TY - GEN
T1 - Forty-Class SSVEP-Based Brain-Computer Interface to Inter-subject Using Complex Spectrum Features
AU - Flores, Christian
AU - Attux, Romis
AU - Carvalho, Sarah N.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - The Steady-State Visually Evoked Potential (SSVEP) is one of the most popular paradigms for Brain-Computer Interface (BCI) applications. In this study, we address two challenges in designing SSVEP-based BCI. Firstly, our BCI system must be able to discriminate among the 40 available visual stimuli. In addition to the complexity brought by the high number of classes, visual stimuli flicker at close frequencies, only 0.2 Hz apart in the range of 8 to 15.8 Hz. The second challenge we addressed was the attempt to eliminate individualized system tuning. Our SSVEP-based BCI was designed using only data from subjects other than the user, that is, with cross-subject training. In the treatment of these two challenges, we extracted features with frequency and phase information for each of the 40 visual stimuli and applied them to a Linear Discriminant Analysis. The database has data from 35 subjects, so we trained with 34 subjects and tested with the remaining ones. We applied three different time windows of 1, 2 and 3 s to segment brain data and analyze the effect on classification accuracy. Our results reached an average classification, considering 40 classes, of 28.14%, 56.85% and 71.45% for a time window of 1, 2 and 3 s, respectively.
AB - The Steady-State Visually Evoked Potential (SSVEP) is one of the most popular paradigms for Brain-Computer Interface (BCI) applications. In this study, we address two challenges in designing SSVEP-based BCI. Firstly, our BCI system must be able to discriminate among the 40 available visual stimuli. In addition to the complexity brought by the high number of classes, visual stimuli flicker at close frequencies, only 0.2 Hz apart in the range of 8 to 15.8 Hz. The second challenge we addressed was the attempt to eliminate individualized system tuning. Our SSVEP-based BCI was designed using only data from subjects other than the user, that is, with cross-subject training. In the treatment of these two challenges, we extracted features with frequency and phase information for each of the 40 visual stimuli and applied them to a Linear Discriminant Analysis. The database has data from 35 subjects, so we trained with 34 subjects and tested with the remaining ones. We applied three different time windows of 1, 2 and 3 s to segment brain data and analyze the effect on classification accuracy. Our results reached an average classification, considering 40 classes, of 28.14%, 56.85% and 71.45% for a time window of 1, 2 and 3 s, respectively.
KW - Brain-Computer Interfaces
KW - Linear Discriminant Analysis
KW - Steady-State Visually Evoked Potentials
KW - spectrum features
UR - http://www.scopus.com/inward/record.url?scp=85181984925&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-49404-8_5
DO - 10.1007/978-3-031-49404-8_5
M3 - Conference contribution
AN - SCOPUS:85181984925
SN - 9783031494031
T3 - IFMBE Proceedings
SP - 44
EP - 52
BT - 9th Latin American Congress on Biomedical Engineering and 28th Brazilian Congress on Biomedical Engineering - Proceedings of CLAIB and CBEB 2022—Volume 2
A2 - Marques, Jefferson Luiz Brum
A2 - Rodrigues, Cesar Ramos
A2 - Suzuki, Daniela Ota Hisayasu
A2 - García Ojeda, Renato
A2 - Marino Neto, José
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th Latin American Congress on Biomedical Engineering, CLAIB 2022 and 28th Brazilian Congress on Biomedical Engineering, CBEB 2022
Y2 - 24 October 2022 through 28 October 2022
ER -