Phase space reconstruction for improving the classification of single trial EEG

Abstract

Electroencephalogram (EEG) signals are nonlinear time series, which are generally very noisy, nonstationary, and contaminated with artifacts that can deteriorate classification methods. This contribution presents an efficient scheme to extract features in phase space by exploiting the theoretical results derived in nonlinear dynamics for motor imagery tasks recognition. To remodel the single nonlinear sequence is to reveal variety of information hidden in the origin series by its phase space reconstruction (PSR), and maintaining the original information continuity. The phase space features (PSF) were extracted by the amplitude–frequency analysis (AFA) method in the state space of EEG signals (AFAPS). The linear discriminant analysis (LDA) classifiers based on the AFAPS features are used to classify two Graz datasets used in BCI Competition 2003 and 2005. The results have shown that the LDA classifiers based on PSF outperformed most of other similar studies on the same Graz dataset in terms of the competition criterions. The features extracted by the proposed scheme contain the nonlinear information which helps to improve the classification results in the BCI.