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 journalArticle

1 Citation (Scopus)

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

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Blind source separation
Electroencephalography
Artifacts
Neurofeedback
Calibration
Linear Models
Regression Analysis
Linear regression
Regression analysis
Availability

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

Cite this

Online EEG artifact removal for BCI applications by adaptive spatial filtering. / Guarnieri, Roberto; Marino, Marco; Barban, Federico; Ganzetti, Marco; Mantini, Dante.

In: Journal of Neural Engineering, Vol. 15, No. 5, 056009, 18.07.2018.

Research output: Contribution to journalArticle

Guarnieri, Roberto ; Marino, Marco ; Barban, Federico ; Ganzetti, Marco ; Mantini, Dante. / Online EEG artifact removal for BCI applications by adaptive spatial filtering. In: Journal of Neural Engineering. 2018 ; Vol. 15, No. 5.
@article{68022aaea97545b1a9fc45972929ed84,
title = "Online EEG artifact removal for BCI applications by adaptive spatial filtering",
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.",
keywords = "blind source separation, brain-computer interface, electroencephalography, independent component analysis, linear regression, online processing",
author = "Roberto Guarnieri and Marco Marino and Federico Barban and Marco Ganzetti and Dante Mantini",
year = "2018",
month = "7",
day = "18",
doi = "10.1088/1741-2552/aacfdf",
language = "English",
volume = "15",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "5",

}

TY - JOUR

T1 - Online EEG artifact removal for BCI applications by adaptive spatial filtering

AU - Guarnieri, Roberto

AU - Marino, Marco

AU - Barban, Federico

AU - Ganzetti, Marco

AU - Mantini, Dante

PY - 2018/7/18

Y1 - 2018/7/18

N2 - 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.

AB - 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.

KW - blind source separation

KW - brain-computer interface

KW - electroencephalography

KW - independent component analysis

KW - linear regression

KW - online processing

UR - http://www.scopus.com/inward/record.url?scp=85053153776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053153776&partnerID=8YFLogxK

U2 - 10.1088/1741-2552/aacfdf

DO - 10.1088/1741-2552/aacfdf

M3 - Article

VL - 15

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 5

M1 - 056009

ER -