Discriminador binario de imaginación visual a partir de señales EEG basado en redes neuronales convolucionales

Fabio Ricardo Llorella Costa, Eduardo Iáñez, José Maria Azorín, Gustavo Patow

Resumen

La interfaz cerebro-máquina (Brain-Computer Intarface, BCI, en inglés) es una tecnología que permite la comunicación directaentre el cerebro y el mundo exterior sin necesidad de utilizar el sistema nervioso perif ́erico. La mayoría de sistemas BCI se centranen la utilización de la imaginación motora, los potenciales evocados o los ritmos corticales lentos. En este trabajo se ha estudiadola posibilidad de utilizar la imaginación visual para construir un discriminador binario (brain-switch, en inglés). Concretamente,a partir del registro de señales EEG de siete personas mientras imaginaban siete figuras geométricas, se ha desarrollado un BCIbasado en redes neuronales convolucionales y en la densidad de potencia espectral en la banda α(8-12) Hz, que ha conseguidodistinguir entre la imaginación de una figura geométrica cualquiera y el relax, con un acierto promedio del 91 %, con un valor Kappa de Cohen de 0.77 y una porcentaje de falsos positivos del 9 %

Palabras clave

Brain-Switch; Imaginación visual;red neuronal convolucional;EEG

Clasificación por materias

Aprendizaje automático aplicado a la bioingeniería o medicina;Control automático de sistemas biomédicos o en bioingeniería;Interfaces inteligentes para control de sistemas en bioingeniería o medicina

Texto completo:

PDF

Referencias

Abhiram, Singh, A., Gumaste, 2019. Decoding imagined speech and computercontrol using brain waves. arXiv.

Aggarwal, S., Chugh, N., Jan. 2019. Signal processing techniques for motorimagery brain computer interface: A review. Array 1-2, 100003.URL:https://doi.org/10.1016/j.array.2019.100003DOI:10.1016/j.array.2019.100003

Ahn, M., Lee, M., Choi, J., Jun, S., Aug. 2014. A review of brain-computer in-terface games and an opinion survey from researchers, developers and users.Sensors 14 (8), 14601–14633.URL:https://doi.org/10.3390/s140814601DOI:10.3390/s140814601

Altman, D. G., 2006. Practical Statistics for Medical Research. Chapman &Hall/CRC.

Bigdely-Shamlo, N., Mullen, T., Kothe, C., Su, K.-M., Robbins, K. A., Jun.2015. The PREP pipeline: standardized preprocessing for large-scale EEGanalysis. Frontiers in Neuroinformatics 9.URL:https://doi.org/10.3389/fninf.2015.00016DOI:10.3389/fninf.2015.00016

Birbaumer, N., Ghanayim, N., Hinterberger, T., Iversen, I., Kotchoubey, B.,K ̈ubler, A., Perelmouter, J., Taub, E., Flor, H., Mar. 1999. A spelling de-vice for the paralysed. Nature 398 (6725), 297–298.URL:https://doi.org/10.1038/18581DOI:10.1038/18581

Bobrov, P., Frolov, A., Cantor, C., Fedulova, I., Bakhnyan, M., Zhavoronkov,A., Jun. 2011. Brain-computer interface based on generation of visual ima-ges. PLoS ONE 6 (6), e20674.URL:https://doi.org/10.1371/journal.pone.0020674DOI:10.1371/journal.pone.0020674

Craik, A., He, Y., Contreras-Vidal, J. L., Apr. 2019. Deep learning for elec-troencephalogram (EEG) classification tasks: a review. Journal of NeuralEngineering 16 (3), 031001.URL:https://doi.org/10.1088/1741-2552/ab0ab5DOI:10.1088/1741-2552/ab0ab5

Esfahani, E. T., Sundararajan, V., Oct. 2012. Classification of primitive shapesusing brain–computer interfaces. Computer-Aided Design 44 (10), 1011–1019.URL:https://doi.org/10.1016/j.cad.2011.04.008DOI:10.1016/j.cad.2011.04.008

Fernando, L., Nicolas-Alonso, J., Gomez-Gil, 2012. Brain computer interface,a review. Sensors 12 (2), 1211–1279

Gavali, P., Banu, J. S., 2019. Deep convolutional neural network for image clas-sification on CUDA platform. En: Deep Learning and Parallel ComputingEnvironment for Bioengineering Systems. Elsevier, pp. 99–122.URL:https://doi.org/10.1016/b978-0-12-816718-2.00013-0DOI:10.1016/b978-0-12-816718-2.00013-0

Gong, M., Xu, G., Li, M., Lin, F., May 2020. An idle state-detecting methodbased on transient visual evoked potentials for an asynchronous ERP-basedBCI. Journal of Neuroscience Methods 337, 108670.URL:https://doi.org/10.1016/j.jneumeth.2020.108670DOI:10.1016/j.jneumeth.2020.108670

