The role of the reference electrode in EEG recordings: looking from an inverted perspective.

Abstract

The electroencephalographic signal variability caused by the active reference electrode is a major challenge for classification of motor tasks in Brain-Computer Interfaces. In this work a strategy to deal with the reference is proposed: use the information from all channels to extract more reliable information from the reference, the Inverted Perspective Reference Electrode (IPRE). In this novel approach the original set of signals is re-referenced to the electrode of interest, in contrast with all other available methods. At total, eight scenarios were analyzed independently: C3 and C4 as reference electrode, alpha and beta frequency bands, and motor imagery and motor execution tasks. Principal Component Analysis (PCA) was used to extract the information from the reference. This information was analyzed by means of the separability between motor tasks. Thirty-six subsets of electrodes were analyzed, including four typical choices of channels for comparison. A dataset with 109 subjects was used. Results showed that the quantity and location of electrodes are determinant to provide class-separable signals at the reference electrode. The IPRE showed greater separability compared to typical channel choices. Therefore, the strategy revealed better outcomes, encouraging further investigation with the inverted perspective to overcome the challenge of the active reference.