Online EEG artifact removal for BCI applications by adaptive spatial filtering

J Neural Eng. 2018 Oct;15(5):056009. doi: 10.1088/1741-2552/aacfdf. Epub 2018 Jun 28.


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.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Artifacts*
  • Brain-Computer Interfaces*
  • Calibration
  • Electroencephalography / methods*
  • Humans
  • Linear Models
  • Online Systems
  • Principal Component Analysis
  • Reproducibility of Results
  • Signal Processing, Computer-Assisted