A subject-independent pattern-based brain-computer interface

Andreas M. Ray, Ranganatha Sitaram, Mohit Rana, Emanuele Pasqualotto, Korhan Buyukturkoglu, Cuntai Guan, Kai Keng Ang, Cristián Tejos, Francisco Zamorano, Francisco Aboitiz, Niels Birbaumer, Sergio Ruiz

Research output: Contribution to journalArticle

Abstract

While earlier Brain-Computer Interface (BCI) studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG) signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs) from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30% was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e., happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to “match” their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.

Original languageEnglish
Article number269
JournalFrontiers in Behavioral Neuroscience
Volume9
Issue numberOCTOBER
DOIs
Publication statusPublished - Oct 20 2015

Fingerprint

Brain-Computer Interfaces
Neurofeedback
Imagery (Psychotherapy)
Brain
Healthy Volunteers
Hand

Keywords

  • BCI
  • Common spatial patterns
  • Emotion imagery
  • Neurofeedback
  • Subject-independent classification

ASJC Scopus subject areas

  • Behavioral Neuroscience
  • Cognitive Neuroscience
  • Neuropsychology and Physiological Psychology

Cite this

Ray, A. M., Sitaram, R., Rana, M., Pasqualotto, E., Buyukturkoglu, K., Guan, C., ... Ruiz, S. (2015). A subject-independent pattern-based brain-computer interface. Frontiers in Behavioral Neuroscience, 9(OCTOBER), [269]. https://doi.org/10.3389/fnbeh.2015.00269

A subject-independent pattern-based brain-computer interface. / Ray, Andreas M.; Sitaram, Ranganatha; Rana, Mohit; Pasqualotto, Emanuele; Buyukturkoglu, Korhan; Guan, Cuntai; Ang, Kai Keng; Tejos, Cristián; Zamorano, Francisco; Aboitiz, Francisco; Birbaumer, Niels; Ruiz, Sergio.

In: Frontiers in Behavioral Neuroscience, Vol. 9, No. OCTOBER, 269, 20.10.2015.

Research output: Contribution to journalArticle

Ray, AM, Sitaram, R, Rana, M, Pasqualotto, E, Buyukturkoglu, K, Guan, C, Ang, KK, Tejos, C, Zamorano, F, Aboitiz, F, Birbaumer, N & Ruiz, S 2015, 'A subject-independent pattern-based brain-computer interface', Frontiers in Behavioral Neuroscience, vol. 9, no. OCTOBER, 269. https://doi.org/10.3389/fnbeh.2015.00269
Ray AM, Sitaram R, Rana M, Pasqualotto E, Buyukturkoglu K, Guan C et al. A subject-independent pattern-based brain-computer interface. Frontiers in Behavioral Neuroscience. 2015 Oct 20;9(OCTOBER). 269. https://doi.org/10.3389/fnbeh.2015.00269
Ray, Andreas M. ; Sitaram, Ranganatha ; Rana, Mohit ; Pasqualotto, Emanuele ; Buyukturkoglu, Korhan ; Guan, Cuntai ; Ang, Kai Keng ; Tejos, Cristián ; Zamorano, Francisco ; Aboitiz, Francisco ; Birbaumer, Niels ; Ruiz, Sergio. / A subject-independent pattern-based brain-computer interface. In: Frontiers in Behavioral Neuroscience. 2015 ; Vol. 9, No. OCTOBER.
@article{225fd9747ef54981a469ad1712d934ce,
title = "A subject-independent pattern-based brain-computer interface",
abstract = "While earlier Brain-Computer Interface (BCI) studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG) signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs) from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30{\%} was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e., happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to “match” their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.",
keywords = "BCI, Common spatial patterns, Emotion imagery, Neurofeedback, Subject-independent classification",
author = "Ray, {Andreas M.} and Ranganatha Sitaram and Mohit Rana and Emanuele Pasqualotto and Korhan Buyukturkoglu and Cuntai Guan and Ang, {Kai Keng} and Cristi{\'a}n Tejos and Francisco Zamorano and Francisco Aboitiz and Niels Birbaumer and Sergio Ruiz",
year = "2015",
month = "10",
day = "20",
doi = "10.3389/fnbeh.2015.00269",
language = "English",
volume = "9",
journal = "Frontiers in Behavioral Neuroscience",
issn = "1662-5153",
publisher = "Frontiers Research Foundation",
number = "OCTOBER",

}

TY - JOUR

T1 - A subject-independent pattern-based brain-computer interface

AU - Ray, Andreas M.

AU - Sitaram, Ranganatha

AU - Rana, Mohit

AU - Pasqualotto, Emanuele

AU - Buyukturkoglu, Korhan

AU - Guan, Cuntai

AU - Ang, Kai Keng

AU - Tejos, Cristián

AU - Zamorano, Francisco

AU - Aboitiz, Francisco

AU - Birbaumer, Niels

AU - Ruiz, Sergio

PY - 2015/10/20

Y1 - 2015/10/20

N2 - While earlier Brain-Computer Interface (BCI) studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG) signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs) from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30% was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e., happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to “match” their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.

AB - While earlier Brain-Computer Interface (BCI) studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG) signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs) from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30% was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e., happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to “match” their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.

KW - BCI

KW - Common spatial patterns

KW - Emotion imagery

KW - Neurofeedback

KW - Subject-independent classification

UR - http://www.scopus.com/inward/record.url?scp=84947547565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947547565&partnerID=8YFLogxK

U2 - 10.3389/fnbeh.2015.00269

DO - 10.3389/fnbeh.2015.00269

M3 - Article

AN - SCOPUS:84947547565

VL - 9

JO - Frontiers in Behavioral Neuroscience

JF - Frontiers in Behavioral Neuroscience

SN - 1662-5153

IS - OCTOBER

M1 - 269

ER -