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
N1 - Publisher Copyright:
© 2015 Ray, Sitaram, Rana, Pasqualotto, Buyukturkoglu, Guan, Ang, Tejos, Zamorano, Aboitiz, BirbaumerandRuiz.
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
U2 - 10.3389/fnbeh.2015.00269
DO - 10.3389/fnbeh.2015.00269
M3 - Article
AN - SCOPUS:84947547565
SN - 1662-5153
VL - 9
JO - Frontiers in Behavioral Neuroscience
JF - Frontiers in Behavioral Neuroscience
IS - OCTOBER
M1 - 269
ER -