for EEG signal classification, IEEE Trans Rehab Eng, 2003, 11(2), pp141–144.
Wang L., Zhang X.: Improvement of mental tasks with relevant speech imagery for BCI, Measurement 91, 2016, 201–9.
Nguyen T., Khosravi A.: EEG signal classification for BCI applications by wavelets and interval type-2 fuzzy logic systems, Expert Syst Appl, 42, 2015, pp. 4370– 4380.
Zhou Z., Wan B.: Wavelet packet-based independent component analysis for feature extraction from motor imagery EEG of complex movements, Clinical Neurophysiology 123, 2012, pp.1779–1788.
Zainuddin AZ., Huong LK.,On the Use of Wavelet Neural Networks in the Task of Epileptic Seizure Detection from EEG Signals, Procedia Comput Sci, 2012, pp.149–159.
Sankar S., Nair S,: Wavelet Sub Band Entropy Based Feature Extraction Method for BCI, Procedia Comput Sci, 2015, pp.1476–1482.
Bashar S.:Classification of motor imagery movements using multivariate empirical mode decomposition and STFT based hybrid method, Eng Sci & Tech, 19(3), 2016, pp.1457–64.
Rutkowski G., Patan K.,: Comparison of Time-Frequency Feature Extraction Methods for EEG Signals Classification, Artificial Intelligence and Soft Computing Lecture Notes in Computer Science Sc, 2013, pp.320–329.
Zalay O.C., Khang E.E., Cotic M.: A Wavelet Packet-Based Algorithm for the Extraction of Neural Rhythms, Ann Biomed Eng, 37 (3), 2009, pp. 595–613.
Paul S.K., Nine M., Hasan M.: Cognitive Task Classificaiton from Wireless EEG, Brain Informatics and Health Lect Notes Comput Sci, 2015, pp.13–22.
ZA Keirn., JI Aunon: A new mode of communication between man and his surroundings. IEEE Trans Biomed Eng. 37(12), 1990, pp.1209–1214.
Vetterli M., Kovacevic J. : Wavelets and Subband Coding, Prentice-Hall, Englewood Cliffs, NJ, 1995.
Vuckovic A., Sepulveda F.: A four-class BCI based on motor imagination of the right and the left hand wrist, 1st Int. Sym. on Appl. Sci.on Biom. and Com. Tech., 2008, pp.1–4.
Robinson N., Vinod A.P: A Wavelet-CSP method to classify hand movement directions in EEG based BCI system, Inf. Comm. and Signal Processing, Int. Conf. on,2011, pp.1–5.
Yang B., Liu L., Zan P. : Wavelet Packet-Based Feature Extraction for BCI, Lect Notes Comput Sci, 2010, pp.19– 26.
Dhiman R., Saini S.: Wavelet Analysis of Electrical Signals from Brain: The Electroencephalogram, Lecture Notes of the Institute for Computer Science, Social Informatics and Telecommunications Engineering Quality, 2013, pp. 283–289.
Hramov A., Koronovskii A. Makarov V.: Time– Frequency Analysis of EEG: From Theory to Practice, Wavelets in Neuroscience Springer Series in Synergetics, 2014,pp.211–251.
Ivanovic M., Budimac Z.: Emotional Agents – State of the Art & Applications, Comput Sci Inf Sys, 2015,12(4):1121–48.
Ouyang W., Cashion K.,: Electroencephalography based brain machine interface for controlling a robotic arm, 2013 IEEE Applied Image Pattern Recognition Workshop.
Sridhar G.V., Rao P.M.: A Neural Network Approach for EEG Classification in BCI, International Journal of Computer Science and Telecommunications, 2012, 3(10), pp. 44–48.
Qin L., He B. : A wavelet-based time–frequency analysis approach for classification of motor imagery for brain– computer interface applications, J Neural Eng, 2005, pp. 65–72.
Khare V., Santhosh J., Anand S. : Classification of EEG Signals based on Neural Network to Discriminate Five Mental States, Proceedings of SPIT-IEEE Colloquium and International Conference, 2010.
Sherwood J., Derakhsani R.: On Classifiability of Wavelet Features for EEG-Based Brain-computer Interfaces, Int. Joint Conference on Neural Networks, 2009, pp.1–8.
Brodu, N., Lotte, F., Lecuyer : A. Comparative study of band-power extraction techniques for Motor Imagery classification, in CCMB, 2011, IEEE Symposium on, pp.1–6.
Mallat S.: A wavelet tour of signal processing: The sparse way,third edition, Academic Press, 2009.
