A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding
In recent years, deep-learning-based motor imagery (MI) electroencephalography (EEG) decoding methods have shown great potential in the field of the brain–computer interface (BCI). The existing literature is relatively mature in decoding methods for two classes of MI tasks. However, with the increas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/9/1233 |
| _version_ | 1797490453278359552 |
|---|---|
| author | Siheng Gao Jun Yang Tao Shen Wen Jiang |
| author_facet | Siheng Gao Jun Yang Tao Shen Wen Jiang |
| author_sort | Siheng Gao |
| collection | DOAJ |
| description | In recent years, deep-learning-based motor imagery (MI) electroencephalography (EEG) decoding methods have shown great potential in the field of the brain–computer interface (BCI). The existing literature is relatively mature in decoding methods for two classes of MI tasks. However, with the increase in MI task classes, decoding studies for four classes of MI tasks need to be further explored. In addition, it is difficult to obtain large-scale EEG datasets. When the training data are limited, deep-learning-based decoding models are prone to problems such as overfitting and poor robustness. In this study, we design a data augmentation method for MI-EEG. The original EEG is slid along the time axis and reconstructed to expand the size of the dataset. Second, we combine the gated recurrent unit (GRU) and convolutional neural network (CNN) to construct a parallel-structured feature fusion network to decode four classes of MI tasks. The parallel structure can avoid temporal, frequency and spatial features interfering with each other. Experimenting on the well-known four-class MI dataset BCI Competition IV 2a shows a global average classification accuracy of 80.7% and a kappa value of 0.74. The proposed method improves the robustness of deep learning to decode small-scale EEG datasets and alleviates the overfitting phenomenon caused by insufficient data. The method can be applied to BCI systems with a small amount of daily recorded data. |
| first_indexed | 2024-03-10T00:33:12Z |
| format | Article |
| id | doaj.art-2b8baf81687f41b0b5efa7cb8a780a88 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-10T00:33:12Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-2b8baf81687f41b0b5efa7cb8a780a882023-11-23T15:21:28ZengMDPI AGBrain Sciences2076-34252022-09-01129123310.3390/brainsci12091233A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG DecodingSiheng Gao0Jun Yang1Tao Shen2Wen Jiang3Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaIn recent years, deep-learning-based motor imagery (MI) electroencephalography (EEG) decoding methods have shown great potential in the field of the brain–computer interface (BCI). The existing literature is relatively mature in decoding methods for two classes of MI tasks. However, with the increase in MI task classes, decoding studies for four classes of MI tasks need to be further explored. In addition, it is difficult to obtain large-scale EEG datasets. When the training data are limited, deep-learning-based decoding models are prone to problems such as overfitting and poor robustness. In this study, we design a data augmentation method for MI-EEG. The original EEG is slid along the time axis and reconstructed to expand the size of the dataset. Second, we combine the gated recurrent unit (GRU) and convolutional neural network (CNN) to construct a parallel-structured feature fusion network to decode four classes of MI tasks. The parallel structure can avoid temporal, frequency and spatial features interfering with each other. Experimenting on the well-known four-class MI dataset BCI Competition IV 2a shows a global average classification accuracy of 80.7% and a kappa value of 0.74. The proposed method improves the robustness of deep learning to decode small-scale EEG datasets and alleviates the overfitting phenomenon caused by insufficient data. The method can be applied to BCI systems with a small amount of daily recorded data.https://www.mdpi.com/2076-3425/12/9/1233brain-computer interface (BCI)convolutional neural network (CNN)four-class motor imagerygated recurrent unit (GRU) |
| spellingShingle | Siheng Gao Jun Yang Tao Shen Wen Jiang A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding Brain Sciences brain-computer interface (BCI) convolutional neural network (CNN) four-class motor imagery gated recurrent unit (GRU) |
| title | A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding |
| title_full | A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding |
| title_fullStr | A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding |
| title_full_unstemmed | A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding |
| title_short | A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding |
| title_sort | parallel feature fusion network combining gru and cnn for motor imagery eeg decoding |
| topic | brain-computer interface (BCI) convolutional neural network (CNN) four-class motor imagery gated recurrent unit (GRU) |
| url | https://www.mdpi.com/2076-3425/12/9/1233 |
| work_keys_str_mv | AT sihenggao aparallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT junyang aparallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT taoshen aparallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT wenjiang aparallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT sihenggao parallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT junyang parallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT taoshen parallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding AT wenjiang parallelfeaturefusionnetworkcombininggruandcnnformotorimageryeegdecoding |