000218356 001__ 218356
000218356 005__ 20181203024233.0
000218356 0247_ $$2doi$$a10.1088/1741-2560/13/3/036018
000218356 022__ $$a1741-2552
000218356 02470 $$2ISI$$a000375701200022
000218356 037__ $$aARTICLE
000218356 245__ $$aContext-aware adaptive spelling in motor imagery BCI
000218356 260__ $$bInstitute of Physics$$c2016$$aBristol
000218356 269__ $$a2016
000218356 300__ $$a14
000218356 336__ $$aJournal Articles
000218356 520__ $$aObjective. This work presents a first motor imagery-based, adaptive brain–computer interface (BCI) speller, which is able to exploit application-derived context for improved, simultaneous classifier adaptation and spelling. Online spelling experiments with ten able-bodied users evaluate the ability of our scheme, first, to alleviate non-stationarity of brain signals for restoring the subject’s performances, second, to guide naive users into BCI control avoiding initial offline BCI calibration and, third, to outperform regular unsupervised adaptation. Approach. Our co-adaptive framework combines the BrainTree speller with smooth-batch linear discriminant analysis adaptation. The latter enjoys contextual assistance through BrainTree’s language model to improve online expectation-maximization maximum-likelihood estimation. Main results. Our results verify the possibility to restore single-sample classification and BCI command accuracy, as well as spelling speed for expert users. Most importantly, context-aware adaptation performs significantly better than its unsupervised equivalent and similar to the supervised one. Although no significant differences are found with respect to the state-of-the-art PMean approach, the proposed algorithm is shown to be advantageous for 30% of the users. Significance. We demonstrate the possibility to circumvent supervised BCI recalibration, saving time without compromising the adaptation quality. On the other hand, we show that this type of classifier adaptation is not as efficient for BCI training purposes.
000218356 6531_ $$abrain-computer interface
000218356 6531_ $$aBCI
000218356 6531_ $$aclassifier adaptation
000218356 6531_ $$amotor imagery
000218356 6531_ $$acontext-aware
000218356 6531_ $$aspeller
000218356 6531_ $$atext-entry
000218356 700__ $$0242173$$g192137$$aPerdikis, Serafeim
000218356 700__ $$0242179$$g192497$$aLeeb, Robert
000218356 700__ $$aMillán, José del R.$$g149175$$0240030
000218356 773__ $$j13$$tJournal of Neural Engineering$$k3$$q036018
000218356 909C0 $$xU12599$$0252517$$pCNP
000218356 909C0 $$xU12103$$0252018$$pCNBI
000218356 909CO $$pSTI$$particle$$ooai:infoscience.tind.io:218356
000218356 917Z8 $$x192137
000218356 917Z8 $$x149175
000218356 937__ $$aEPFL-ARTICLE-218356
000218356 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000218356 980__ $$aARTICLE