Dual attentive fusion for EEG-based brain-computer interfaces
The classification based on Electroencephalogram (EEG) is a challenging task in the brain-computer interface (BCI) field due to data with a low signal-to-noise ratio. Most current deep learning based studies in this challenge focus on designing a desired convolutional neural network (CNN) to learn a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.1044631/full |
| _version_ | 1811186733249724416 |
|---|---|
| author | Yuanhua Du Jian Huang Xiuyu Huang Kaibo Shi Nan Zhou |
| author_facet | Yuanhua Du Jian Huang Xiuyu Huang Kaibo Shi Nan Zhou |
| author_sort | Yuanhua Du |
| collection | DOAJ |
| description | The classification based on Electroencephalogram (EEG) is a challenging task in the brain-computer interface (BCI) field due to data with a low signal-to-noise ratio. Most current deep learning based studies in this challenge focus on designing a desired convolutional neural network (CNN) to learn and classify the raw EEG signals. However, only CNN itself may not capture the highly discriminative patterns of EEG due to a lack of exploration of attentive spatial and temporal dynamics. To improve information utilization, this study proposes a Dual Attentive Fusion Model (DAFM) for the EEG-based BCI. DAFM is employed to capture the spatial and temporal information by modeling the interdependencies between the features from the EEG signals. To our best knowledge, our method is the first to fuse spatial and temporal dimensions in an interactive attention module. This module improves the expression ability of the extracted features. Extensive experiments implemented on four publicly available datasets demonstrate that our method outperforms state-of-the-art methods. Meanwhile, this work also indicates the effectiveness of Dual Attentive Fusion Module. |
| first_indexed | 2024-04-11T13:51:27Z |
| format | Article |
| id | doaj.art-55492afbfd324e759fe5a7ba7023b30f |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-11T13:51:27Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-55492afbfd324e759fe5a7ba7023b30f2022-12-22T04:20:35ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-11-011610.3389/fnins.2022.10446311044631Dual attentive fusion for EEG-based brain-computer interfacesYuanhua Du0Jian Huang1Xiuyu Huang2Kaibo Shi3Nan Zhou4College of Applied Mathematics, Chengdu University of Information Technology, Chengdu, ChinaCollege of Applied Mathematics, Chengdu University of Information Technology, Chengdu, ChinaCentre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR, ChinaSchool of Electronic Information and Electronic Engineering, Chengdu University, Chengdu, ChinaSchool of Electronic Information and Electronic Engineering, Chengdu University, Chengdu, ChinaThe classification based on Electroencephalogram (EEG) is a challenging task in the brain-computer interface (BCI) field due to data with a low signal-to-noise ratio. Most current deep learning based studies in this challenge focus on designing a desired convolutional neural network (CNN) to learn and classify the raw EEG signals. However, only CNN itself may not capture the highly discriminative patterns of EEG due to a lack of exploration of attentive spatial and temporal dynamics. To improve information utilization, this study proposes a Dual Attentive Fusion Model (DAFM) for the EEG-based BCI. DAFM is employed to capture the spatial and temporal information by modeling the interdependencies between the features from the EEG signals. To our best knowledge, our method is the first to fuse spatial and temporal dimensions in an interactive attention module. This module improves the expression ability of the extracted features. Extensive experiments implemented on four publicly available datasets demonstrate that our method outperforms state-of-the-art methods. Meanwhile, this work also indicates the effectiveness of Dual Attentive Fusion Module.https://www.frontiersin.org/articles/10.3389/fnins.2022.1044631/fullbrain-computer interfaceelectroencephalographyP300motor imagerydual attentive fusion |
| spellingShingle | Yuanhua Du Jian Huang Xiuyu Huang Kaibo Shi Nan Zhou Dual attentive fusion for EEG-based brain-computer interfaces Frontiers in Neuroscience brain-computer interface electroencephalography P300 motor imagery dual attentive fusion |
| title | Dual attentive fusion for EEG-based brain-computer interfaces |
| title_full | Dual attentive fusion for EEG-based brain-computer interfaces |
| title_fullStr | Dual attentive fusion for EEG-based brain-computer interfaces |
| title_full_unstemmed | Dual attentive fusion for EEG-based brain-computer interfaces |
| title_short | Dual attentive fusion for EEG-based brain-computer interfaces |
| title_sort | dual attentive fusion for eeg based brain computer interfaces |
| topic | brain-computer interface electroencephalography P300 motor imagery dual attentive fusion |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.1044631/full |
| work_keys_str_mv | AT yuanhuadu dualattentivefusionforeegbasedbraincomputerinterfaces AT jianhuang dualattentivefusionforeegbasedbraincomputerinterfaces AT xiuyuhuang dualattentivefusionforeegbasedbraincomputerinterfaces AT kaiboshi dualattentivefusionforeegbasedbraincomputerinterfaces AT nanzhou dualattentivefusionforeegbasedbraincomputerinterfaces |