Enhancing detection of steady-state visual evoked potentials using frequency and harmonics of that frequency in OpenVibe
In recent years, the use of Brain Computer Interface (BCI) systems has become more popular due to rehabilitation applications, easy installation, cheapness, and so forth.Brain Computer Interface Systems can receive brain signals and input them into a computer. These signals can then be analysed. An...
Guardado en:
Autores principales: | , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/41a085924a954711a4f84d7d52bb5210 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Sumario: | In recent years, the use of Brain Computer Interface (BCI) systems has become more popular due to rehabilitation applications, easy installation, cheapness, and so forth.Brain Computer Interface Systems can receive brain signals and input them into a computer. These signals can then be analysed. An important feature of BCI systems is that they have the ability to help people with disabilities or special needs, so that these people can use the system to control external devices or computer applications.In the presented paper, we have used BCI-SSVEP-Training dataset and OpenVibe open-source software. In OpenVibe, the CSP (Common Spatial Pattern) is used to detect the frequency of the stimulus that each subject looks at. We also considered the stimulus frequency harmonics and used the FBCSP (Filter Bank Common Spatial Pattern) and compared the results with each other.This study shows that using the FBCSP algorithm with Butterworth filter and High-cut and Low-cut equal to ± 1 Hz on the considered stimuli (12, 15 and 20) can improve the classification and detection accuracy in SSVEP data while the harmonic stimuli is considered. Therefore, for frequencies of 12, 15, 20 Hertz the accuracies are 92.91%, 98.95% and 94.50% with an ITR of 76.34bitmin . |
---|