Louis A., P. Maaß: Wavelets, B.G. Teubner, 1994.
Debnath, Lokenath, and Firdous Ahmad Shah. Wavelet transforms and their applications. New York: Birkhäuser, 2015.
Büssow R.: An algorithm for the continuous Morlet wavelet transform, AA (Institute of Fluid Mechanics and Engineering Acoustics, Berlin University of Technology, Mech Syst Signal Pr, 2007, 21(8), pp. 2970–2979.
Addison P: The Illustrated Wavelet Transform Handbook: Introductory Theory and Applications in Science, Engineering, Medicine and Finance, 2002, by CRC Press.
Kuzu A., Baran E., Bogosyan S. : Wavelet packet transform-based compression for teleoperation. Proceedings of the Institution of Mechanical Engineers, Part I: J. Syst. Control Eng., 2015, 229 (7), pp. 639–651.
Imah, E.M., Al Afif, F. Fanany, M.I. Jatmiko, W. Basaruddin, T.: A comparative study on Daubechies Wavelet Transformation, Kernel PCA and PCA as feature extractors for arrhythmia detection using SVM, IEEE Region 10 Conference, 2011, pp.5–9.
Tapan G., Panigrahi B.K. A comparative study of wavelet families for EEG signal classification Neurocomputing 74, 2011, pp. 3051–3057.
Chin, Zheng Yang, Kai Keng A., “Multi-class filter bank common spatial pattern for four-class motor imagery BCI.”Int. Conf. of the IEEE Eng. in Medicine and Biology Society, 2009.
Weeks M.: Digital Signal Processing Using MATLAB & Wavelets, 2nd Ed., Jones and Bartlett Publishers, USA, 2010.
Ranjeet K., A. Kumar, Rajesh K. Pandey.: ECG Signal Compression using Optimum WFB Based on Kaiser Window, Int. Conf. on Modelling Opt. and Comp. 2012, pp. 2889–2902.
Saeid S., Chambers J.A: EEG Signal Processing, Wiley, 2007.
Whittingstall, Logothetis N.K.: Frequency-Band Coupling in Surface EEG Reflects Spiking Activity in Monkey Visual Cortex, Neuron, 64 (2), 2009, pp.281–289
Abdul – Bary Raouf Suleiman, Toka Abdul-Hameed Fatehi: Features Extraction Techniques of EEG Signal for BCI Applications, Computer and Information Engineering Department, University of Mosul, Mosul, Iraq, 2011.
Widmann A., Schroder E., Maess B.:Digital filter design for electrophysiological data – a practical approach, J Neurosci Methods, 2015, 30; 250:34–46.
Daud S.S., Sudirman R.: Butterworth Bandpass and Stationary Wavelet Transform Filter Comparison for Electroencephalography Signal, Int. Conference on Intelligent Systems, Modelling and Simulation, 2015, pp. 123–126.
Priyanka K., Archana T.: Removal of Noise from EEG Signals Using Cascaded Filter - Wavelet Transforms Method, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 3 (12), 2007, 13713–13719.
Paarman L.: Design and Analysis of Analog Filters a Signal Processing Perspective, Kluwer Academic Publishers, NY, 2003.
Vigario R., Sarela J., Jousmiki V.: Independent component approach to the analysis of EEG and MEG recordings. IEEE Trans Biomed Eng. 2000, 47: 589–593.
Jung T.P., Makeig S, McKeown M.J., McKeown M.J.,: Imaging brain dynamics using independent component analysis. Proc IEEE 89, 2001, pp. 1107–1122.
Shedeed, H.A.; Issa, M.F.; El-Sayed, S.M.: Brain EEG signal processing for controlling a robotic arm, in Computer Engineering & Systems, 2013 8th Int. Conf. on, 152–157.
Fahlman S.E. : An Empirical Study of Learning Speed in Back-Propagation Networks, Technical Report, 88–162., 1988.
Kyungdoo T.: A heuristic procedure for specifying parameters in neural network models for Shewhart X-bar control chart applications. University of North Texas Denton, TX, USA, 1993.
G. Kose, H. Sever, M. Bal, A. Ustundag, Comparison of different inference algorithms for medical decision making, Int. J. Comput. Intell. Appl., 7(1), 2014, 29–44.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
About this article
Cite this article
Uyulan, C., Erguzel, T.T. Analysis of Time — Frequency EEG Feature Extraction Methods for Mental Task Classification. Int J Comput Intell Syst 10, 1280–1288 (2017). https://doi.org/10.2991/ijcis.10.1.87
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.2991/ijcis.10.1.87