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.
Online EEG artifact removal for BCI applications by adaptive spatial filtering
Barban, F.;
2018-01-01
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.