Cited 7 time in
Cited 8 time in
Minimizing inter-subject variability in fNIRS-based brain-computer interfaces via multiple-kernel support vector learning
- Minimizing inter-subject variability in fNIRS-based brain-computer interfaces via multiple-kernel support vector learning
- Abibullaev, B[Abibullaev, Berdakh]; An, J[An, Jinung]; Jin, SH[Jin, Sang-Hyeon]; Lee, SH[Lee, Seung Hyun]; Moon, JI[Moon, Jeon Il]
- DGIST Authors
- An, J[An, Jinung]; Jin, SH[Jin, Sang-Hyeon]; Moon, JI[Moon, Jeon Il]
- Issue Date
- Medical Engineering and Physics, 35(12), 1811-1818
- Article Type
- Adult; Algorithms; Brain-Computer Interfaces; Brain Computer Interface; Classification Algorithm; Classifier; Decision Boundary; Functional Near-Infrared Spectroscopies; Functional Near-Infrared Spectroscopy (FNIRS); Human; Human Experiment; Humans; Inter-Subject Variability; Interfaces (Computer); Kernel Method; Mental Task; Multiple Kernel Learning; Near-Infrared Spectroscopy; Normal Human; Oxyhemoglobin; Priority Journal; Reproducing Kernel Hilbert Spaces; RKHS; Spectrophotometry, Infrared; Support Vector Learning; Support Vector Machine; Support Vector Machines; System Analysis
- 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. © 2013 IPEM.
- Elsevier Ltd
- Related Researcher
There are no files associated with this item.
- Convergence Research Center for Collaborative Robots1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.