DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network
Electroencephalogram (EEG) signals are important bioelectrical signals widely used in brain activity studies, cognitive mechanism research, and the diagnosis and treatment of neurological disorders. However, EEG signals are often influenced by various physiological artifacts, which can significantly...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548951912710144 |
|---|---|
| author | Yinan Cai Zhao Meng Dian Huang |
| author_facet | Yinan Cai Zhao Meng Dian Huang |
| author_sort | Yinan Cai |
| collection | DOAJ |
| description | Electroencephalogram (EEG) signals are important bioelectrical signals widely used in brain activity studies, cognitive mechanism research, and the diagnosis and treatment of neurological disorders. However, EEG signals are often influenced by various physiological artifacts, which can significantly affect data analysis and diagnosis. Recently, deep learning-based EEG denoising methods have exhibited unique advantages over traditional methods. Most existing methods mainly focus on identifying the characteristics of clean EEG signals to facilitate artifact removal; however, the potential to integrate cross-disciplinary knowledge, such as insights from artifact research, remains an area that requires further exploration. In this study, we developed DHCT-GAN, a new EEG denoising model, using a dual-branch hybrid network architecture. This model independently learns features from both clean EEG signals and artifact signals, then fuses this information through an adaptive gating network to generate denoised EEG signals that accurately preserve EEG signal features while effectively removing artifacts. We evaluated DHCT-GAN’s performance through waveform analysis, power spectral density (PSD) analysis, and six performance metrics. The results demonstrate that DHCT-GAN significantly outperforms recent state-of-the-art networks in removing various artifacts. Furthermore, ablation experiments revealed that the hybrid model surpasses single-branch models in artifact removal, underscoring the crucial role of artifact knowledge constraints in improving denoising effectiveness. |
| format | Article |
| id | doaj-art-d3f152e100f14e379f341b6eeeed1d1b |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-d3f152e100f14e379f341b6eeeed1d1b2025-01-10T13:21:18ZengMDPI AGSensors1424-82202025-01-0125123110.3390/s25010231DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer NetworkYinan Cai0Zhao Meng1Dian Huang2National Supercomputing Center in Shenzhen, Shenzhen 518055, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaGuangdong Institute of Intelligence Science and Technology, Hengqin, Zhuhai 519031, ChinaElectroencephalogram (EEG) signals are important bioelectrical signals widely used in brain activity studies, cognitive mechanism research, and the diagnosis and treatment of neurological disorders. However, EEG signals are often influenced by various physiological artifacts, which can significantly affect data analysis and diagnosis. Recently, deep learning-based EEG denoising methods have exhibited unique advantages over traditional methods. Most existing methods mainly focus on identifying the characteristics of clean EEG signals to facilitate artifact removal; however, the potential to integrate cross-disciplinary knowledge, such as insights from artifact research, remains an area that requires further exploration. In this study, we developed DHCT-GAN, a new EEG denoising model, using a dual-branch hybrid network architecture. This model independently learns features from both clean EEG signals and artifact signals, then fuses this information through an adaptive gating network to generate denoised EEG signals that accurately preserve EEG signal features while effectively removing artifacts. We evaluated DHCT-GAN’s performance through waveform analysis, power spectral density (PSD) analysis, and six performance metrics. The results demonstrate that DHCT-GAN significantly outperforms recent state-of-the-art networks in removing various artifacts. Furthermore, ablation experiments revealed that the hybrid model surpasses single-branch models in artifact removal, underscoring the crucial role of artifact knowledge constraints in improving denoising effectiveness.https://www.mdpi.com/1424-8220/25/1/231electroencephalogram (EEG)transformergenerative adversarial network (GAN)denoising |
| spellingShingle | Yinan Cai Zhao Meng Dian Huang DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network Sensors electroencephalogram (EEG) transformer generative adversarial network (GAN) denoising |
| title | DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network |
| title_full | DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network |
| title_fullStr | DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network |
| title_full_unstemmed | DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network |
| title_short | DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN–Transformer Network |
| title_sort | dhct gan improving eeg signal quality with a dual branch hybrid cnn transformer network |
| topic | electroencephalogram (EEG) transformer generative adversarial network (GAN) denoising |
| url | https://www.mdpi.com/1424-8220/25/1/231 |
| work_keys_str_mv | AT yinancai dhctganimprovingeegsignalqualitywithadualbranchhybridcnntransformernetwork AT zhaomeng dhctganimprovingeegsignalqualitywithadualbranchhybridcnntransformernetwork AT dianhuang dhctganimprovingeegsignalqualitywithadualbranchhybridcnntransformernetwork |