{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T15:18:13Z","timestamp":1778426293293,"version":"3.51.4"},"reference-count":27,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Council, Taiwan","award":["NSTC 114-2628-E-150-001-MY2"],"award-info":[{"award-number":["NSTC 114-2628-E-150-001-MY2"]}]},{"name":"Smart Machinery and Intelligent Manufacturing Research Center, National Formosa University, Yunlin, Taiwan"},{"name":"Intelligent Recognition Industry Service Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electrocardiograms (ECGs) are critical for cardiovascular disease diagnosis, but their accuracy is often compromised by electrode motion (EM) artifacts\u2014large, nonstationary distortions caused by patient movement and electrode-skin interface shifts. These artifacts overlap in frequency with genuine cardiac signals, rendering traditional filtering methods ineffective and increasing the risk of false alarms and misdiagnosis, particularly in wearable and ambulatory ECG applications. To address this, we propose the Feature-Shuffle Multi-Head Attention Autoencoder (FMHA-AE), a novel architecture integrating multi-head self-attention (MHSA) and a feature-shuffle mechanism to enhance ECG denoising. MHSA captures long-range temporal and spatial dependencies, while feature shuffling improves representation robustness and generalization. Experimental results show that FMHA-AE achieves an average signal-to-noise ratio (SNR) improvement of 25.34 dB and a percentage root mean square difference (PRD) of 10.29%, outperforming conventional wavelet-based and deep learning baselines. These results confirm the model\u2019s ability to retain critical ECG morphology while effectively removing noise. FMHA-AE demonstrates strong potential for real-time ECG monitoring in mobile and clinical environments. This work contributes an efficient deep learning approach for noise-robust ECG analysis, supporting accurate cardiovascular assessment under motion-prone conditions.<\/jats:p>","DOI":"10.3390\/s25206322","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T08:34:26Z","timestamp":1760517266000},"page":"6322","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Feature-Shuffle and Multi-Head Attention-Based Autoencoder for Eliminating Electrode Motion Noise in ECG Applications"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0003-8397","authenticated-orcid":false,"given":"Szu-Ting","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung City, Wufeng 413310, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Yen","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin County, Douliu 64002, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0011-3649","authenticated-orcid":false,"given":"Shin-Chi","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Automation Engineering and the Smart Machinery and Intelligent Manufacturing Research Center, National Formosa University, Yunlin County, Huwei 632301, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8417-474X","authenticated-orcid":false,"given":"Ming-Hwa","family":"Sheu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin County, Douliu 64002, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9476-8130","authenticated-orcid":false,"given":"Chuan-Yu","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Yunlin University of Science and Technology, Yunlin County, Douliu 64002, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9828-0773","authenticated-orcid":false,"given":"Shih-Chang","family":"Hsia","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin County, Douliu 64002, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-1764","authenticated-orcid":false,"given":"Szu-Hong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin County, Douliu 64002, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"29","DOI":"10.46439\/biomedres.5.041","article-title":"Recent Developments in the Diagnosis, Treatment, and Management of Cardiovascular Diseases Through Artificial Intelligence and Other Innovative Approaches","volume":"5","author":"Addissouky","year":"2024","journal-title":"J. Biomed. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1109\/TBME.1984.325244","article-title":"Reducing Motion Artifacts and Interference in Biopotential Recording","volume":"BME-31","author":"Webster","year":"1984","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/TBME.1973.324169","article-title":"60-Hz Interference in Electrocardiography","volume":"BME-20","author":"Huhta","year":"1973","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1109\/JSEN.2011.2111453","article-title":"Efficient and Simplified Adaptive Noise Cancelers for ECG Sensor Based Remote Health Monitoring","volume":"12","author":"Rahman","year":"2012","journal-title":"IEEE Sens. J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sharma, I., Mehra, R., and Singh, M. (2015, January 2\u20134). Adaptive filter design for ECG noise reduction using LMS algorithm. Proceedings of the 2015 4th International Conference on Reliability, Infocom Technologies and Optimization: Trends and Future Directions (ICRITO 2015), Noida, India.","DOI":"10.1109\/ICRITO.2015.7359333"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shaddeli, R., Yazdanjue, N., Ebadollahi, S., Saberi, M.M., and Gill, B. (2021, January 12\u201317). Noise Removal from ECG Signals by Adaptive Filter Based on Variable Step Size LMS Using Evolutionary Algorithms. Proceedings of the Canadian Conference on Electrical and Computer Engineering, Toronto, ON, Canada.","DOI":"10.1109\/CCECE53047.2021.9569149"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, M., and Wei, G. (2020). An Integrated EMD Adaptive Threshold Denoising Method for Reduction of Noise in ECG. