000168236 001__ 168236
000168236 005__ 20190812205534.0
000168236 037__ $$aCONF
000168236 245__ $$aA supervised recalibration protocol for unbiased BCI
000168236 269__ $$a2011
000168236 260__ $$c2011
000168236 336__ $$aConference Papers
000168236 520__ $$aOne important source of performance degradation in BCIs is bias towards one of the mental classes. Recent literature has focused on the general problem of classification accuracy drop, identifying non-stationarity as the generating factor, thus leading to several classifier adaptation approaches suggested as of today. In this work, we explicitly focus on bias elimination, demonstrating that the problem has two separate components, one related to non-stationarity and another one attributed to the nature of the feature distributions and the assumptions made by the classification methods. We propose a cued recalibration protocol including a supervised adaptation method and a novel framework for unbiased classification with a modified, unbiased Linear Discriminant Analysis classifier. Preliminary results show that our protocol can assist the subject to achieve quickly accurate and unbiased control of the BCI.
000168236 6531_ $$aBCI
000168236 6531_ $$aEEG
000168236 6531_ $$aMotor Imagery
000168236 6531_ $$asupervised recalibration
000168236 6531_ $$aclassifier adaptation
000168236 6531_ $$aunbiased classification
000168236 700__ $$0242173$$g192137$$aPerdikis, Serafeim
000168236 700__ $$0242176$$g190287$$aTavella, Michele
000168236 700__ $$0242179$$g192497$$aLeeb, Robert
000168236 700__ $$aChavarriaga, Ricardo$$0241256$$g137762
000168236 700__ $$0240030$$aMillán, José del R.$$g149175
000168236 7112_ $$dSeptember 22-24, 2011$$cGraz, Austria$$a5th International Brain-Computer Interface Conference 2011
000168236 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/168236/files/UnbiasGraz11.pdf$$s418800
000168236 909C0 $$xU12103$$pCNBI$$0252018
000168236 909C0 $$0252517$$xU12599$$pCNP
000168236 909CO $$qGLOBAL_SET$$pconf$$pSTI$$ooai:infoscience.tind.io:168236
000168236 917Z8 $$x192137
000168236 917Z8 $$x137762
000168236 937__ $$aEPFL-CONF-168236
000168236 973__ $$rREVIEWED$$sACCEPTED$$aEPFL
000168236 980__ $$aCONF