Comparison of Gaussian process models for single-trial event-related potentials | IEEE Conference Publication | IEEE Xplore

Comparison of Gaussian process models for single-trial event-related potentials


Abstract:

In this work we present a comparative study of Gaussian process models for single-trial event-related potentials (ERPs) in electroencephalography (EEG) recordings. Our da...Show More

Abstract:

In this work we present a comparative study of Gaussian process models for single-trial event-related potentials (ERPs) in electroencephalography (EEG) recordings. Our data comes from a motor task experiment where an ERP arises before the motor response of the participant to a stimulus. We consider models based on stationary and non-stationary kernel functions. The comparison is done based on two different criteria: model likelihood and model reaction time prediction. We show how models with high likelihoods do not necessarily perform well at predicting reaction time. The non-stationary kernel function achieved the best predictive performance.
Date of Conference: 05-08 August 2012
Date Added to IEEE Xplore: 04 October 2012
ISBN Information:
Print ISSN: 2373-0803
Conference Location: Ann Arbor, MI, USA

References

References is not available for this document.