TY - JOUR
T1 - Minimizing inter-subject variability in fNIRS-based brain-computer interfaces via multiple-kernel support vector learning
AU - Abibullaev, Berdakh
AU - An, Jinung
AU - Jin, Sang Hyeon
AU - Lee, Seung Hyun
AU - Moon, Jeon Il
PY - 2013/12/1
Y1 - 2013/12/1
N2 - Brain signal variation across different subjects and sessions significantly impairs the accuracy of most brain-computer interface (BCI) systems. Herein, we present a classification algorithm that minimizes such variation, using linear programming support-vector machines (LP-SVM) and their extension to multiple kernel learning methods. The minimization is based on the decision boundaries formed in classifiers' feature spaces and their relation to BCI variation. Specifically, we estimate subject/session-invariant features in the reproducing kernel Hilbert spaces (RKHS) induced with Gaussian kernels. The idea is to construct multiple subject/session-dependent RKHS and to perform classification with LP-SVMs. To evaluate the performance of the algorithm, we applied it to oxy-hemoglobin data sets acquired from eight sessions and seven subjects as they performed two different mental tasks. Results show that our classifiers maintain good performance when applied to random patterns across varying sessions/subjects.
AB - Brain signal variation across different subjects and sessions significantly impairs the accuracy of most brain-computer interface (BCI) systems. Herein, we present a classification algorithm that minimizes such variation, using linear programming support-vector machines (LP-SVM) and their extension to multiple kernel learning methods. The minimization is based on the decision boundaries formed in classifiers' feature spaces and their relation to BCI variation. Specifically, we estimate subject/session-invariant features in the reproducing kernel Hilbert spaces (RKHS) induced with Gaussian kernels. The idea is to construct multiple subject/session-dependent RKHS and to perform classification with LP-SVMs. To evaluate the performance of the algorithm, we applied it to oxy-hemoglobin data sets acquired from eight sessions and seven subjects as they performed two different mental tasks. Results show that our classifiers maintain good performance when applied to random patterns across varying sessions/subjects.
KW - Brain-computer interfaces
KW - Functional near-infrared spectroscopy
KW - Inter-subject variability
KW - Multiple kernel learning
KW - RKHS
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=84889593590&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84889593590&partnerID=8YFLogxK
U2 - 10.1016/j.medengphy.2013.08.009
DO - 10.1016/j.medengphy.2013.08.009
M3 - Article
C2 - 24054981
AN - SCOPUS:84889593590
VL - 35
SP - 1811
EP - 1818
JO - Medical Engineering and Physics
JF - Medical Engineering and Physics
SN - 1350-4533
IS - 12
ER -