文献类型：期刊文献

英文题名：Discriminative Canonical Pattern Matching for Single-Trial Classification of ERP Components

作者：Xiao, Xiaolin[1];Xu, Minpeng[1,2];Jin, Jing[3];Wang, Yijun[4];Jung, Tzyy-Ping[1,5];Ming, Dong[1,2]

机构：[1]Tianjin Univ, Coll Precis Instruments & Optoelect Engn, Dept Biomed Engn, Lab Neural Engn & Rehabil, Tianjin 300072, Peoples R China;[2]Tianjin Univ, Acad Med Engn & Translat Med, Tianjin Int Joint Res Ctr Neural Engn, Tianjin 300072, Peoples R China;[3]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai, Peoples R China;[4]Chinese Acad Sci, Inst Semicond, State Key Lab Integrated Optoelect, Beijing 100083, Peoples R China;[5]Univ Calif, Swartz Ctr Computat Neurosci, La Jolla, CA USA

年份：2020

卷号：67

期号：8

起止页码：2266

外文期刊名：IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING

收录：;EI(收录号：20203108993439);WOS:【SCI-EXPANDED(收录号:WOS:000550653800012)】；

基金：This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1300302, in part by the National Natural Science Foundation of China under Grants 61976152 and 81630051, and in part by Tianjin Key Technology R&D Program under Grant 17ZXRGGX00020.

语种：英文

外文关键词：Electroencephalography; Band-pass filters; Electrodes; Visualization; Classification algorithms; Training; Electric potential; Brain-computer interface (BCI); electroencephalogram (EEG); single-trial classification; event-related potential (ERP); discriminative canonical pattern matching (DCPM)

摘要：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.