Representation Learning for Motor Imagery Recognition with Deep Neural Network
This study describes a method for classifying electrocorticograms (ECoGs) based on motor imagery (MI) on the brain–computer interface (BCI) system. This method is different from the traditional feature extraction and classification method. In this paper, the proposed method employs the deep learning...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/2/112 |
| _version_ | 1797415319070834688 |
|---|---|
| author | Fangzhou Xu Fenqi Rong Yunjing Miao Yanan Sun Gege Dong Han Li Jincheng Li Yuandong Wang Jiancai Leng |
| author_facet | Fangzhou Xu Fenqi Rong Yunjing Miao Yanan Sun Gege Dong Han Li Jincheng Li Yuandong Wang Jiancai Leng |
| author_sort | Fangzhou Xu |
| collection | DOAJ |
| description | This study describes a method for classifying electrocorticograms (ECoGs) based on motor imagery (MI) on the brain–computer interface (BCI) system. This method is different from the traditional feature extraction and classification method. In this paper, the proposed method employs the deep learning algorithm for extracting features and the traditional algorithm for classification. Specifically, we mainly use the convolution neural network (CNN) to extract the features from the training data and then classify those features by combing with the gradient boosting (GB) algorithm. The comprehensive study with CNN and GB algorithms will profoundly help us to obtain more feature information from brain activities, enabling us to obtain the classification results from human body actions. The performance of the proposed framework has been evaluated on the dataset I of BCI Competition III. Furthermore, the combination of deep learning and traditional algorithms provides some ideas for future research with the BCI systems. |
| first_indexed | 2024-03-09T05:45:58Z |
| format | Article |
| id | doaj.art-4cf5f7c1160444b49058d361834a3ece |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T05:45:58Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-4cf5f7c1160444b49058d361834a3ece2023-12-03T12:20:59ZengMDPI AGElectronics2079-92922021-01-0110211210.3390/electronics10020112Representation Learning for Motor Imagery Recognition with Deep Neural NetworkFangzhou Xu0Fenqi Rong1Yunjing Miao2Yanan Sun3Gege Dong4Han Li5Jincheng Li6Yuandong Wang7Jiancai Leng8Department of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaDepartment of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaDepartment of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaDepartment of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaDepartment of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaDepartment of Physics, School of Electronic and Information Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThis study describes a method for classifying electrocorticograms (ECoGs) based on motor imagery (MI) on the brain–computer interface (BCI) system. This method is different from the traditional feature extraction and classification method. In this paper, the proposed method employs the deep learning algorithm for extracting features and the traditional algorithm for classification. Specifically, we mainly use the convolution neural network (CNN) to extract the features from the training data and then classify those features by combing with the gradient boosting (GB) algorithm. The comprehensive study with CNN and GB algorithms will profoundly help us to obtain more feature information from brain activities, enabling us to obtain the classification results from human body actions. The performance of the proposed framework has been evaluated on the dataset I of BCI Competition III. Furthermore, the combination of deep learning and traditional algorithms provides some ideas for future research with the BCI systems.https://www.mdpi.com/2079-9292/10/2/112electrocorticogram (ECoG)motor imagery (MI)brain–computer interface (BCI)convolution neural network (CNN)gradient boosting (GB) |
| spellingShingle | Fangzhou Xu Fenqi Rong Yunjing Miao Yanan Sun Gege Dong Han Li Jincheng Li Yuandong Wang Jiancai Leng Representation Learning for Motor Imagery Recognition with Deep Neural Network Electronics electrocorticogram (ECoG) motor imagery (MI) brain–computer interface (BCI) convolution neural network (CNN) gradient boosting (GB) |
| title | Representation Learning for Motor Imagery Recognition with Deep Neural Network |
| title_full | Representation Learning for Motor Imagery Recognition with Deep Neural Network |
| title_fullStr | Representation Learning for Motor Imagery Recognition with Deep Neural Network |
| title_full_unstemmed | Representation Learning for Motor Imagery Recognition with Deep Neural Network |
| title_short | Representation Learning for Motor Imagery Recognition with Deep Neural Network |
| title_sort | representation learning for motor imagery recognition with deep neural network |
| topic | electrocorticogram (ECoG) motor imagery (MI) brain–computer interface (BCI) convolution neural network (CNN) gradient boosting (GB) |
| url | https://www.mdpi.com/2079-9292/10/2/112 |
| work_keys_str_mv | AT fangzhouxu representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT fenqirong representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT yunjingmiao representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT yanansun representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT gegedong representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT hanli representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT jinchengli representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT yuandongwang representationlearningformotorimageryrecognitionwithdeepneuralnetwork AT jiancaileng representationlearningformotorimageryrecognitionwithdeepneuralnetwork |