Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification
Feature extraction and classification play an important role in brain–computer interface (BCI) systems. In traditional approaches, methods in pattern recognition field are adopted to solve these problems. Nowadays, the deep learning theory has developed so fast that researchers have emplo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8585027/ |
| _version_ | 1818557075614072832 |
|---|---|
| author | Baoguo Xu Linlin Zhang Aiguo Song Changcheng Wu Wenlong Li Dalin Zhang Guozheng Xu Huijun Li Hong Zeng |
| author_facet | Baoguo Xu Linlin Zhang Aiguo Song Changcheng Wu Wenlong Li Dalin Zhang Guozheng Xu Huijun Li Hong Zeng |
| author_sort | Baoguo Xu |
| collection | DOAJ |
| description | Feature extraction and classification play an important role in brain–computer interface (BCI) systems. In traditional approaches, methods in pattern recognition field are adopted to solve these problems. Nowadays, the deep learning theory has developed so fast that researchers have employed it in many areas like computer vision and speech recognition, which have achieved remarkable results. However, few people introduce the deep learning method into the study of biomedical signals, especially EEG signals. In this paper, a wavelet transform-based input, which combines the time-frequency images of C3, Cz, and C4 channels, is proposed to extract the feature of motor imagery EEG signal. Then, a 2-Layer convolutional neural network is built as the classifier and convolutional kernels of different sizes are validated. The performance obtained by the proposed approach is evaluated by accuracy and Kappa value. The accuracy on dataset III from BCI competition II reaches 90%, and the best Kappa value on dataset 2a from competition IV is greater than many of other methods. In addition, the proposed method utilizes a resized small input, which reduces calculation complexity, so the training period is relatively faster. The results show that the method using convolutional neural network can be comparable or better than the other state-of-the-art approaches, and the performance will be improved when there is sufficient data. |
| first_indexed | 2024-12-13T23:55:17Z |
| format | Article |
| id | doaj.art-3485c007470a4b63b7b8da93ea04b4d9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T23:55:17Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3485c007470a4b63b7b8da93ea04b4d92022-12-21T23:26:34ZengIEEEIEEE Access2169-35362019-01-0176084609310.1109/ACCESS.2018.28890938585027Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG ClassificationBaoguo Xu0https://orcid.org/0000-0001-7714-9645Linlin Zhang1Aiguo Song2https://orcid.org/0000-0002-1982-6780Changcheng Wu3Wenlong Li4Dalin Zhang5Guozheng Xu6Huijun Li7Hong Zeng8State Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaCollege of Automation, Nanjing University of Posts and Telecommunications, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaState Key Laboratory of Bioelectronics, Jiangsu Key Lab of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaFeature extraction and classification play an important role in brain–computer interface (BCI) systems. In traditional approaches, methods in pattern recognition field are adopted to solve these problems. Nowadays, the deep learning theory has developed so fast that researchers have employed it in many areas like computer vision and speech recognition, which have achieved remarkable results. However, few people introduce the deep learning method into the study of biomedical signals, especially EEG signals. In this paper, a wavelet transform-based input, which combines the time-frequency images of C3, Cz, and C4 channels, is proposed to extract the feature of motor imagery EEG signal. Then, a 2-Layer convolutional neural network is built as the classifier and convolutional kernels of different sizes are validated. The performance obtained by the proposed approach is evaluated by accuracy and Kappa value. The accuracy on dataset III from BCI competition II reaches 90%, and the best Kappa value on dataset 2a from competition IV is greater than many of other methods. In addition, the proposed method utilizes a resized small input, which reduces calculation complexity, so the training period is relatively faster. The results show that the method using convolutional neural network can be comparable or better than the other state-of-the-art approaches, and the performance will be improved when there is sufficient data.https://ieeexplore.ieee.org/document/8585027/Brain computer interface (BCI)motor imagery (MI)wavelet transform time-frequency imageconvolutional neural network (CNN) |
| spellingShingle | Baoguo Xu Linlin Zhang Aiguo Song Changcheng Wu Wenlong Li Dalin Zhang Guozheng Xu Huijun Li Hong Zeng Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification IEEE Access Brain computer interface (BCI) motor imagery (MI) wavelet transform time-frequency image convolutional neural network (CNN) |
| title | Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification |
| title_full | Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification |
| title_fullStr | Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification |
| title_full_unstemmed | Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification |
| title_short | Wavelet Transform Time-Frequency Image and Convolutional Network-Based Motor Imagery EEG Classification |
| title_sort | wavelet transform time frequency image and convolutional network based motor imagery eeg classification |
| topic | Brain computer interface (BCI) motor imagery (MI) wavelet transform time-frequency image convolutional neural network (CNN) |
| url | https://ieeexplore.ieee.org/document/8585027/ |
| work_keys_str_mv | AT baoguoxu wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT linlinzhang wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT aiguosong wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT changchengwu wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT wenlongli wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT dalinzhang wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT guozhengxu wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT huijunli wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification AT hongzeng wavelettransformtimefrequencyimageandconvolutionalnetworkbasedmotorimageryeegclassification |