TY - GEN
T1 - A motor imagery BCI experiment using wavelet analysis and spatial patterns feature extraction
AU - Carrera-León, Obed
AU - Ramirez, Juan Manuel
AU - Alarcon-Aquino, Vicente
AU - Baker, Mary
AU - D'Croz-Baron, David
AU - Gomez-Gil, Pilar
PY - 2012
Y1 - 2012
N2 - A brain computer interface (BCI) is a system that aims to control devices by analyzing brain signals patterns. In this work, a convenient time-frequency representation (TFR) for visualizing ERD/ERS phenomenon (Event related synchronization and desynchronization) based on Hilbert transform and spatial patterns is addressed, and a wavelet based feature extraction method for motor imagery tasks is presented. The feature vectors are constructed with four statistical and energy parameters obtained from wavelet decomposition, based on the sub-band coding algorithm. Experimentation with three classification methods for comparison purposes was carried out using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Support Vector Machine (SVM). In each case, ten-fold validation is used to obtain average misclassification rates.
AB - A brain computer interface (BCI) is a system that aims to control devices by analyzing brain signals patterns. In this work, a convenient time-frequency representation (TFR) for visualizing ERD/ERS phenomenon (Event related synchronization and desynchronization) based on Hilbert transform and spatial patterns is addressed, and a wavelet based feature extraction method for motor imagery tasks is presented. The feature vectors are constructed with four statistical and energy parameters obtained from wavelet decomposition, based on the sub-band coding algorithm. Experimentation with three classification methods for comparison purposes was carried out using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Support Vector Machine (SVM). In each case, ten-fold validation is used to obtain average misclassification rates.
KW - BCI
KW - EEG
KW - LDA
KW - Support Vector Machine
KW - Wavelet (DWT)
UR - http://www.scopus.com/inward/record.url?scp=84864248207&partnerID=8YFLogxK
U2 - 10.1109/WEA.2012.6220084
DO - 10.1109/WEA.2012.6220084
M3 - Conference contribution
AN - SCOPUS:84864248207
SN - 9781467308700
T3 - 2012 Workshop on Engineering Applications, WEA 2012
BT - 2012 Workshop on Engineering Applications, WEA 2012
T2 - 2012 Workshop on Engineering Applications, WEA 2012
Y2 - 2 May 2012 through 4 May 2012
ER -