Single-Trial Estimation of Evoked Potential Signals via ARX Model and Sparse Coding

Abstract

This paper presents a single-trial evoked potential (EP) estimation method based on an autoregressive model with exogenous input modeling and sparse coding. This method uses sparse coding instead of the autoregressive-moving-average model to model EPs, as the former is more flexible. The best matching atoms from the dictionary are used to represent the EP signal without needing to estimate the number of atoms beforehand. By transforming the electroencephalography signal into white noise, the single-trial EP estimation is transformed into a signal denoising problem for white noise. With the dictionary constructed specially for EPs, the EP signal can be extracted easily with sparse coding. Moreover, since the location of the atom in the dictionary has no influence on the effectiveness of sparse decomposition, variations of the amplitude and latency of EPs have only a minor impact on the performance of the proposed method. The proposed method can thus track EP signal variations. Experimental results also demonstrate that this method is effective.