Comparison of Linear and Nonlinear Approaches on Single Trial ERP Detection in Rapid Serial Visual Presentation Tasks

In this paper, we describe a system for detecting encephalography (EEG) signatures of visual recognition events evoked in a single trial during rapid serial visual presentation (RSVP). In order to investigate the viability of nonlinear approaches in EEG detection and assess the performance comparison, we applied three classifiers (linear logistic regression model, Laplacian classifier, and spectral maximum mutual information projection) in the detection tasks. The EEG was recorded using 32 electrodes during the rapid image presentation (50 ms/100 ms per image). Subjects were instructed to push a button when they recognize a target image. The results suggest that while the detection of single trial EEG-based recognition is possible, taking advantage of the nonlinear techniques requires data representation that would overcome the non-stationarity of the EEG signals.

[1]  Lucas C. Parra,et al.  Cortical origins of response time variability during rapid discrimination of visual objects , 2005, NeuroImage.

[2]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[3]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Barak A. Pearlmutter,et al.  Single-trial detection in EEG and MEG: Keeping it linear , 2003, Neurocomputing.

[5]  Mark Witkowski,et al.  Image presentation in space and time: errors, preferences and eye-gaze activity , 2004, AVI.

[6]  T. Sejnowski,et al.  Dynamic Brain Sources of Visual Evoked Responses , 2002, Science.

[7]  David G. Stork,et al.  Pattern Classification , 1973 .

[8]  J. Biesiada,et al.  Feature ranking methods based on information entropy with Parzen windows , 2005 .

[9]  Barak A. Pearlmutter,et al.  Linear Spatial Integration for Single-Trial Detection in Encephalography , 2002, NeuroImage.

[10]  U. Ozertem.  Maximally discriminative spectral feature projections using mutual information , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[11]  Aapo Hyvärinen,et al.  Statistical models of images and early vision , 2005 .

[12]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[13]  Tzyy-Ping Jung,et al.  Independent Component Analysis of Electroencephalographic Data , 1995, NIPS.

[14]  P. Sajda,et al.  Cortically coupled computer vision for rapid image search , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Data Mining Researchers , 2003 .

[16]  Robert Jenssen,et al.  The Laplacian PDF Distance: A Cost Function for Clustering in a Kernel Feature Space , 2004, NIPS.

[17]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[18]  G. Ferber,et al.  Treatment of some nonstationarities in the EEG. , 1987, Neuropsychobiology.

[19]  Lucas C. Parra,et al.  Recipes for the linear analysis of EEG , 2005, NeuroImage.

[20]  Robert Jenssen,et al.  The Laplacian Classifier , 2007, IEEE Transactions on Signal Processing.

[21]  Bernhard Graimann,et al.  Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis , 2004, IEEE Transactions on Biomedical Engineering.

[22]  R. Cook.  Generalized Linear Model , 2005 .

[23]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[24]  M.M. Moore,et al.  Real-world applications for brain-computer interface technology , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[25]  S. Thorpe,et al.  Speed of processing in the human visual system , 1996, Nature.