Cited 7 time in webofscience Cited 8 time in scopus

Minimizing inter-subject variability in fNIRS-based brain-computer interfaces via multiple-kernel support vector learning

Title
Minimizing inter-subject variability in fNIRS-based brain-computer interfaces via multiple-kernel support vector learning
Authors
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
2013-12
Citation
Medical Engineering and Physics, 35(12), 1811-1818
Type
Article
Article Type
Article
Keywords
AdultAlgorithmsBrain-Computer InterfacesBrain Computer InterfaceClassification AlgorithmClassifierDecision BoundaryFunctional Near-Infrared SpectroscopiesFunctional Near-Infrared Spectroscopy (FNIRS)HumanHuman ExperimentHumansInter-Subject VariabilityInterfaces (Computer)Kernel MethodMental TaskMultiple Kernel LearningNear-Infrared SpectroscopyNormal HumanOxyhemoglobinPriority JournalReproducing Kernel Hilbert SpacesRKHSSpectrophotometry, InfraredSupport Vector LearningSupport Vector MachineSupport Vector MachinesSystem Analysis
ISSN
1350-4533
Abstract
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.
URI
http://hdl.handle.net/20.500.11750/1688
DOI
10.1016/j.medengphy.2013.08.009
Publisher
Elsevier Ltd
Related Researcher
Files:
There are no files associated with this item.
Collection:
Convergence Research Center for Collaborative Robots1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE