Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation
Electrocardiograms (ECG) are vital for diagnosing various cardiac conditions but are often corrupted by noise from multiple sources, which can hinder accurate interpretation. Denoising ECG signals is particularly challenging because noise usually overlaps with the frequency range of the signal of in...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10925413/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849767631489335296 |
|---|---|
| author | Alif Wicaksana Ramadhan Syifa Kushirayati Salsabila Aurellia Mgs M. Luthfi Ramadhan Muhammad Hannan Hunafa Muhammad Febrian Rachmadi Aprinaldi Jasa Mantau Siti Nurmaini Satria Mandala Wisnu Jatmiko |
| author_facet | Alif Wicaksana Ramadhan Syifa Kushirayati Salsabila Aurellia Mgs M. Luthfi Ramadhan Muhammad Hannan Hunafa Muhammad Febrian Rachmadi Aprinaldi Jasa Mantau Siti Nurmaini Satria Mandala Wisnu Jatmiko |
| author_sort | Alif Wicaksana Ramadhan |
| collection | DOAJ |
| description | Electrocardiograms (ECG) are vital for diagnosing various cardiac conditions but are often corrupted by noise from multiple sources, which can hinder accurate interpretation. Denoising ECG signals is particularly challenging because noise usually overlaps with the frequency range of the signal of interest. We proposed a convolutional autoencoder with sequential and channel attention (CAE-SCA) to address this issue. Sequential attention (SA) is based on long short-term memory (LSTM), which captures causal-temporal relationships. Meanwhile, channel attention (CA) is used to emphasize important features within channels. SA is applied to the skip connection of each encoder block, and CA is applied after each decoder block. We validated the CAE-SCA using the MIT-BIH and SHDB-AF databases as clean ECG signals, with the MIT-BIH Noise Stress Test Database as the noise source. Experimental results give an average SNR value of 16.187 dB, RMSE of 0.059, and PRD value of 18.529 in the MIT-BIH database. While in the SHDB-AF dataset, the model obtained 15.308 dB of SNR, 0.049 of RMSE, and 19.220 of PRD. These results demonstrate our CAE-SCA outperforms all the state-of-the-art methods across all tested metrics. For efficiency, CAE-SCA achieved competitive results in the metrics of floating-point operations (FLOPs), inference time, and total parameters. This allowed CAE-SCA to be implemented in edge devices as we tested using our custom ECG acquisition circuit. A significance test further confirms a statistically significant improvement in SNR values achieved by the CAE-SCA compared to baseline models, suggesting the CAE-SCA’s potential for advancing ECG processing in healthcare applications. |
| format | Article |
| id | doaj-art-6dac22e57f934cb1b8bc12995f41ee58 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6dac22e57f934cb1b8bc12995f41ee582025-08-20T03:04:07ZengIEEEIEEE Access2169-35362025-01-0113544075442210.1109/ACCESS.2025.355094910925413Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device ImplementationAlif Wicaksana Ramadhan0https://orcid.org/0009-0002-4090-6950Syifa Kushirayati1https://orcid.org/0009-0006-5949-166XSalsabila Aurellia2https://orcid.org/0000-0001-8370-9434Mgs M. Luthfi Ramadhan3https://orcid.org/0000-0001-8571-8924Muhammad Hannan Hunafa4https://orcid.org/0009-0006-4084-2976Muhammad Febrian Rachmadi5Aprinaldi Jasa Mantau6Siti Nurmaini7Satria Mandala8https://orcid.org/0000-0001-6997-5875Wisnu Jatmiko9https://orcid.org/0000-0002-0530-7955Faculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaIntelligent System Research Group, Sriwijaya University, Palembang, IndonesiaHuman Centric (HUMIC) Engineering, Telkom University, Bandung, IndonesiaFaculty of Computer Science, University of Indonesia, Depok, IndonesiaElectrocardiograms (ECG) are vital for diagnosing various cardiac conditions but are often corrupted by noise from multiple sources, which can hinder accurate interpretation. Denoising ECG signals is particularly challenging because noise usually overlaps with the frequency range of the signal of interest. We proposed a convolutional autoencoder with sequential and channel attention (CAE-SCA) to address this issue. Sequential attention (SA) is based on long short-term memory (LSTM), which captures causal-temporal relationships. Meanwhile, channel attention (CA) is used to emphasize important features within channels. SA is applied to the skip connection of each encoder block, and CA is applied after each decoder block. We validated the CAE-SCA using the MIT-BIH and SHDB-AF databases as clean ECG signals, with the MIT-BIH Noise Stress Test Database as the noise source. Experimental results give an average SNR value of 16.187 dB, RMSE of 0.059, and PRD value of 18.529 in the MIT-BIH database. While in the SHDB-AF dataset, the model obtained 15.308 dB of SNR, 0.049 of RMSE, and 19.220 of PRD. These results demonstrate our CAE-SCA outperforms all the state-of-the-art methods across all tested metrics. For efficiency, CAE-SCA achieved competitive results in the metrics of floating-point operations (FLOPs), inference time, and total parameters. This allowed CAE-SCA to be implemented in edge devices as we tested using our custom ECG acquisition circuit. A significance test further confirms a statistically significant improvement in SNR values achieved by the CAE-SCA compared to baseline models, suggesting the CAE-SCA’s potential for advancing ECG processing in healthcare applications.https://ieeexplore.ieee.org/document/10925413/Autoencoderconvolutional neural networks (CNN)ECGsignal denoisingLSTM |
| spellingShingle | Alif Wicaksana Ramadhan Syifa Kushirayati Salsabila Aurellia Mgs M. Luthfi Ramadhan Muhammad Hannan Hunafa Muhammad Febrian Rachmadi Aprinaldi Jasa Mantau Siti Nurmaini Satria Mandala Wisnu Jatmiko Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation IEEE Access Autoencoder convolutional neural networks (CNN) ECG signal denoising LSTM |
| title | Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation |
| title_full | Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation |
| title_fullStr | Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation |
| title_full_unstemmed | Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation |
| title_short | Convolutional Autoencoder With Sequential and Channel Attention for Robust ECG Signal Denoising With Edge Device Implementation |
| title_sort | convolutional autoencoder with sequential and channel attention for robust ecg signal denoising with edge device implementation |
| topic | Autoencoder convolutional neural networks (CNN) ECG signal denoising LSTM |
| url | https://ieeexplore.ieee.org/document/10925413/ |
| work_keys_str_mv | AT alifwicaksanaramadhan convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT syifakushirayati convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT salsabilaaurellia convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT mgsmluthfiramadhan convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT muhammadhannanhunafa convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT muhammadfebrianrachmadi convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT aprinaldijasamantau convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT sitinurmaini convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT satriamandala convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation AT wisnujatmiko convolutionalautoencoderwithsequentialandchannelattentionforrobustecgsignaldenoisingwithedgedeviceimplementation |