{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-network-for-capacitive-ecg-denoising","title":"Deep Network for Capacitive ECG Denoising","arxiv_id":"1903.12536","date":"2019-03-29","proceeding":null,"authors":["Vignesh Ravichandran","Balamurali Murugesan","Sharath M. Shankaranarayana","Keerthi Ram","Preejith S. P","Jayaraj Joseph","Mohanasankar Sivaprakasam"],"abstract":"Continuous monitoring of cardiac health under free living condition is\ncrucial to provide effective care for patients undergoing post operative\nrecovery and individuals with high cardiac risk like the elderly. Capacitive\nElectrocardiogram (cECG) is one such technology which allows comfortable and\nlong term monitoring through its ability to measure biopotential in conditions\nwithout having skin contact. cECG monitoring can be done using many household\nobjects like chairs, beds and even car seats allowing for seamless monitoring\nof individuals. This method is unfortunately highly susceptible to motion\nartifacts which greatly limits its usage in clinical practice. The current use\nof cECG systems has been limited to performing rhythmic analysis. In this paper\nwe propose a novel end-to-end deep learning architecture to perform the task of\ndenoising capacitive ECG. The proposed network is trained using motion\ncorrupted three channel cECG and a reference LEAD I ECG collected on\nindividuals while driving a car. Further, we also propose a novel joint loss\nfunction to apply loss on both signal and frequency domain. We conduct\nextensive rhythmic analysis on the model predictions and the ground truth. We\nfurther evaluate the signal denoising using Mean Square Error(MSE) and Cross\nCorrelation between model predictions and ground truth. We report MSE of 0.167\nand Cross Correlation of 0.476. The reported results highlight the feasibility\nof performing morphological analysis using the filtered cECG. The proposed\napproach can allow for continuous and comprehensive monitoring of the\nindividuals in free living conditions.","url_abs":"http://arxiv.org/abs/1903.12536v1","url_pdf":"http://arxiv.org/pdf/1903.12536v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"ecg-denoising","task_name":"ECG Denoising"},{"task_slug":"electrocardiography-ecg","task_name":"Electrocardiography (ECG)"},{"task_slug":"morphological-analysis","task_name":"Morphological Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ecg-denoising-on-unovis_auto2012","task":"ECG Denoising","dataset":"UnoViS_auto2012","model":"L1 + RFFT","rank_in_archive_order":1,"of":1,"metrics":{"MSE":"0.167"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}