Advertisement

Artificial Neural Networks Based Fusion and Classification of EEG/EOG Signals

  • Vikrant BhatejaEmail author
  • Aparna Gupta
  • Apoorva Mishra
  • Ayushi Mishra
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 863)

Abstract

Electroencephalogram (EEG) denotes to the brain waves whereas Electrooculogram (EOG) denotes the eye blinking signals. Both the signals are accompanied by various artifacts when they are recorded. Preprocessing becomes an important task in order to get rid of artifacts and use these signals in various biometric and clinical applications. Stationary Wavelet transform (SWT) with the combination of Independent Component Analysis (SWT + ICA) is used to preprocess EEG signal and Empirical Mode Decomposition (EMD) is used to preprocess EOG data. After the processing/filtering of both the signals, feature extraction is done. For the purpose of feature extraction, time delineation in the case of EOG and Auto-Regressive Modeling (AR) technique in the case of EEG signal is implemented. In order to minimize the number of features, fusion of extracted features is performed using Canonical Correlation Analysis (CCA). In order to perform dimensionality reduction, classification is performed which classifies the features into sets. Artificial Neural Network (ANN) is used to form suitable feature arrays and evaluate the classifier’s performance. The chief goal is to develop a multimodal system which possesses high classification and recognition accuracy so that biometric authentication can be performed using the combination of EEG and EOG signals.

