Transfer Learning Algorithm of P300-EEG Signal Based on XDAWN Spatial Filter and Riemannian Geometry Classifier

Abstract

The electroencephalogram (EEG) signal in the brain–computer interface (BCI) has suffered great cross-subject variability. The BCI system needs to be retrained before each time it is used, which is a waste of resources and time. Thus, it is difficult to generalize a fixed classification method for all subjects. Therefore, the transfer learning method proposed in this article, which combines XDAWN spatial filter and Riemannian Geometry classifier (RGC), can achieve offline cross-subject transfer learning in the P300-speller paradigm. The XDAWN spatial filter is used to enhanced the P300 components in the raw signal as well as reduce its dimensions. Then, the Riemannian Geometry Mean (RGM) is used as the reference matrix to perform the affine transformation of the symmetric positive definite (SPD) covariance matrix calculated from the filtered signal, which makes the data from different subjects comparable. Finally, the RGC is used to obtain the result of transfer learning experiments. The proposed algorithm was evaluated on two datasets (Dataset I from real patients and Dataset II from the laboratory). By comparing with two state-of-the-art and classic algorithms in the current BCI field, Ensemble of Support Vector Machine (E-SVM) and Stepwise Linear Discriminant Analysis (SWLDA), the maximum averaged area under the receiver operating characteristic curve (AUC) score of our algorithm reached 0.836, proving the potential of our proposed algorithm.

Review of brain encoding and decoding mechanisms for EEG-based brain–computer interface

“…To reduce its computational cost, He and Wu (2019) suggested using the Euclidean mean covariance matrix instead of the Riemannian mean covariance matrix. Li et al (2020) validated the xDAWN algorithm combined with Riemannian whitening for P300 datasets. Qi et al (2018) proposed a speedy calibration method with Riemannian geometry for P300 spellers by selecting related samples from the database.…”

Towards a minimal EEG channel array for a biometric system using resting-state and a genetic algorithm for channel selection

“…The dataset used in this paper consists of EEG signals from a single session, which limits the experimental configurations and does not allow evaluation of whether we can create models for each subject from a certain session and be able to recognize the subjects or reject them using data from another session. Future steps will center the attention on tackling this problem and analyzing a possible way to use new correctly-classified instances to decrease session-to-session variability, as well as using and comparing current progress in transfer learning, using machine-/deep-learning methods for this problem 16,46 .…”

“…For certain brain–computer interface (BCI) applications, the problem of recognizing new instances from new sessions has been studied using EEG data from different sessions or adding new instances for calibration. In the case of session-to-session or subject-to-subject transfer, the learning problem has been studied using linear discriminant analysis (LDA) and SVM, based on motor imagery or P300 paradigms 34 , 43 – 46 . To adapt the EEG feature space and thus reduce session-to-session variability, we can use a data space adaptation method based on the Kullback-Leibler divergence criterion (Also called relative entropy), aiming to minimize the distribution of differences from the training session to a different session 44 .…”

Spatial-Temporal Neural Network for P300 Detection

“…Commonly used classifiers include linear discriminant analysis (LDA) [16], support vector machine (SVM) [17], and Riemannian geometry classifier (RGC) [18], among others. Of these, the combination of XDAWN and RGC is perhaps the most potent approach for P300 detection [19], which exhibits a strong generalization capability for variable EEG signals. Nevertheless, it is still not as competitive as DL approaches [20].…”