A Comparative Analysis of Multi-Class EEG Classification for Brain Computer Interface

Classifying different electroencephalogram (EEG) patterns is one of the key components to designing a usable Brain Computer Interface (BCI). Although it is well known that Support Vector Machine (SVM) is a strong classifier, it does not replace simple Linear Discriminant Analysis (LDA) or Nearest Neighbor Classifier (NNC), which are still in use in current BCI systems. This paper presents a comparison of SVM, LDA and NNC against each other by applying to the EEG data, where two methods were used to preprocess the raw EEG data: the Common Spatial Patterns (CSP) method and the feature extraction by estimate the adaptive autoregressive (AAR) parameters.

[1]  Christa Neuper,et al.  An asynchronously controlled EEG-based virtual keyboard: improvement of the spelling rate , 2004, IEEE Transactions on Biomedical Engineering.

[2]  E Donchin,et al.  The mental prosthesis: assessing the speed of a P300-based brain-computer interface. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[3]  Bernhard Schölkopf,et al.  Methods Towards Invasive Human Brain Computer Interfaces , 2004, NIPS.

[4]  G. Pfurtscheller,et al.  Designing optimal spatial filters for single-trial EEG classification in a movement task , 1999, Clinical Neurophysiology.

[5]  G Pfurtscheller,et al.  Adaptive Autoregressive Modeling used for Single-trial EEG Classification - Verwendung eines Adaptiven Autoregressiven Modells für die Klassifikation von Einzeltrial-EEG-Daten , 1997, Biomedizinische Technik. Biomedical engineering.

[6]  Z J Koles,et al.  The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. , 1991, Electroencephalography and clinical neurophysiology.

[7]  Klaus-Robert Müller,et al.  The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials , 2004, IEEE Transactions on Biomedical Engineering.

[8]  G. Pfurtscheller,et al.  ‘Thought’ – control of functional electrical stimulation to restore hand grasp in a patient with tetraplegia , 2003, Neuroscience Letters.

[9]  H. Flor,et al.  The thought translation device (TTD) for completely paralyzed patients. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[10]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[11]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[12]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..