Detection of Change to SSVEPs Using Analysis of Phase Space Topological Features: A Novel Approach

Abstract

A novel method based on EEG nonlinear analysis and analysis of steady-state visual evoked potentials (SSVEPs) has been processed. The EEG phase space is reconstructed, and some new geometrical features are extracted. Statistical analysis is carried out based on ANOVA, and most significant features are selected and then fed into a multi-class support vector machine (MSVM). Both offline and online phases are considered to fully address SSVEP detection. In the offline mode, the whole design evaluation, feature selection, and classifier training are performed. In the online scenario, the proposed method is evaluated and the detection rate is reported for both phases. Subject-dependent and subject-independent scenarios are considered in online SSVEP detection. Five significant features, whose P values are less than 0.05, have been selected. The MSVM is trained in the offline mode, and fivefold cross-validation is performed to evaluate the proposed method. The average classification performance for offline and online phases are 92.56 and 92.91%, respectively. The information transfer rate (ITR) is about 2.5 bits per trial in the online phase, which is comparable with the results of previous studies in this field. Thus, we have introduced a user-friendly and precise SSVEP-based brain-computer interface (BCI) system. The effectiveness of the proposed method has been demonstrated. The suggested geometrical features can truly reflect the brain dynamics. This study paves the way for researchers to conduct future studies in the field of SSVEP detection.