Online EEG artifact removal for BCI applications by adaptive spatial filtering

Roberto Guarnieri, Marco Marino, Federico Barban, Marco Ganzetti, Dante Mantini

Research output: Contribution to journalArticlepeer-review

Abstract

Objective. The performance of brain-computer interfaces (BCIs) based on electroencephalography (EEG) data strongly depends on the effective attenuation of artifacts that are mixed in the recordings. To address this problem, we have developed a novel online EEG artifact removal method for BCI applications, which combines blind source separation (BSS) and regression (REG) analysis. Approach. The BSS-REG method relies on the availability of a calibration dataset of limited duration for the initialization of a spatial filter using BSS. Online artifact removal is implemented by dynamically adjusting the spatial filter in the actual experiment, based on a linear regression technique. Main results. Our results showed that the BSS-REG method is capable of attenuating different kinds of artifacts, including ocular and muscular, while preserving true neural activity. Thanks to its low computational requirements, BSS-REG can be applied to low-density as well as high-density EEG data. Significance. We argue that BSS-REG may enable the development of novel BCI applications requiring high-density recordings, such as source-based neurofeedback and closed-loop neuromodulation.

Original languageEnglish
Article number056009
JournalJournal of Neural Engineering
Volume15
Issue number5
DOIs
Publication statusPublished - Jul 18 2018

Keywords

  • blind source separation
  • brain-computer interface
  • electroencephalography
  • independent component analysis
  • linear regression
  • online processing

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Fingerprint Dive into the research topics of 'Online EEG artifact removal for BCI applications by adaptive spatial filtering'. Together they form a unique fingerprint.

Cite this