AUTHOR=Ma Yan , Tang Yiou , Zeng Yang , Ding Tao , Liu Yifu 

TITLE=An N400 identification method based on the combination of Soft-DTW and transformer

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2023.1120566

DOI=10.3389/fncom.2023.1120566

ISSN=1662-5188

ABSTRACT=As a time-domain EEG feature reflecting the semantic processing of the human brain, N400 event-related potentials still lack a more mature classification recognition scheme. To address the problems of low signal-to-noise ratio and difficult feature extraction of N400 data, we propose a Soft-DTW-based single-subject short-distance event-related potential averaging method based on the Soft-DTW distance in the single-subject range based on partial Soft-DTW averaging and propose a Transformer-based ERP classification model, which captures contextual information by introducing location coding and self-attentive mechanism and combines with Softmax classifier to bifurcate N400 data. The experimental results show that the highest recognition accuracy of 0.8992 is achieved on the ERP-CORE N400 public dataset, which verifies the effectiveness of the model and the averaging method.