Analysis of EEG Signals Fused With CNN and Complex Networks
Currently, brain-computer interface technology still poses hidden dangers in the complete control of ideas. Additionally, there are issues with the low sampling frequency and accuracy of EEG signal acquisition equipment. To address these concerns, this study proposes a combined model for EEG signal...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10474366/ |
| _version_ | 1797238857062678528 |
|---|---|
| author | Lu Ma Haipeng Xu |
| author_facet | Lu Ma Haipeng Xu |
| author_sort | Lu Ma |
| collection | DOAJ |
| description | Currently, brain-computer interface technology still poses hidden dangers in the complete control of ideas. Additionally, there are issues with the low sampling frequency and accuracy of EEG signal acquisition equipment. To address these concerns, this study proposes a combined model for EEG signal recognition and classification analysis by combining frequency division multi-feature complex brain networks with parallel convolutional neural networks. The effectiveness of this model has been verified. In model visualization analysis, the visualization results of t-distribution random neighborhood embedding in the third separable convolutional layer indicate that the two types of imagination have already experienced separation. There is a clear boundary between the two at position 0 on both the horizontal and vertical axes. This is a significant improvement compared to the comparative model. In the model performance verification, the full band classification accuracy in the synchronous network was maintained between 60% to 84%, and the <inline-formula> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula>-rhythm was maintained between 59% to 81%. The average classification accuracy of the combined model was 77.40% with higher performance, which was higher than 68.53% and 70.87% of the single scale convolutional neural network. In comparison with deep learning algorithms, the average classification accuracy of the combined model was 85.74%, much higher than the 66.20% and 76.69% of the comparative models. The composite model constructed has good performance in recognizing and classifying electroencephalogram signals. It can be effectively applied in practical brain-computer interface technology or electroencephalogram signal analysis. The potential application area of this study in the future is the recognition and processing of complex EEG signals in medical institutions, which can improve the efficiency of signal processing in this field and reduce the manpower expenditure of medical personnel. |
| first_indexed | 2024-04-24T17:42:18Z |
| format | Article |
| id | doaj.art-ea727bb926d34026971893a001bab693 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T17:42:18Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ea727bb926d34026971893a001bab6932024-03-27T23:00:16ZengIEEEIEEE Access2169-35362024-01-0112427104272410.1109/ACCESS.2024.337873210474366Analysis of EEG Signals Fused With CNN and Complex NetworksLu Ma0https://orcid.org/0009-0004-3971-5633Haipeng Xu1School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaShangqiu City Development Investment Group Company Ltd., Shangqiu, ChinaCurrently, brain-computer interface technology still poses hidden dangers in the complete control of ideas. Additionally, there are issues with the low sampling frequency and accuracy of EEG signal acquisition equipment. To address these concerns, this study proposes a combined model for EEG signal recognition and classification analysis by combining frequency division multi-feature complex brain networks with parallel convolutional neural networks. The effectiveness of this model has been verified. In model visualization analysis, the visualization results of t-distribution random neighborhood embedding in the third separable convolutional layer indicate that the two types of imagination have already experienced separation. There is a clear boundary between the two at position 0 on both the horizontal and vertical axes. This is a significant improvement compared to the comparative model. In the model performance verification, the full band classification accuracy in the synchronous network was maintained between 60% to 84%, and the <inline-formula> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula>-rhythm was maintained between 59% to 81%. The average classification accuracy of the combined model was 77.40% with higher performance, which was higher than 68.53% and 70.87% of the single scale convolutional neural network. In comparison with deep learning algorithms, the average classification accuracy of the combined model was 85.74%, much higher than the 66.20% and 76.69% of the comparative models. The composite model constructed has good performance in recognizing and classifying electroencephalogram signals. It can be effectively applied in practical brain-computer interface technology or electroencephalogram signal analysis. The potential application area of this study in the future is the recognition and processing of complex EEG signals in medical institutions, which can improve the efficiency of signal processing in this field and reduce the manpower expenditure of medical personnel.https://ieeexplore.ieee.org/document/10474366/Frequency division multi feature complex brain networkparallel convolutional neural networkclassification accuracyfull frequency bandsynchronous network |
| spellingShingle | Lu Ma Haipeng Xu Analysis of EEG Signals Fused With CNN and Complex Networks IEEE Access Frequency division multi feature complex brain network parallel convolutional neural network classification accuracy full frequency band synchronous network |
| title | Analysis of EEG Signals Fused With CNN and Complex Networks |
| title_full | Analysis of EEG Signals Fused With CNN and Complex Networks |
| title_fullStr | Analysis of EEG Signals Fused With CNN and Complex Networks |
| title_full_unstemmed | Analysis of EEG Signals Fused With CNN and Complex Networks |
| title_short | Analysis of EEG Signals Fused With CNN and Complex Networks |
| title_sort | analysis of eeg signals fused with cnn and complex networks |
| topic | Frequency division multi feature complex brain network parallel convolutional neural network classification accuracy full frequency band synchronous network |
| url | https://ieeexplore.ieee.org/document/10474366/ |
| work_keys_str_mv | AT luma analysisofeegsignalsfusedwithcnnandcomplexnetworks AT haipengxu analysisofeegsignalsfusedwithcnnandcomplexnetworks |