Keywords

AR ANN CCA EEG EOG EMD SWT-ICA 

References

  1. 1.
    Klass, D.W.: The continuing challenge of artifacts in the EEG. J. EEG Technol. 35(4), 239–269 (1995)CrossRefGoogle Scholar
  2. 2.
    Tatum, W.O., Dworetzky, B.A., Schomer, D.L.: Artifact and recording concepts in EEG. J. Clin. Neurophysiol. 28(3), 252–263 (2011)CrossRefGoogle Scholar
  3. 3.
    Lay-Ekuakille, A., Vergallo, P., Griffo, G., Urooj, S., Bhateja, V., Conversano, F., Casciaro, S., Trabacca, A.: Multidimensional analysis of EEG features using advanced spectral estimates for diagnosis accuracy. In: Proceedings of Medical Measurements and Applications, pp. 237–240, IEEE (2013)Google Scholar
  4. 4.
    Abbas, S.N., Zahhad, M.A.: Eye blinking EOG signals as biometrics. In: Biometric Security and Privacy in Signal Processing, pp. 121–140. Springer, Heidelberg (24 December, 2016)Google Scholar
  5. 5.
    Lay-Ekuakille, A., Vergallo, P., Griffo, G., Conversano, F., Casciaro, S., Urooj, S., Bhateja, V., Trabacca, A.: Entropy index in quantitative EEG measurement for diagnosis accuracy. IEEE Trans. Instrum. Meas. 63(6), 1440–1450 (2014)CrossRefGoogle Scholar
  6. 6.
    Mishra, A., Bhateja, V., Gupta, A., Mishra, A.: Noise removal in EEG signal using SWT-ICA combinational approach. In: 2nd International Conference on Smart Computing and Informatics (SCI-2018)Google Scholar
  7. 7.
    Zahhad, M.A., Ahmed, S. M., Abbas, S.N.: A new multi-level approach to EEG based human authentication using eye blinking. J. Pattern Recogn. Lett. 82, 216–225 (Elsevier) (11 August, 2015)Google Scholar
  8. 8.
    Bhateja, V., Verma, R., Mehrotra, R., Urooj, S.: A non-linear approach to ECG signal processing using morphological filters. Int. J. Meas. Technol. Instrum. Eng. 3(3), 46–59 (2013)Google Scholar
  9. 9.
    Verma, R., Mehrotra, R., Bhateja, V.: An improved algorithm for noise suppression and baseline correction of ecg signals, In: Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA), pp. 733–739, Springer, Heidelberg (2013)Google Scholar
  10. 10.
    Verma, R., Mehrotra, R., Bhateja, V.: An integration of improved median and morphological filtering techniques for electrocardiogram signal processing. In: 3rd International Advance Computing Conference (IACC), pp. 1223–1228, IEEE (February 2013)Google Scholar
  11. 11.
    Anand, D., Bhateja, V., Srivastava, A., Tiwari, D.K.: An approach for the preprocessing of EMG signals using canonical correlation analysis. In: Smart Computing and Informatics, pp. 201–208, Springer, Singapore (2018)Google Scholar
  12. 12.
    Gupta, A., Bhateja, V., Mishra, A., Mishra, A.: Auto regressive modeling based feature extraction of EEG/EOG signals. In: International Conference Information and Communication Technology for Intelligent Systems (2018)Google Scholar
  13. 13.
    Gold, M., Sommer, D., Chen, M., Trustschel, U., Mandic, P.D.: Feature fusion for detection of microsleep events. In: J. VLSI Signal Process. 49(10), 329–342 (October 2007)Google Scholar
  14. 14.
    Kaur, R., Kaur, S.: An approach for image fusion using PCA and genetic algorithm. Int. J. Comput. Appl. 145(6), 54–59 (2016)Google Scholar
  15. 15.
    Zheng, Y., Wan, X., Ling, C.: An estimation method for multi-channel EEG data based on canonical correlation analysis. J. Electron. 24(3), 569–572 (2015)Google Scholar
  16. 16.
    Muller, K.R., Anderson, C.W., Birch, G.E.: Linear and nonlinear methods for brain computer interfaces. IEEE Trans. Neural Syst. Rehabil. Eng. 11(2), 165–169 (2003)CrossRefGoogle Scholar
  17. 17.
    Basheer, I.A., Hajmeer, M.: Artificial neural networks: fundamentals, computing, design and application. J. Microbiol. Methods 43(1), 3–31 (2000)CrossRefGoogle Scholar
  18. 18.
    Tiwari, D.K., Bhateja, V., Anand, D., Srivastava, A., Omar, Z.: Combination of EEMD and morphological filtering for baseline wander correction in EMG signals. In: Proceedings of 2nd International Conference on Micro-Electronics, Electromagnetics & Telecommunications, vol. 434, pp. 365–373, Springer, Heidelberg (2018)Google Scholar
  19. 19.
    Lay-Ekuakille, A., Griffo, G., Conversano, F., Casciaro, S., Massaro, A., Bhateja, V., Spano, F.: EEG signal processing and acquisition for detecting abnormalities via bio-implantable devices. In: International Symposium on Medical Measurements and Applications (MeMeA), pp. 1–5, IEEE (May, 2016)Google Scholar
  20. 20.
    Guler, I., Ubeyli, E.D.: A mixture of experts network structure for modeling doppler ultrasound blood flow signals. Comput. Biol. Med. 35(7), 565–582 (2005)CrossRefGoogle Scholar
  21. 21.
    Gautam, A., Bhateja, V., Tiwari, A., Satapathy, S.C.: An improved mammogram classification approach using back propagation neural network. In: Data Engineering and Intelligent Computing, vol. 542, pp. 369–376. Springer, Singapore (2018)Google Scholar
  22. 22.
    Mishra, A., Bhateja, V., Gupta, A., Mishra, A.: Feature fusion and classification of EEG/EOG signals. In: International Conference on Soft Computing and Signal Processing (2018)Google Scholar
  23. 23.
    Abraham, A.: Artificial neural networks. In: Handbook of Measuring System Design, 1st edn. Wiley publications, USA (2005)Google Scholar
  24. 24.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Vikrant Bhateja
    • 1
    Email author
  • Aparna Gupta
    • 1
  • Apoorva Mishra
    • 1
  • Ayushi Mishra
    • 1
  1. 1.Department of Electronics and Communication EngineeringShri Ramswaroop Memorial Group of Professional Colleges (SRMGPC)LucknowIndia

Personalised recommendations