Abstract
The goal of this work is to predict the state of alertness of an individual by analyzing the brain activity through electroencephalographic data (EEG) captured with 58 electrodes. Alertness is characterized here as a binary variable that can be in a “normal” or “relaxed” state.We collected data from 44 subjects before and after a relaxation practice, giving a total of 88 records. After a pre-processing step and data validation, we analyzed each record and discriminate the alertness states using our proposed “slope criterion”.Afterwards, several commonmethods for supervised classification (k nearest neighbors, decision trees (CART), random forests, PLS and discriminant sparse PLS) were applied as predictors for the state of alertness of each subject. The proposed “slope criterion” was further refined using a genetic algorithm to select the most important EEG electrodes in terms of classification accuracy.Results show that the proposed strategy derives accurate predictive models of alertness.
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
Preview
Unable to display preview. Download preview PDF.
References
Anderson, C., Sijercic, Z.: Classification of EEG signals from four subjects during five mental tasks. In: Proceedings of the Conference on Engineering Applications in Neural Networks, London, United Kingdom, pp. 407–414 (1996)
Ben Khalifa, K., Bédoui, M., Dogui, M., Alexandre, F.: Alertness states classification by SOM and LVQ neural networks. International Journal of Information Technology 1, 131–134 (2005)
Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)
Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and regression trees. Wadsworth Advanced Books and Software (1984)
Broadhursta, D., Goodacrea, R., Ah Jonesa, A., Rowlandb, J.J., Kelp, D.B.: Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry. Analytica Chimica Acta 348, 71–86 (1997)
Cavill, R., Keun, H.C., Holmes, E., Lindon, J.C., Nicholson, J.K., Ebbels, T.M.: Genetic algorithms for simultaneous variable and sample selection in metabonomics. Bioinformatics 25, 112–118 (2009)
Cecotti, H., Graeser, A.: Convolutional neural network with embedded fourier transform for EEG classification. In: International Conference on Pattern Recognition, Tampa, Florida, pp. 1–4 (2008)
Daubechies, I.: Ten Lectures on Wavelets. SIAM (1992)
De Jong, K.A.: An Analysis of the Behavior of a Class of Genetic Adaptive Systems. PhD thesis, University of Michigan (1975)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn. Springer (2009)
Hazarika, N., Chen, J., Tsoi, C., Sergejew, A.: Classification of EEG signals using the wavelet transform. Signal Processing 59, 61–72 (1997)
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)
Jaffard, S., Meyer, Y.: Wavelet methods for pointwise regularity and local oscillations of functions. Mem. Amer. Math. Soc. 123(587) (1996)
Jasper, H.H.: Report of the committee on methods of clinical examination in electroencephalography. Electroencephalography and Clinical Neurophysiology 10, 1–370 (1958)
Lé Cao, K.-A., Rossouw, D., Robert-Granié, C., Besse, P.: Sparse PLS: Variable selection when integrating omics data. Statistical Applications in Genetics and Molecular Biology 7(Article 35) (2008)
Legrand, P.: Débruitage et interpolation par analyse de la régularité Höldérienne. Application à la modélisation du frottement pneumatique-chaussée. PhD thesis, École Centrale de Nantes et Université de Nantes (2004)
Levy Vehel, J., Seuret, S.: The 2-microlocal formalism. In: Fractal Geometry and Applications: A Jubilee of Benoit Mandelbrot, Proc. Sympos. Pure Math., vol. 72, Part 2, pp. 153–215 (2004)
Mallat, S.: A Wavelet Tour of Signal Processing, 3rd edn. Academic Press (2008)
Naitoh, P., Johnson, L.C., Lubin, A.: Modification of surface negative slow potential (CNV) in the human brain after total sleep loss. Electroencephalography and Clinical Neurophysiology 30, 17–22 (1971)
Niedermeyer, E., Lopes da Silva, F.: Electroencephalography, basic principles, clinical applications and related fields, 5th edn., ch. 9 (2005)
Obermaier, B., Guger, C., Neuper, C., Pfurtscheller, G.: Hidden markov models for online classification of single trial EEG data. Pattern Recognition Letters 22, 1299–1309 (2001)
Rosenblith, W.: Some quantifiable aspects of the electrical activity of the nervous system (with emphasis upon responses to sensory stimuli). Revs. Mod. Physics 31, 532–545 (1959)
Shaker, M.: EEG waves classifier using wavelet transform and fourier transform. International Journal of Biological and Life Sciences, 85–90 (2005)
Subasi, A., Akin, M., Kiymik, K., Erogul, O.: Automatic recognition of vigilance state by using a wavelet-based artificial neural network. Neural Comput. and Applic. 14, 45–55 (2005)
Tecce, J.J.: A CNV rebound effect. Electroencephalography and Clinical Neurophysiology 46, 546–551 (1979)
Tenenhaus, M.: La régression PLS, Théorie et Pratique (1998)
Timsit-Berthier, M., Gerono, A., Mantanus, H.: Inversion de polarité de la variation contingente négative au cours d’état d’endormissement. EEG Neurophysiol. 11, 82–88 (1981)
Vézard, L.: Réduction de dimension en apprentissage supervisé. Applications à l’étude de l’activité cérébrale. Master’s thesis, INSA de Toulouse (2010), http://www.sm.u-bordeaux2.fr/~vezard/wp-content/uploads/2012/05/rapport.pdf
Vuckovic, A., Radivojevic, V., Chen, A., Popovic, D.: Automatic recognition of alertness and drowsiness from EEG by an artificial neural network. Medical Engineering and Physics 24, 349–360 (2002)
Walter, W.G., Cooper, R., Aldridge, V., McCallum, W.C., Winter, A.: Contingent negative variation: An electric sign of sensorimotor association and expectancy in the human brain. Nature 203, 380–384 (1964)
Yeo, M., Li, X., Shen, K., Wilder-Smith, E.: Can SVM be used for automatic EEG detection of drowsiness? Safety Science 47, 115–124 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Vézard, L., Legrand, P., Chavent, M., Faïta-Aïnseba, F., Clauzel, J., Trujillo, L. (2014). Classification of EEG Signals by an Evolutionary Algorithm. In: Guillet, F., Pinaud, B., Venturini, G., Zighed, D. (eds) Advances in Knowledge Discovery and Management. Studies in Computational Intelligence, vol 527. Springer, Cham. https://doi.org/10.1007/978-3-319-02999-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-02999-3_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02998-6
Online ISBN: 978-3-319-02999-3
eBook Packages: EngineeringEngineering (R0)