Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fukushima, Takuto, Miyamoto, Ryusuke
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914707146801152
author Fukushima, Takuto
Miyamoto, Ryusuke
author_facet Fukushima, Takuto
Miyamoto, Ryusuke
contents Motor imagery classification based on electroencephalography (EEG) signals is one of the most important brain-computer interface applications, although it needs further improvement. Several methods have attempted to obtain useful information from EEG signals by using recent deep learning techniques such as transformers. To improve the classification accuracy, this study proposes a novel EEG-based motor imagery classification method with three key features: generation of a topological map represented as a two-dimensional image from EEG signals with coordinate transformation based on t-SNE, use of the InternImage to extract spatial features, and use of spatiotemporal pooling inspired by PoolFormer to exploit spatiotemporal information concealed in a sequence of EEG images. Experimental results using the PhysioNet EEG Motor Movement/Imagery dataset showed that the proposed method achieved the best classification accuracy of 88.57%, 80.65%, and 70.17% on two-, three-, and four-class motor imagery tasks in cross-individual validation.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification
Fukushima, Takuto
Miyamoto, Ryusuke
Computer Vision and Pattern Recognition
Motor imagery classification based on electroencephalography (EEG) signals is one of the most important brain-computer interface applications, although it needs further improvement. Several methods have attempted to obtain useful information from EEG signals by using recent deep learning techniques such as transformers. To improve the classification accuracy, this study proposes a novel EEG-based motor imagery classification method with three key features: generation of a topological map represented as a two-dimensional image from EEG signals with coordinate transformation based on t-SNE, use of the InternImage to extract spatial features, and use of spatiotemporal pooling inspired by PoolFormer to exploit spatiotemporal information concealed in a sequence of EEG images. Experimental results using the PhysioNet EEG Motor Movement/Imagery dataset showed that the proposed method achieved the best classification accuracy of 88.57%, 80.65%, and 70.17% on two-, three-, and four-class motor imagery tasks in cross-individual validation.
title Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04353