Uso de Machine Learning para detectar señales cerebrales de tipo P300 generando estímulos visuales y auditivos

Alejandro Jesús Perdomo Cely; Camilo Ernesto Pardo Beainy; Moshé Alonso Amarillo

doi:10.24054/rcta.v2i44.3069

Authors

Alejandro Jesús Perdomo Cely Universidad Santo Tomás https://orcid.org/0009-0006-0615-3659
Camilo Ernesto Pardo Beainy Universidad Santo Tomás https://orcid.org/0000-0003-0012-3679
Moshé Alonso Amarillo Universidad de Los Andes https://orcid.org/0000-0003-1062-1129

DOI:

https://doi.org/10.24054/rcta.v2i44.3069

Keywords:

Machine Learning, P300, electroencephalography, data augmentation

Abstract

The P300 signal is an evoked potential that occurs in the occipital region of the brain when an unexpected visual or auditory change to a light or sound pattern is presented. This pulse is commonly studied in the field of biomedicine, used in partial recovery of mobility in quadriplegic patients through a screen with different commands, in which the patient moves his eyes towards the desired command, and generating the P300 is performed. the desired command. It is from here that the Machine Learning models are used, being Logistic Regression, Decision Tree, Support Vector Machine and K Nearest Neighbors, to recognize characteristics of electroencephalographic signals with the presence and absence of P300 and an increase in data is applied to them by improving the training, in order to obtain the analysis of the best predictors of the P300 brain signal.

Downloads

Download data is not yet available.

References

B. Miner, Y. Pan, C. Burzynski, L. Iannone, M. Knauert, T. Gill and H. Yaggi, "0726 Agreement Between an Electroencephalography-Measuring Headband and Polysomnography in Older Adults with Sleep Disturbances," in Sleep, Oxford Academic, 2023, pp. A319-A320. DOI: https://doi.org/10.1093/sleep/zsad077.0726

O. A. Broggi Angulo, D. G. Koc Gonzáles y P. C. Martinez Esteban, «Guía de procedimiento de electroencefalografía y videoelectroencefalografía,» Ministerio de Salud de la República del Perú, San Borja, 2022.

Y. Zhang, H. Xu, Y. Zhao, L. Zhang y Y. Zhang, «Application of the P300 potential in cognitive impairment assessments after transient ischemic attack or minor stroke,» Neurological Research, vol. 43, nº 4, pp. 336-341, 2021. DOI: https://doi.org/10.1080/01616412.2020.1866245

J. M. Macías Macías, J. A. Ramirez Quintana, J. S. A. Méndez Aguirre, M. I. Chacón Murgia y A. D. Corral Sáenz, «Procesamiento Embebido de P300 Basado en Red Neuronal Convolucional para Interfaz Cerebro-Computadora Ubicua,» ReCIBE. Revista electrónica de Computación, Informática, Biomédica y Electrónica, vol. 9, núm. 2, pp. 1-24, 2020. DOI: https://doi.org/10.32870/recibe.v9i2.153

«Electroencefalografía (EEG),» 2018. [En línea]. Available: https://brainsigns.com/es/science/s2/technologies/eeg.

S. Silva Pereira, E. Ekin Özer and N. Sebastian-Galles, "Complexity of STG signals and linguistic rhythm: a methodological study for EEG data," Cerebral Cortex, vol. 34, no. 2, 2024. DOI: https://doi.org/10.1093/cercor/bhad549

L. E. Morillo, «ANÁLISIS VISUAL DEL ELECTROENCEFALOGRAMA,» pp. 145-153.

C. F. Blanco Díaz y A. F. Ruiz Olaya, «Caracterización de señales de EEG relacionadas a potenciales evocados visuales en estado estacionario,» Ontare, pp. 18-20, 2019. DOI: https://doi.org/10.21158/23823399.v7.n0.2019.2459

R. Chandra Poonia, V. Singh y S. Ranjan Nayak, Deep Learning for Sustainable Agriculture, A volume in Cognitive Data Science in Sustainable Computing, India: Elsevier, 2022.

M. Razavi, V. Janfaza, T. Yamauchi, A. Leontyev, S. Longmire-Monford and J. Orr, "OpenSync: An opensource platform for synchronizing multiple measures in neuroscience experiments," pp. 3-7, 2021. DOI: https://doi.org/10.1016/j.jneumeth.2021.109458

T. Mo, W. Huang, W. Sun, Y. Hu, L. Mcdonald, Z. Hu, L. Chen, J. Liao, B. Hermann, V. Prabhakaran y H. Zeng, «Activation Map Reveals Language Impairment in Children with Benign Epilepsy with Centrotemporal Spikes (BECTS),» Neuropsychiatric Disease and Treatment, vol. 19, p. 1949–1957, 2023. DOI: https://doi.org/10.2147/NDT.S419840

C. Biarnés Rabella, «Diseño, caracterización y evaluación de electrodos capacitivos para la medida de ECG y EEG,» Universitat Politécnica de Catalunya, pp. 12-15, 2018.

F. Wu, M. Gong, J. Ji, G. Peng, L. Yao, Y. Li and W. Zeng, "Interval and subinterval perturbation finite element-boundary element method for low-frequency uncertain analysis of structural-acoustic systems," Journal of Sound and Vibration, vol. 462, no. 114939, 2019. DOI: https://doi.org/10.1016/j.jsv.2019.114939

L. Bianchi, A. Antonietti, G. Bajwa, R. Ferrante, M. Mahmud y P. & Balachandran, «A functional BCI model by the IEEE P2731 working group: data storage and sharing,» Brain-Computer Interfaces, vol. 8, nº 3, p. 108–116, 2021. DOI: https://doi.org/10.1080/2326263X.2021.1968632

S. Gannouni, A. Aledaily, K. Belwafi and H. Aboalsamh, "Emotion detection using electroencephalography signals and a zero time windowing based epoch estimation and relevant electrode identifcation," Nature Portfolio, pp. 5-7, 2021. DOI: https://doi.org/10.1038/s41598-021-86345-5

I. M. Hojas, «Regresión Logística en Python,» [En línea]. Available: https://www.statdeveloper.com/regresion-logistica-en-python/.

R. Romo, «Árboles de Decisión / Decision Trees con python,» [En línea]. Available: https://rubenjromo.com/decision-trees/.

L. Gonzales, «K Vecinos más Cercanos – Teoría,» 19 Julio 2019. [En línea]. Available: https://aprendeia.com/algoritmo-k-vecinos-mas-cercanos-teoria-machine-learning/.

J. G. J. R. S. S. M. M. H. R. S. H. K. E. &. L. J. K. Peirce, «PsychoPy2: Experiments in behavior made easy.,» 2019. [En línea]. Available: https://doi.org/10.3758/s13428-018-01193-y. DOI: https://doi.org/10.3758/s13428-018-01193-y

Z. Zhang, X. Liang, W. Qin, S. Yu and Y. Xie, "matFR: a MATLAB toolbox for feature ranking," Bioinformatics, vol. 36, no. 19, p. 4968–4969, 2020. DOI: https://doi.org/10.1093/bioinformatics/btaa621