Automated artifact rejection algorithms harm P3 Speller brain-computer interface performance

ABSTRACT

Brain-Computer Interfaces (BCIs) have been used to restore communication and control to people with severe paralysis. However, noninvasive BCIs based on electroencephalogram (EEG) are particularly vulnerable to noise artifacts. These artifacts, including electro-oculogram (EOG), can be orders of magnitude larger than the signal to be detected. Many automated methods have been proposed to remove EOG and other artifacts from EEG recordings, most based on blind source separation. This work presents a performance comparison of ten different automated artifact removal methods. Unfortunately, all tested methods substantially and significantly reduced P3 Speller BCI performance, and all methods were more likely to reduce performance than increase it. The least harmful methods were titled SOBI, JADER, and EFICA, but even these methods caused an average of approximately ten percentage points drop in BCI accuracy. Possible mechanistic causes for this empirical performance reduction are proposed.

KEYWORDS:

• Brain-computer interfaces
• P300 Speller
• artifacts rejection
• physiological signals
• signal processing

Disclosure Statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The data presented here were collected under National Institute of Child Health and Human Development (NICHD), the National Institutes of Health (NIH) under Grant [R21HD054697] and by the National Institute on Disability and Rehabilitation Research (NIDRR) in the Department of Education under Grant H133G090005 and Award Number [H133P090008]. Data collection and early analysis were supported by the National Science Foundation (NSF) Graduate Student Research Fellowship under Grant [DGE0718128]. The present analysis was supported by Kansas State University (KSU) faculty startup funds, undergraduate research support from the K-State Department of Electrical and Computer Engineering, and the NSF under Award 1910526. Any opinions, findings, conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the respective funding agencies.