Discriminative Canonical Pattern Matching for Single-Trial Classification of ERP Components.

Xiaolin Xiao,Jing Jin,Tzyy-Ping Jung,Yijun Wang,Dong Ming,Minpeng Xu

doi:10.1109/tbme.2019.2958641

Abstract

Event-related potentials (ERPs) are one of the most popular control signals for brain-computer interfaces (BCIs). However, they are very weak and sensitive to the experimental settings including paradigms, stimulation parameters and even surrounding environments, resulting in a diversity of ERP patterns across different BCI experiments. It's still a challenge to develop a general decoding algorithm that can adapt to the ERP diversities of different BCI datasets with small training sets. This study compared a recently developed algorithm, i.e., discriminative canonical pattern matching (DCPM), with seven ERP-BCI classification methods, i.e., linear discriminant analysis (LDA), stepwise LDA, bayesian LDA, shrinkage LDA, spatial-temporal discriminant analysis (STDA), xDAWN and EEGNet for the single-trial classification of two private EEG datasets and three public EEG datasets with small training sets. The feature ERPs of the five datasets included P300, motion visual evoked potential (mVEP), and miniature asymmetric visual evoked potential (aVEP). Study results showed that the DCPM outperformed other classifiers for all of the tested datasets, suggesting the DCPM is a robust classification algorithm for assessing a wide range of ERP components.

Highlights

B RAIN-COMPUTER interfaces (BCIs) directly link the brain and the external world without the involvement of muscles and peripheral nerves, which allow users to communicate with their environments and control external devices [1]–[4]
Among all EEG features, event-related potentials (ERPs) are one of the most important brain control signals used for BCIs, which includes P300 [8]–[10], N170 [11], N200 [12], [13], motion visual evoked potential [14] and miniature asymmetric visual evoked potential [15], etc
It’s desirable to develop a robust classification method that can adapt to a wide range of ERP patterns for practical applications of ERP-based BCIs

Summary

Introduction

B RAIN-COMPUTER interfaces (BCIs) directly link the brain and the external world without the involvement of muscles and peripheral nerves, which allow users to communicate with their environments and control external devices [1]–[4]. Among all EEG features, event-related potentials (ERPs) are one of the most important brain control signals used for BCIs, which includes P300 [8]–[10], N170 [11], N200 [12], [13], motion visual evoked potential (mVEP) [14] and miniature asymmetric visual evoked potential (aVEP) [15], etc. ERP-based BCIs have many practical applications in both clinical and non-clinical fields. A key component of an ERP-based BCI is to discriminate ERPs from the noisy background EEG. As the background EEG signals are non-linear, non-stationary and often many times larger than ERPs, it’s difficult to recognize the single-trial ERPs and needs to collect multiple samples. It’s desirable to develop a robust classification method that can adapt to a wide range of ERP patterns for practical applications of ERP-based BCIs

Methods

Findings

Discussion

Conclusion