EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916298532847616 |
|---|---|
| author | Liao, Wangdan Wang, Weidong |
| author_facet | Liao, Wangdan Wang, Weidong |
| contents | Brain-computer interfaces (BCIs) harness electroencephalographic signals for direct neural control of devices, offering a significant benefit for individuals with motor impairments. Traditional machine learning methods for EEG-based motor imagery (MI) classification encounter challenges such as manual feature extraction and susceptibility to noise.This paper introduces EEGEncoder, a deep learning framework that employs modified transformers and TCNs to surmount these limitations. We innovatively propose a fusion architecture, namely Dual-Stream Temporal-Spatial Block (DSTS), to capture temporal and spatial features, improving the accuracy of Motor Imagery classification task. Additionally, we use multiple parallel structures to enhance the performance of the model. When tested on the BCI Competition IV-2a dataset, our model results outperform current state-of-the-art techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14869 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification Liao, Wangdan Wang, Weidong Human-Computer Interaction Machine Learning Brain-computer interfaces (BCIs) harness electroencephalographic signals for direct neural control of devices, offering a significant benefit for individuals with motor impairments. Traditional machine learning methods for EEG-based motor imagery (MI) classification encounter challenges such as manual feature extraction and susceptibility to noise.This paper introduces EEGEncoder, a deep learning framework that employs modified transformers and TCNs to surmount these limitations. We innovatively propose a fusion architecture, namely Dual-Stream Temporal-Spatial Block (DSTS), to capture temporal and spatial features, improving the accuracy of Motor Imagery classification task. Additionally, we use multiple parallel structures to enhance the performance of the model. When tested on the BCI Competition IV-2a dataset, our model results outperform current state-of-the-art techniques. |
| title | EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2404.14869 |