A large scale screening study with a SMR-based BCI: Categorization of BCI users and differences in their SMR activity

Claudia Sannelli, Carmen Vidaurre, Klaus Muller, Benjamin Blankertz

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25%. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from a large-scale screening study conducted on 80 novice participants with the Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one BCI session with resting state Encephalography, Motor Observation, Motor Execution and Motor Imagery recordings and 128 electrodes. A significant portion of the participants (40%) could not achieve BCI control (feedback performance > 70%). Based on the performance of the calibration and feedback runs, BCI users were stratified in three groups. Analyses directed to detect and elucidate the differences in the SMR activity of these groups were performed. Statistics on reactive frequencies, task prevalence and classification results are reported. Based on their SMR activity, also a systematic list of potential reasons leading to performance drops and thus hints for possible improvements of BCI experimental design are given. The categorization of BCI users has several advantages, allowing researchers 1) to select subjects for further analyses as well as for testing new BCI paradigms or algorithms, 2) to adopt a better subject-dependent training strategy and 3) easier comparisons between different studies.

Original languageEnglish
Article numbere0207351
JournalPLoS One
Volume14
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Brain-Computer Interfaces
user interface
Brain computer interface
Screening
screening
brain
artificial intelligence
Imagery (Psychotherapy)
Computer Systems
Berlin
Design of experiments
electrodes
Calibration
Feedback control
Learning systems
Electrodes
calibration
Research Design
statistics
researchers

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

A large scale screening study with a SMR-based BCI : Categorization of BCI users and differences in their SMR activity. / Sannelli, Claudia; Vidaurre, Carmen; Muller, Klaus; Blankertz, Benjamin.

In: PLoS One, Vol. 14, No. 1, e0207351, 01.01.2019.

Research output: Contribution to journalArticle

Sannelli, Claudia ; Vidaurre, Carmen ; Muller, Klaus ; Blankertz, Benjamin. / A large scale screening study with a SMR-based BCI : Categorization of BCI users and differences in their SMR activity. In: PLoS One. 2019 ; Vol. 14, No. 1.
@article{ad36c9b2fc1146b4917c040d29e11341,
title = "A large scale screening study with a SMR-based BCI: Categorization of BCI users and differences in their SMR activity",
abstract = "Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25{\%}. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from a large-scale screening study conducted on 80 novice participants with the Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one BCI session with resting state Encephalography, Motor Observation, Motor Execution and Motor Imagery recordings and 128 electrodes. A significant portion of the participants (40{\%}) could not achieve BCI control (feedback performance > 70{\%}). Based on the performance of the calibration and feedback runs, BCI users were stratified in three groups. Analyses directed to detect and elucidate the differences in the SMR activity of these groups were performed. Statistics on reactive frequencies, task prevalence and classification results are reported. Based on their SMR activity, also a systematic list of potential reasons leading to performance drops and thus hints for possible improvements of BCI experimental design are given. The categorization of BCI users has several advantages, allowing researchers 1) to select subjects for further analyses as well as for testing new BCI paradigms or algorithms, 2) to adopt a better subject-dependent training strategy and 3) easier comparisons between different studies.",
author = "Claudia Sannelli and Carmen Vidaurre and Klaus Muller and Benjamin Blankertz",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0207351",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

TY - JOUR

T1 - A large scale screening study with a SMR-based BCI

T2 - Categorization of BCI users and differences in their SMR activity

AU - Sannelli, Claudia

AU - Vidaurre, Carmen

AU - Muller, Klaus

AU - Blankertz, Benjamin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25%. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from a large-scale screening study conducted on 80 novice participants with the Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one BCI session with resting state Encephalography, Motor Observation, Motor Execution and Motor Imagery recordings and 128 electrodes. A significant portion of the participants (40%) could not achieve BCI control (feedback performance > 70%). Based on the performance of the calibration and feedback runs, BCI users were stratified in three groups. Analyses directed to detect and elucidate the differences in the SMR activity of these groups were performed. Statistics on reactive frequencies, task prevalence and classification results are reported. Based on their SMR activity, also a systematic list of potential reasons leading to performance drops and thus hints for possible improvements of BCI experimental design are given. The categorization of BCI users has several advantages, allowing researchers 1) to select subjects for further analyses as well as for testing new BCI paradigms or algorithms, 2) to adopt a better subject-dependent training strategy and 3) easier comparisons between different studies.

AB - Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25%. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from a large-scale screening study conducted on 80 novice participants with the Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one BCI session with resting state Encephalography, Motor Observation, Motor Execution and Motor Imagery recordings and 128 electrodes. A significant portion of the participants (40%) could not achieve BCI control (feedback performance > 70%). Based on the performance of the calibration and feedback runs, BCI users were stratified in three groups. Analyses directed to detect and elucidate the differences in the SMR activity of these groups were performed. Statistics on reactive frequencies, task prevalence and classification results are reported. Based on their SMR activity, also a systematic list of potential reasons leading to performance drops and thus hints for possible improvements of BCI experimental design are given. The categorization of BCI users has several advantages, allowing researchers 1) to select subjects for further analyses as well as for testing new BCI paradigms or algorithms, 2) to adopt a better subject-dependent training strategy and 3) easier comparisons between different studies.

UR - http://www.scopus.com/inward/record.url?scp=85060551021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060551021&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0207351

DO - 10.1371/journal.pone.0207351

M3 - Article

C2 - 30682025

AN - SCOPUS:85060551021

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 1

M1 - e0207351

ER -