Han, C.-H., M ̈uller, K.-R., Hwang, H.-J., Mar. 2020. Brain-switches for asyn-chronous brain–computer interfaces: A systematic review. Electronics 9 (3),422.URL:https://doi.org/10.3390/electronics9030422DOI:10.3390/electronics9030422

Hortal, E., Planelles, D., Resquin, F., Climent, J. M., Azor ́ın, J. M., Pons, J. L.,Oct. 2015. Using a brain-machine interface to control a hybrid upper limbexoskeleton during rehabilitation of patients with neurological conditions.Journal of NeuroEngineering and Rehabilitation 12 (1).URL:https://doi.org/10.1186/s12984-015-0082-9DOI:10.1186/s12984-015-0082-9

Jiang, J., Zhou, Z., Yin, E., Yu, Y., Liu, Y., Hu, D., Nov. 2015. A novel morsecode-inspired method for multiclass motor imagery brain–computer interfa-ce (BCI) design. Computers in Biology and Medicine 66, 11–19.URL:https://doi.org/10.1016/j.compbiomed.2015.08.011DOI:10.1016/j.compbiomed.2015.08.011

Jurcak, V., Tsuzuki, D., Dan, I., Feb. 2007. 10/20, 10/10, and 10/5 systemsrevisited: Their validity as relative head-surface-based positioning systems.NeuroImage 34 (4), 1600–1611.URL:https://doi.org/10.1016/j.neuroimage.2006.09.024DOI:10.1016/j.neuroimage.2006.09.024

Kim, C., Sun, J., Liu, D., Wang, Q., Paek, S., Mar. 2018. An effective featureextraction method by power spectral density of EEG signal for 2-class mo-tor imagery-based BCI. Medical & Biological Engineering & Computing56 (9), 1645–1658.URL:https://doi.org/10.1007/s11517-017-1761-4DOI:10.1007/s11517-017-1761-4

Knauff, M., Kassubek, J., Mulack, T., Greenlee, M. W., Dec. 2000. Corticalactivation evoked by visual mental imagery as measured by fMRI. Neuro-Report 11 (18), 3957–3962.URL:https://doi.org/10.1097/00001756-200012180-00011DOI:10.1097/00001756-200012180-00011

Kosmyna, N., Lindgren, J. T., L ́ecuyer, A., Sep. 2018. Attending to visual sti-muli versus performing visual imagery as a control strategy for EEG-basedbrain-computer interfaces. Scientific Reports 8 (1).URL:https://doi.org/10.1038/s41598-018-31472-9DOI:10.1038/s41598-018-31472-9

Lotte, F., Congedo, M., L ́ecuyer, A., Lamarche, F., Arnaldi, B., Jan. 2007. A re-view of classification algorithms for EEG-based brain–computer interfaces.Journal of Neural Engineering 4 (2), R1–R13.URL:https://doi.org/10.1088/1741-2560/4/2/r01DOI:10.1088/1741-2560/4/2/r01

McCall, J., Dec. 2005. Genetic algorithms for modelling and optimisation. Jour-nal of Computational and Applied Mathematics 184 (1), 205–222.URL:https://doi.org/10.1016/j.cam.2004.07.034DOI:10.1016/j.cam.2004.07.034

Proakis, John, M., Dimitri, 1996. Digital signal processing: principles, algo-rithms and applications. Prentice-Hall, 910–913.

Reza, Abiri, S., Borhani, E. W., Sellers, Y., Jiang, X., Zhao, 2018. A com-prehensive review of eeg-based brain-computer interface paradigms. Journalof Neural Engineering 16.

Seeck, M., Koessler, L., Bast, T., Leijten, F., Michel, C., Baumgartner, C., He,B., Beniczky, S., Oct. 2017. The standardized EEG electrode array of theIFCN. Clinical Neurophysiology 128 (10), 2070–2077.URL:https://doi.org/10.1016/j.clinph.2017.06.254DOI:10.1016/j.clinph.2017.06.254

Swets, J., 2014. Signal detection theory and ROC analysis in psychology anddiagnostics : collected papers. Psychology Press, New York, New York Ho-ve, England.

Xie, S., Kaiser, D., Cichy, R. M., Aug. 2020. Visual imagery and perceptionshare neural representations in the alpha frequency band. Current Biology30 (15), 3062.URL:https://doi.org/10.1016/j.cub.2020.07.023DOI:10.1016/j.cub.2020.07.023

Zhang, W., Tan, C., Sun, F., Wu, H., Zhang, B., Dec. 2018. A review of EEG-based brain-computer interface systems design. Brain Science Advances4 (2), 156–167.URL:https://doi.org/10.26599/bsa.2018.9050010DOI:10.26599/bsa.2018.9050010

Abstract Views

287
Metrics Loading ...

Metrics powered by PLOS ALM




Creative Commons License

Esta revista se publica bajo una Licencia Creative Commons Attribution-NonCommercial-CompartirIgual 4.0 International (CC BY-NC-SA 4.0)

Universitat Politècnica de València     https://doi.org/10.4995/riai

e-ISSN: 1697-7920     ISSN: 1697-7912