Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG
This paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/14/6957 |
| _version_ | 1797433864502640640 |
|---|---|
| author | Yu-Syuan Jhang Szu-Ting Wang Ming-Hwa Sheu Szu-Hong Wang Shin-Chi Lai |
| author_facet | Yu-Syuan Jhang Szu-Ting Wang Ming-Hwa Sheu Szu-Hong Wang Shin-Chi Lai |
| author_sort | Yu-Syuan Jhang |
| collection | DOAJ |
| description | This paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are as follows: (1) In the skip connection layer, less memory is needed to transfer the features extracted by the neural network; (2) Pixel shuffle and pixel unshuffle techniques with point-wise convolution are used to effectively reserve the key features generated from each layer in both the encoder and decoder; (3) Overall, fewer parameters are required to reconstruct the ECG signal. This paper describes three deep neural network models, namely CPDAE<sub>Lite</sub>, CPDAE<sub>Regular</sub>, and CPDAE<sub>Full</sub>, which support various computational capacity and hardware arrangements. The three proposed structures involve an encoder and decoder with six, seven, and eight layers, respectively. Furthermore, the CPDAE<sub>Lite</sub>, CPDAE<sub>Regular</sub>, and CPDAE<sub>Full</sub> structures require fewer multiply-accumulate operations—355.01, 56.96, and 14.69 million, respectively—and less parameter usage—2.69 million, 149.7 thousand, and 55.5 thousand, respectively. To evaluate the denoising performance, the MIT–BIH noise stress test database containing six signal-to-noise ratios (SNRs) of noisy ECGs was employed. The results demonstrated that the proposed models had a higher improvement of SNR and lower percentage root-mean-square difference than other state-of-the-art methods under various conditions of SNR. |
| first_indexed | 2024-03-09T10:22:59Z |
| format | Article |
| id | doaj.art-2e083c99e5aa41bdad7a0ad1cc67d5e0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T10:22:59Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2e083c99e5aa41bdad7a0ad1cc67d5e02023-12-01T21:50:55ZengMDPI AGApplied Sciences2076-34172022-07-011214695710.3390/app12146957Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECGYu-Syuan Jhang0Szu-Ting Wang1Ming-Hwa Sheu2Szu-Hong Wang3Shin-Chi Lai4Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin 640301, TaiwanDoctor’s Program of Smart Industry Technology Research and Design, National Formosa University, Yunlin 632301, TaiwanDepartment of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin 640301, TaiwanDepartment of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin 640301, TaiwanDepartment of Automation Engineering, National Formosa University, Yunlin 632301, TaiwanThis paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are as follows: (1) In the skip connection layer, less memory is needed to transfer the features extracted by the neural network; (2) Pixel shuffle and pixel unshuffle techniques with point-wise convolution are used to effectively reserve the key features generated from each layer in both the encoder and decoder; (3) Overall, fewer parameters are required to reconstruct the ECG signal. This paper describes three deep neural network models, namely CPDAE<sub>Lite</sub>, CPDAE<sub>Regular</sub>, and CPDAE<sub>Full</sub>, which support various computational capacity and hardware arrangements. The three proposed structures involve an encoder and decoder with six, seven, and eight layers, respectively. Furthermore, the CPDAE<sub>Lite</sub>, CPDAE<sub>Regular</sub>, and CPDAE<sub>Full</sub> structures require fewer multiply-accumulate operations—355.01, 56.96, and 14.69 million, respectively—and less parameter usage—2.69 million, 149.7 thousand, and 55.5 thousand, respectively. To evaluate the denoising performance, the MIT–BIH noise stress test database containing six signal-to-noise ratios (SNRs) of noisy ECGs was employed. The results demonstrated that the proposed models had a higher improvement of SNR and lower percentage root-mean-square difference than other state-of-the-art methods under various conditions of SNR.https://www.mdpi.com/2076-3417/12/14/6957electrocardiogram (ECG)deep learningdenoising autoencodersignal denoising |
| spellingShingle | Yu-Syuan Jhang Szu-Ting Wang Ming-Hwa Sheu Szu-Hong Wang Shin-Chi Lai Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG Applied Sciences electrocardiogram (ECG) deep learning denoising autoencoder signal denoising |
| title | Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG |
| title_full | Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG |
| title_fullStr | Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG |
| title_full_unstemmed | Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG |
| title_short | Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG |
| title_sort | channel wise average pooling and 1d pixel shuffle denoising autoencoder for electrode motion artifact removal in ecg |
| topic | electrocardiogram (ECG) deep learning denoising autoencoder signal denoising |
| url | https://www.mdpi.com/2076-3417/12/14/6957 |
| work_keys_str_mv | AT yusyuanjhang channelwiseaveragepoolingand1dpixelshuffledenoisingautoencoderforelectrodemotionartifactremovalinecg AT szutingwang channelwiseaveragepoolingand1dpixelshuffledenoisingautoencoderforelectrodemotionartifactremovalinecg AT minghwasheu channelwiseaveragepoolingand1dpixelshuffledenoisingautoencoderforelectrodemotionartifactremovalinecg AT szuhongwang channelwiseaveragepoolingand1dpixelshuffledenoisingautoencoderforelectrodemotionartifactremovalinecg AT shinchilai channelwiseaveragepoolingand1dpixelshuffledenoisingautoencoderforelectrodemotionartifactremovalinecg |