Title
Multiclass classification of single-trial evoked EEG responses.
Abstract
The detection of event-related potentials (ERPs) in the electroencephalogram (EEG) signal has several real-world applications, from cognitive state monitoring to brain-computer interfaces. Current systems based on the detection of ERPs only consider a single type of response to detect. Hence, the classification methods that are considered for ERP detection are binary classifiers (target vs. non target). Here we investigated multiclass classification of single-trial evoked responses during a rapid serial visual presentation task in which short video clips were presented to fifteen observers. Each trial contained potential targets that were human or non-human, stationary or moving. The goal of the classification analysis was to discriminate between three classes: moving human targets, moving non-human targets, and non-moving human targets. The analysis revealed that the mean volume under the ROC surface of 0.878. These results suggest that it is possible to efficiently discriminate between more than two types of evoked responses using single-trial detection.
Year
DOI
Venue
2012
10.1109/EMBC.2012.6346280
EMBC
Keywords
Field
DocType
short video clips,single-trial evoked eeg responses,cognition,bioelectric potentials,moving human targets,nonmoving human targets,classification analysis,electroencephalography,brain-computer interfaces,multiclass classification,medical signal processing,moving nonhuman targets,cognitive state monitoring,signal classification,electroencephalogram signal,rapid serial visual presentation task,event-related potential detection,roc surface,binary classifiers,sensitivity analysis,brain computer interfaces
Computer vision,Computer science,Brain–computer interface,Speech recognition,Artificial intelligence,Signal classification,Cognition,Electroencephalography,Rapid serial visual presentation,Multiclass classification
Conference
Volume
ISSN
ISBN
2012
1557-170X
978-1-4577-1787-1
Citations 
PageRank 
References 
3
0.41
6
Authors
4
Name
Order
Citations
PageRank
Hubert Cecotti126324.03
Anthony J. Ries2395.61
Miguel P Eckstein38616.23
Barry Giesbrecht4688.58