Author(s): Xiao, XL (Xiao, Xiaolin); Xu, MP (Xu, Minpeng); Jin, J (Jin, Jing); Wang, YJ (Wang, Yijun); Jung, TP (Jung, Tzyy-Ping); Ming, D (Ming, Dong)

Source: IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING Volume: 67 Issue: 8 Pages: 2266-2275 DOI: 10.1109/TBME.2019.2958641 Published: AUG. 2020

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.

Accession Number: WOS:000550653800012

PubMed ID: 31831401

Author Identifiers:

Author        Web of Science ResearcherID        ORCID Number

Jung, Tzyy-Ping                  0000-0002-8377-2166

ISSN: 0018-9294

eISSN: 1558-2531

Full Text: https://ieeexplore.ieee.org/document/8930304