ERP Detection Based on Smoothness Priors.

Abstract

Detection of event-related potentials (ERPs) in electroencephalography (EEG) is of great interest in the study of brain responses to various stimuli. This is challenging due to the low signal-to-noise ratio of these deflections. To address this problem, a new scheme to detect the ERPs based on smoothness priors is proposed. The problem is considered as a binary hypothesis test and solved using a smooth version of the generalized likelihood ratio test (SGLRT). First, we estimate the parameters of probability density functions from the training data under the Gaussian assumption. Then, these parameters are treated as known values and the unknown ERPs are estimated under the smoothness constraint. The performance of the proposed SGLRT is assessed for ERP detection in post-stimuli EEG recordings of two oddball settings. We compared our method with several powerful methods regarding ERP detection. The presented method performs better than the competing algorithms and improves the classification accuracy. SGLRT can be employed as a powerful means for different ERP detection schemes. The proposed scheme is opening a new direction in ERP identification which provides better classification results compared to several popular ERP detection methods.