A Novel Multimodule Neural Network for EEG Denoising
In this paper, a novel multi-module neural network (MMNN) is proposed to remove ocular artifacts (OAs) and myogenic artifacts (MAs) from noisy single-channel electroencephalogram (EEG) signals. This network is a based on deep learning (DL) architecture consisting of multiple denoising modules connec...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9770811/ |
| _version_ | 1818201288771371008 |
|---|---|
| author | Zhen Zhang Xiaoyan Yu Xianwei Rong Makoto Iwata |
| author_facet | Zhen Zhang Xiaoyan Yu Xianwei Rong Makoto Iwata |
| author_sort | Zhen Zhang |
| collection | DOAJ |
| description | In this paper, a novel multi-module neural network (MMNN) is proposed to remove ocular artifacts (OAs) and myogenic artifacts (MAs) from noisy single-channel electroencephalogram (EEG) signals. This network is a based on deep learning (DL) architecture consisting of multiple denoising modules connected in parallel. Each denoising module is built using one-dimensional convolutions (Conv1Ds) and fully connected (FC) layers, and it estimates not only clean EEG signals but also artifacts. The proposed MMNN has two main advantages. Frist, the multiple denoising modules can purify noisy input EEG signals by continuously removing artifacts in the forward propagation. Second, the parallel architecture allows the parameters of each denoising module to be updated concurrently in the backpropagation, thereby improving the learning capacity of neural networks. We tested the network denoising performance using a recent public database, namely, EEGdenoiseNet. The results revealed that the proposed network reduced the temporal relative root mean square error (T-RRMSE) and spectral relative root mean square error (S-RRMSE) by at least 6% and enhanced the correlation coefficient (CC) by at least 3% over the state-of-the-art approaches. These significant performance improvements were confirmed by observing the deviation distribution between the denoised and clean signals. Furthermore, the proposed network achieved a similar performance efficiency with only 60% of the training data compared to the existing DL models. Our model can be found at: <uri>https://github.com/Zhangzhenkut/Multi-Module-Neural-Network-for-EEG-Denoising</uri> |
| first_indexed | 2024-12-12T02:51:11Z |
| format | Article |
| id | doaj.art-82d643cbc6b14f289db9f213538d4097 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T02:51:11Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-82d643cbc6b14f289db9f213538d40972022-12-22T00:40:53ZengIEEEIEEE Access2169-35362022-01-0110495284954110.1109/ACCESS.2022.31732619770811A Novel Multimodule Neural Network for EEG DenoisingZhen Zhang0https://orcid.org/0000-0003-0618-3154Xiaoyan Yu1https://orcid.org/0000-0003-3252-6982Xianwei Rong2https://orcid.org/0000-0002-6779-4111Makoto Iwata3https://orcid.org/0000-0001-9537-984XSchool of Information, Kochi University of Technology, Kochi, JapanDepartment of Physics and Electronic Engineering, Harbin Normal University, Harbin, ChinaDepartment of Physics and Electronic Engineering, Harbin Normal University, Harbin, ChinaSchool of Information, Kochi University of Technology, Kochi, JapanIn this paper, a novel multi-module neural network (MMNN) is proposed to remove ocular artifacts (OAs) and myogenic artifacts (MAs) from noisy single-channel electroencephalogram (EEG) signals. This network is a based on deep learning (DL) architecture consisting of multiple denoising modules connected in parallel. Each denoising module is built using one-dimensional convolutions (Conv1Ds) and fully connected (FC) layers, and it estimates not only clean EEG signals but also artifacts. The proposed MMNN has two main advantages. Frist, the multiple denoising modules can purify noisy input EEG signals by continuously removing artifacts in the forward propagation. Second, the parallel architecture allows the parameters of each denoising module to be updated concurrently in the backpropagation, thereby improving the learning capacity of neural networks. We tested the network denoising performance using a recent public database, namely, EEGdenoiseNet. The results revealed that the proposed network reduced the temporal relative root mean square error (T-RRMSE) and spectral relative root mean square error (S-RRMSE) by at least 6% and enhanced the correlation coefficient (CC) by at least 3% over the state-of-the-art approaches. These significant performance improvements were confirmed by observing the deviation distribution between the denoised and clean signals. Furthermore, the proposed network achieved a similar performance efficiency with only 60% of the training data compared to the existing DL models. Our model can be found at: <uri>https://github.com/Zhangzhenkut/Multi-Module-Neural-Network-for-EEG-Denoising</uri>https://ieeexplore.ieee.org/document/9770811/EEG denoisingmulti-module neural network (MMNN)deep learning (DL) |
| spellingShingle | Zhen Zhang Xiaoyan Yu Xianwei Rong Makoto Iwata A Novel Multimodule Neural Network for EEG Denoising IEEE Access EEG denoising multi-module neural network (MMNN) deep learning (DL) |
| title | A Novel Multimodule Neural Network for EEG Denoising |
| title_full | A Novel Multimodule Neural Network for EEG Denoising |
| title_fullStr | A Novel Multimodule Neural Network for EEG Denoising |
| title_full_unstemmed | A Novel Multimodule Neural Network for EEG Denoising |
| title_short | A Novel Multimodule Neural Network for EEG Denoising |
| title_sort | novel multimodule neural network for eeg denoising |
| topic | EEG denoising multi-module neural network (MMNN) deep learning (DL) |
| url | https://ieeexplore.ieee.org/document/9770811/ |
| work_keys_str_mv | AT zhenzhang anovelmultimoduleneuralnetworkforeegdenoising AT xiaoyanyu anovelmultimoduleneuralnetworkforeegdenoising AT xianweirong anovelmultimoduleneuralnetworkforeegdenoising AT makotoiwata anovelmultimoduleneuralnetworkforeegdenoising AT zhenzhang novelmultimoduleneuralnetworkforeegdenoising AT xiaoyanyu novelmultimoduleneuralnetworkforeegdenoising AT xianweirong novelmultimoduleneuralnetworkforeegdenoising AT makotoiwata novelmultimoduleneuralnetworkforeegdenoising |