Rede Neural Convolucional e LSTM para Biometria Baseada em EEG no Modo de Identificação

• Carlos Freitas UFOP
• Pedro Silva UFOP
• Gladston Moreira UFOP
• Eduardo Luz UFOP

DOI: https://doi.org/10.5753/sbcas.2022.222647

Abstract

With the advancement of biometrics and the need for more robust security systems, different types of human traits have been taken into consideration for biometrics. One of these traits (modalities) is the electroencephalogram (brain signals). This paper evaluates a neural network model, whose architecture combines layers of Convolutional Neural Networks (CNN) and layers of Long Short-Term Memory (LSTM) for biometrics tasks from electroencephalograms. The experimental discussion has been performed on the Physionet Motor Movement/Imagery Dataset, with data from 109 individuals. By using a window size of 12 seconds, a state-of-the-art result of 99.7% accuracy is achieved, proving the efficiency of the applied methodology for biometric identification mode.

References

Bengio, Y. (2012). Practical recommendations for gradient-based training of deep architectures. CoRR, abs/1206.5533:437-478.

Bobkowska, K., Nagaty, K., and Przyborski, M. (2019). Incorporating iris, fingerprint and face biometric for fraud prevention in e-passports using fuzzy vault. IET Image Processing, 13(13):2516-2528.

Carrión-Ojeda, D., Fonseca-Delgado, R., and Pineda, I. (2021). Analysis of factors that influence the performance of biometric systems based on eeg signals. Expert Systems with Applications, 165:113967.

Damasevicius, R., Maskeliunas, R., Kazanavicius, E., and Wozniak, M. (2018). Combining cryptography with EEG biometrics. Computational Intelligence and Neuroscience, 2018:1867548:1-1867548:11.

Das, R., Maiorana, E., and Campisi, P. (2016). Eeg biometrics using visual stimuli: A longitudinal study. IEEE Signal Processing Letters, 23(3):341-345.

Das, R., Maiorana, E., and Campisi, P. (2017). Visually evoked potential for EEG biometrics using convolutional neural network. In 25th European Signal Processing Conference, EUSIPCO 2017, August 28 September 2, 2017, pages 951-955, Kos, Greece. IEEE.

Goldberger, A. L., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., and Stanley, H. E. (2000). Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. circulation, 101(23):e215-e220.

Graves, A., Fernández, S., and Schmidhuber, J. (2005). Bidirectional LSTM networks for improved phoneme classification and recognition. In 15th International Conference on Artificial Neural Networks, pages 799-804.

Jamil, Z., Jamil, A., and Majid, M. (2021). Artifact removal from eeg signals recorded in non-restricted environment. Biocybernetics and Biomedical Engineering, 41(2):503-515.

Jijomon, C. and Vinod, A. (2021). Person-identification using familiar-name auditory evoked potentials from frontal eeg electrodes. Biomedical Signal Processing and Control, 68:102739.

Lee, Y.-Y. and Hsieh, S. (2014). Classifying different emotional states by means of eeg-based functional connectivity patterns. PloS one, 9(4):e95415.

Lin, H. W. and Tegmark, M. (2017). Critical behavior in physics and probabilistic formal languages. Entropy, 19(7):299.

Liu, Y. H. (2018). Feature extraction and image recognition with convolutional neural networks. Journal of Physics: Conference Series, 1087(6):062032.

Lumini, A. and Nanni, L. (2017). Overview of the combination of biometric matchers. Information Fusion, 33:71-85.

Mota, M. R., Silva, P. H., Luz, E. J., Moreira, G. J., Schons, T., Moraes, L. A., and Menotti, D. (2021). A deep descriptor for cross-tasking eeg-based recognition. PeerJ Computer Science, 7:e549.

Obaidat, M. S., Rana, S. P., Maitra, T., Giri, D., and Dutta, S. (2019). Biometric security and internet of things (iot). In Biometric-based physical and cybersecurity systems, pages 477-509. Springer.

Schalk, G., McFarland, D. J., Hinterberger, T., Birbaumer, N., and Wolpaw, J. R. (2004). Bci2000: a general-purpose brain-computer interface (bci) system. IEEE Transactions on biomedical engineering, 51(6):1034-1043.

Schons, T., Moreira, G. J. P., Silva, P. H. L., Coelho, V. N., and da S. Luz, E. J. (2017). Convolutional network for eeg-based biometric. In 22nd Iberoamerican Congress on Pattern Recognition, pages 601-608.

Sherstinsky, A. (2020). Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D: Nonlinear Phenomena, 404:132306.

Sun, Y., Lo, F. P.-W., and Lo, B. (2019). Eeg-based user identification system using 1d-convolutional long short-term memory neural networks. Expert Systems with Applications, 125:259-267.

Wu, Y. and Qin, Y. (2022). Machine translation of english speech: Comparison of multiple algorithms. Journal of Intelligent Systems, 31(1):159-167.

Yang, S., Deravi, F., and Hoque, S. (2018). Task sensitivity in eeg biometric recognition. Pattern Analysis and Applications, 21(1):105-117.