000200114 001__ 200114
000200114 005__ 20190812205802.0
000200114 0247_ $$2doi$$a10.3217/978-3-85125-378-8-64
000200114 037__ $$aCONF
000200114 245__ $$aLatency correction of error-related potentials reduces BCI calibration time
000200114 269__ $$a2014
000200114 260__ $$c2014
000200114 336__ $$aConference Papers
000200114 520__ $$aCalibration of brain-machine interfaces exploiting event-related potentials has to be performed for each experimental paradigm. Even if these signals have been used in previous experiments with different protocols. We show that use of signals from previous experiments can reduce the calibration time for single-trial classification of error-related potentials. Compensating latency variations across tasks yield up to a 50% reduction the training period in new experiments without decrease in online performance compared to the standard training.
000200114 700__ $$0247943$$g212988$$aIturrate, Inaki
000200114 700__ $$0241256$$g137762$$aChavarriaga, Ricardo
000200114 700__ $$aMontesano, Luis
000200114 700__ $$aMinguez, Javier
000200114 700__ $$aMillán, José del R.$$g149175$$0240030
000200114 7112_ $$dSeptember 16-19, 2014$$cGraz, Austria$$a6th Brain-Computer Interface Conference 2014
000200114 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/200114/files/2014_OnlineLatencyCorrection.pdf$$s2525412
000200114 909C0 $$xU12103$$pCNBI$$0252018
000200114 909C0 $$0252517$$xU12599$$pCNP
000200114 909C0 $$xU12367$$pNCCR-ROBOTICS$$0252409
000200114 909CO $$qGLOBAL_SET$$pconf$$pSTI$$ooai:infoscience.tind.io:200114
000200114 917Z8 $$x137762
000200114 917Z8 $$x137762
000200114 917Z8 $$x137762
000200114 917Z8 $$x149175
000200114 937__ $$aEPFL-CONF-200114
000200114 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000200114 980__ $$aCONF