SSVEP-EEG Signal Classification based on Emotiv EPOC BCI and Raspberry Pi

被引：7

作者：

Asanza, Victor ^{[1
]}

Aviles-Mendoza, Karla ^{[2
]}

Trivino-Gonzalez, Hector ^{[2
]}

Rosales-Uribe, Felix ^{[1
]}

Torres-Brunes, Jamil ^{[2
]}

Loayza, Francis R. ^{[2
]}

Pelaez, Enrique ^{[1
]}

Cajo, Ricardo ^{[1
,3
]}

Tinoco-Egas, Raquel ^{[4
]}

机构：

[1] Escuela Super Politecn Litoral, ESPOL, Fac Ingn Elect & Comp, Campus Gustavo Galindo Km 30-5 Via Perimetral,POB, Guayaquil, Ecuador

[2] Escuela Super Politecn Litoral, Neuroimaging & Bioengn Lab, LNB, Fac Ingn Mecan & Ciencias Prod,ESPOL, Campus Gustavo Galindo Km 30-5 Via Perimetral,POB, Guayaquil, Ecuador

[3] Univ Ghent, Dept Electromech Syst & Met Engn, Tech Lane Sci Pk 125, B-9052 Ghent, Belgium

[4] Univ Tecn Machala, UTMACH, Av Panamer Km 5 1-2 Via Pasaje Machala, El Oro, Ecuador

来源：

IFAC PAPERSONLINE | 2021年 / 54卷 / 15期

关键词：

Brain Computer Interface; SSVEP-EEG; Classification; Machine Learning; Data acquisition; XGBoost;

D O I：

10.1016/j.ifacol.2021.10.287

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This work presents the experimental design for recording Electroencephalography (EEG) signals in 20 test subjects submitted to Steady-state visually evoked potential (SSVEP). The stimuli were performed with frequencies of 7, 9, 11 and 13 Hz. Furthermore, the implementation of a classification system based on SSVEP-EEG signals from the occipital region of the brain obtained with the Emotiv EPOC device is presented. These data were used to train algorithms based on artificial intelligence in a Raspberry Pi 4 Model B. Finally, this work demonstrates the possibility of classifying with times of up to 1.8 ms in embedded systems with low computational capacity. Copyright (C) 2021 The Authors.

引用

页码：388 / 393

页数：6

共 21 条

[1] Deep learning for motor imagery EEG-based classification: A review [J].