000061483 001__ 61483
000061483 005__ 20170612112602.0
000061483 0247_ $$2doi$$a10.1371/journal.pone.0061976
000061483 0248_ $$2sideral$$a81242
000061483 037__ $$aART-2013-81242
000061483 041__ $$aeng
000061483 100__ $$0(orcid)0000-0003-3377-0813$$aAntelis, J.M.
000061483 245__ $$aOn the Usage of Linear Regression Models to Reconstruct Limb Kinematics from Low Frequency EEG Signals
000061483 260__ $$c2013
000061483 5060_ $$aAccess copy available to the general public$$fUnrestricted
000061483 5203_ $$aSeveral works have reported on the reconstruction of 2D/3D limb kinematics from low-frequency EEG signals using linear regression models based on positive correlation values between the recorded and the reconstructed trajectories. This paper describes the mathematical properties of the linear model and the correlation evaluation metric that may lead to a misinterpretation of the results of this type of decoders. Firstly, the use of a linear regression model to adjust the two temporal signals (EEG and velocity profiles) implies that the relevant component of the signal used for decoding (EEG) has to be in the same frequency range as the signal to be decoded (velocity profiles). Secondly, the use of a correlation to evaluate the fitting of two trajectories could lead to overly-optimistic results as this metric is invariant to scale. Also, the correlation has a non-linear nature that leads to higher values for sinus/cosinus-like signals at low frequencies. Analysis of these properties on the reconstruction results was carried out through an experiment performed in line with previous studies, where healthy participants executed predefined reaching movements of the hand in 3D space. While the correlations of limb velocity profiles reconstructed from low-frequency EEG were comparable to studies in this domain, a systematic statistical analysis revealed that these results were not above the chance level. The empirical chance level was estimated using random assignments of recorded velocity profiles and EEG signals, as well as combinations of randomly generated synthetic EEG with recorded velocity profiles and recorded EEG with randomly generated synthetic velocity profiles. The analysis shows that the positive correlation results in this experiment cannot be used as an indicator of successful trajectory reconstruction based on a neural correlate. Several directions are herein discussed to address the misinterpretation of results as well as the implications on previous invasive and non-invasive works.
000061483 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/DPI2011-25892$$9info:eu-repo/grantAgreement/ES/MINECO/DPI2009-14732-C02-01$$9info:eu-repo/grantAgreement/ES/MINECO/HYPER-CSD2009-00067
000061483 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000061483 590__ $$a3.534$$b2013
000061483 591__ $$aMULTIDISCIPLINARY SCIENCES$$b8 / 55 = 0.145$$c2013$$dQ1$$eT1
000061483 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000061483 700__ $$0(orcid)0000-0003-1183-349X$$aMontesano, L.$$uUniversidad de Zaragoza
000061483 700__ $$aRamos-Murguialday, A.
000061483 700__ $$aBirbaumer, N.
000061483 700__ $$0(orcid)0000-0002-2957-0133$$aMinguez, J.$$uUniversidad de Zaragoza
000061483 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDepartamento de Informática e Ingeniería de Sistemas$$cLenguajes y Sistemas Informáticos
000061483 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDepartamento de Informática e Ingeniería de Sistemas$$cIngeniería de Sistemas y Automática
000061483 773__ $$g8, 4 (2013), e61976 [14 pp]$$pPLoS One$$tPLoS One$$x1932-6203
000061483 8564_ $$s2529946$$uhttps://zaguan.unizar.es/record/61483/files/texto_completo.pdf$$yVersión publicada
000061483 8564_ $$s130438$$uhttps://zaguan.unizar.es/record/61483/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000061483 909CO $$ooai:zaguan.unizar.es:61483$$particulos$$pdriver
000061483 951__ $$a2017-06-12-09:39:42
000061483 980__ $$aARTICLE