Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification

Transformers have rapidly influenced research across various domains. With their superior capability to encode long sequences, they have demonstrated exceptional performance, outperforming existing machine learning methods. There has been a rapid increase in the development of transformer-based mode...

Full description

Saved in:
Bibliographic Details
Main Authors: Elnaz Vafaei, Mohammad Hosseini
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1293
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052637101129728
author Elnaz Vafaei
Mohammad Hosseini
author_facet Elnaz Vafaei
Mohammad Hosseini
author_sort Elnaz Vafaei
collection DOAJ
description Transformers have rapidly influenced research across various domains. With their superior capability to encode long sequences, they have demonstrated exceptional performance, outperforming existing machine learning methods. There has been a rapid increase in the development of transformer-based models for EEG analysis. The high volumes of recently published papers highlight the need for further studies exploring transformer architectures, key components, and models employed particularly in EEG studies. This paper aims to explore four major transformer architectures: Time Series Transformer, Vision Transformer, Graph Attention Transformer, and hybrid models, along with their variants in recent EEG analysis. We categorize transformer-based EEG studies according to the most frequent applications in motor imagery classification, emotion recognition, and seizure detection. This paper also highlights the challenges of applying transformers to EEG datasets and reviews data augmentation and transfer learning as potential solutions explored in recent years. Finally, we provide a summarized comparison of the most recent reported results. We hope this paper serves as a roadmap for researchers interested in employing transformer architectures in EEG analysis.
format Article
id doaj-art-e0a67566b4584bfe8c4ca97c0c35c37f
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e0a67566b4584bfe8c4ca97c0c35c37f2025-08-20T02:52:45ZengMDPI AGSensors1424-82202025-02-01255129310.3390/s25051293Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion ClassificationElnaz Vafaei0Mohammad Hosseini1Department of Psychology, Northeastern University, Boston, MA 02115, USADepartment of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran 1477893855, IranTransformers have rapidly influenced research across various domains. With their superior capability to encode long sequences, they have demonstrated exceptional performance, outperforming existing machine learning methods. There has been a rapid increase in the development of transformer-based models for EEG analysis. The high volumes of recently published papers highlight the need for further studies exploring transformer architectures, key components, and models employed particularly in EEG studies. This paper aims to explore four major transformer architectures: Time Series Transformer, Vision Transformer, Graph Attention Transformer, and hybrid models, along with their variants in recent EEG analysis. We categorize transformer-based EEG studies according to the most frequent applications in motor imagery classification, emotion recognition, and seizure detection. This paper also highlights the challenges of applying transformers to EEG datasets and reviews data augmentation and transfer learning as potential solutions explored in recent years. Finally, we provide a summarized comparison of the most recent reported results. We hope this paper serves as a roadmap for researchers interested in employing transformer architectures in EEG analysis.https://www.mdpi.com/1424-8220/25/5/1293transformersvision transformergraph attention transformerelectroencephalography (EEG)brain–computer interface (BCI)motor imagery classification
spellingShingle Elnaz Vafaei
Mohammad Hosseini
Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
Sensors
transformers
vision transformer
graph attention transformer
electroencephalography (EEG)
brain–computer interface (BCI)
motor imagery classification
title Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
title_full Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
title_fullStr Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
title_full_unstemmed Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
title_short Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification
title_sort transformers in eeg analysis a review of architectures and applications in motor imagery seizure and emotion classification
topic transformers
vision transformer
graph attention transformer
electroencephalography (EEG)
brain–computer interface (BCI)
motor imagery classification
url https://www.mdpi.com/1424-8220/25/5/1293
work_keys_str_mv AT elnazvafaei transformersineeganalysisareviewofarchitecturesandapplicationsinmotorimageryseizureandemotionclassification
AT mohammadhosseini transformersineeganalysisareviewofarchitecturesandapplicationsinmotorimageryseizureandemotionclassification