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0235330"},{"key":"ref_8","first-page":"253","article-title":"ECG De-Noising Using Thresholding Based on Wavelet Transforms","volume":"3","author":"Supraja","year":"2013","journal-title":"Int. J. Eng. Res. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1049\/iet-spr.2014.0005","article-title":"Electrocardiogram Signal Denoising Using Non-Local Wavelet Transform Domain Filtering","volume":"9","author":"Yadav","year":"2015","journal-title":"IET Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. (2008, January 5\u20138). Extracting and Composing Robust Features with Denoising Autoencoders. Proceedings of the 25th International Conference on Machine Learning, Montreal, QC, Canada.","DOI":"10.1145\/1390156.1390294"},{"key":"ref_11","first-page":"1804","article-title":"Denoising Autoencoder for Eletrocardiogram Signal Enhancement","volume":"5","author":"Xiong","year":"2015","journal-title":"J. Med. Imaging Health Inf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"60806","DOI":"10.1109\/ACCESS.2019.2912036","article-title":"Noise Reduction in ECG Signals Using Fully Convolutional Denoising Autoencoders","volume":"7","author":"Chiang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dasan, E., and Panneerselvam, I. (2021). A Novel Dimensionality Reduction Approach for ECG Signal via Convolutional Denoising Autoencoder with LSTM. Biomed. Signal Process Control, 63.","DOI":"10.1016\/j.bspc.2020.102225"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"57555","DOI":"10.1109\/ACCESS.2022.3178847","article-title":"Integration Design of Portable ECG Signal Acquisition With Deep-Learning Based Electrode Motion Artifact Removal on an Embedded System","volume":"10","author":"Jhang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jhang, Y.S., Wang, S.T., Sheu, M.H., Wang, S.H., and Lai, S.C. (2022). Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG. Appl. Sci., 12.","DOI":"10.3390\/app12146957"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Seo, H.C., Yoon, G.W., Joo, S., and Nam, G.B. (2022). Multiple Electrocardiogram Generator with Single-Lead Electrocardiogram. Comput. Methods Programs Biomed., 221.","DOI":"10.1016\/j.cmpb.2022.106858"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2929","DOI":"10.1109\/JBHI.2022.3169325","article-title":"An ECG Signal Denoising Method Using Conditional Generative Adversarial Net","volume":"26","author":"Wang","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"ref_19","first-page":"5998","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/JBHI.2024.3355960","article-title":"Elimination of Random Mixed Noise in ECG Using Convolutional Denoising Autoencoder with Transformer Encoder","volume":"28","author":"Chen","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"ref_21","unstructured":"Moody, G., and Mark, R. (2025, September 27). MIT-BIH Arrhythmia Database. Available online: https:\/\/www.physionet.org\/content\/mitdb\/1.0.0\/."},{"key":"ref_22","unstructured":"Moody, G., and Mark, R. (2025, September 27). MIT-BIH Noise Stress Test Database. Available online: https:\/\/www.physionet.org\/content\/nstdb\/1.0.0\/."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"111068","DOI":"10.1016\/j.patcog.2024.111068","article-title":"Pixel Shuffling Is All You Need: Spatially Aware Convmixer for Dense Prediction Tasks","volume":"158","author":"Ibrahem","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, P. (2019, January 16\u201317). Image Denoising Using Deep CGAN with Bi-Skip Connections. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00099"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Park, B., Yu, S., and Jeong, J. (2019, January 16\u201317). Densely Connected Hierarchical Network for Image Denoising. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00263"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Dong, L.F., Gan, Y.Z., Mao, X.L., Yang, Y.B., and Shen, C. (2018, January 15\u201320). Learning Deep Representations Using Convolutional Auto-Encoders with Symmetric Skip Connections. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","DOI":"10.1109\/ICASSP.2018.8462085"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/20\/6322\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T07:37:44Z","timestamp":1760686664000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/20\/6322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":27,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["s25206322"],"URL":"https:\/\/doi.org\/10.3390\/s25206322","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]}}}