Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement
Motor Imagery (MI) based on Electroencephalography (EEG), a typical Brain-Computer Interface (BCI) paradigm, can communicate with external devices according to the brain’s intentions. Convolutional Neural Networks (CNN) are gradually used for EEG classification tasks and have achieved sat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10036384/ |
| _version_ | 1797805065950461952 |
|---|---|
| author | Xianlun Tang Caiquan Yang Xia Sun Mi Zou Huiming Wang |
| author_facet | Xianlun Tang Caiquan Yang Xia Sun Mi Zou Huiming Wang |
| author_sort | Xianlun Tang |
| collection | DOAJ |
| description | Motor Imagery (MI) based on Electroencephalography (EEG), a typical Brain-Computer Interface (BCI) paradigm, can communicate with external devices according to the brain’s intentions. Convolutional Neural Networks (CNN) are gradually used for EEG classification tasks and have achieved satisfactory performance. However, most CNN-based methods employ a single convolution mode and a convolution kernel size, which cannot extract multi-scale advanced temporal and spatial features efficiently. What’s more, they hinder the further improvement of the classification accuracy of MI-EEG signals. This paper proposes a novel Multi-Scale Hybrid Convolutional Neural Network (MSHCNN) for MI-EEG signal decoding to improve classification performance. The two-dimensional convolution is used to extract temporal and spatial features of EEG signals and the one-dimensional convolution is used to extract advanced temporal features of EEG signals. In addition, a channel coding method is proposed to improve the expression capacity of the spatiotemporal characteristics of EEG signals. We evaluate the performance of the proposed method on the dataset collected in the laboratory and BCI competition IV 2b, 2a, and the average accuracy is at 96.87%, 85.25%, and 84.86%, respectively. Compared with other advanced methods, our proposed method achieves higher classification accuracy. Then we use the proposed method for an online experiment and design an intelligent artificial limb control system. The proposed method effectively extracts EEG signals’ advanced temporal and spatial features. Additionally, we design an online recognition system, which contributes to the further development of the BCI system. |
| first_indexed | 2024-03-13T05:46:24Z |
| format | Article |
| id | doaj.art-0f7988159593481f9b3a193e39c1036b |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:46:24Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-0f7988159593481f9b3a193e39c1036b2023-06-13T20:09:34ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01311208121810.1109/TNSRE.2023.324228010036384Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature EnhancementXianlun Tang0https://orcid.org/0000-0002-9174-7366Caiquan Yang1Xia Sun2https://orcid.org/0000-0002-2566-3949Mi Zou3Huiming Wang4https://orcid.org/0000-0003-3109-0195Chongqing Key Laboratory of Complex Systems and Bionic Control, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Complex Systems and Bionic Control, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Institute of Engineering, Chongqing, ChinaChongqing Key Laboratory of Complex Systems and Bionic Control, Chongqing University of Posts and Telecommunications, Chongqing, ChinaChongqing Key Laboratory of Complex Systems and Bionic Control, Chongqing University of Posts and Telecommunications, Chongqing, ChinaMotor Imagery (MI) based on Electroencephalography (EEG), a typical Brain-Computer Interface (BCI) paradigm, can communicate with external devices according to the brain’s intentions. Convolutional Neural Networks (CNN) are gradually used for EEG classification tasks and have achieved satisfactory performance. However, most CNN-based methods employ a single convolution mode and a convolution kernel size, which cannot extract multi-scale advanced temporal and spatial features efficiently. What’s more, they hinder the further improvement of the classification accuracy of MI-EEG signals. This paper proposes a novel Multi-Scale Hybrid Convolutional Neural Network (MSHCNN) for MI-EEG signal decoding to improve classification performance. The two-dimensional convolution is used to extract temporal and spatial features of EEG signals and the one-dimensional convolution is used to extract advanced temporal features of EEG signals. In addition, a channel coding method is proposed to improve the expression capacity of the spatiotemporal characteristics of EEG signals. We evaluate the performance of the proposed method on the dataset collected in the laboratory and BCI competition IV 2b, 2a, and the average accuracy is at 96.87%, 85.25%, and 84.86%, respectively. Compared with other advanced methods, our proposed method achieves higher classification accuracy. Then we use the proposed method for an online experiment and design an intelligent artificial limb control system. The proposed method effectively extracts EEG signals’ advanced temporal and spatial features. Additionally, we design an online recognition system, which contributes to the further development of the BCI system.https://ieeexplore.ieee.org/document/10036384/Brain–computer interfaceEEG decodingfeature enhancementmulti-scale hybrid networkartificial limb control |
| spellingShingle | Xianlun Tang Caiquan Yang Xia Sun Mi Zou Huiming Wang Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain–computer interface EEG decoding feature enhancement multi-scale hybrid network artificial limb control |
| title | Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement |
| title_full | Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement |
| title_fullStr | Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement |
| title_full_unstemmed | Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement |
| title_short | Motor Imagery EEG Decoding Based on Multi-Scale Hybrid Networks and Feature Enhancement |
| title_sort | motor imagery eeg decoding based on multi scale hybrid networks and feature enhancement |
| topic | Brain–computer interface EEG decoding feature enhancement multi-scale hybrid network artificial limb control |
| url | https://ieeexplore.ieee.org/document/10036384/ |
| work_keys_str_mv | AT xianluntang motorimageryeegdecodingbasedonmultiscalehybridnetworksandfeatureenhancement AT caiquanyang motorimageryeegdecodingbasedonmultiscalehybridnetworksandfeatureenhancement AT xiasun motorimageryeegdecodingbasedonmultiscalehybridnetworksandfeatureenhancement AT mizou motorimageryeegdecodingbasedonmultiscalehybridnetworksandfeatureenhancement AT huimingwang motorimageryeegdecodingbasedonmultiscalehybridnetworksandfeatureenhancement |