{"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-recurrent-neural-networks-for-ecg-signal","title":"Deep Recurrent Neural Networks for ECG Signal Denoising","arxiv_id":"1807.11551","date":"2018-07-30","proceeding":null,"authors":["Karol Antczak"],"abstract":"Electrocardiographic signal is a subject to multiple noises, caused by\nvarious factors. It is therefore a standard practice to denoise such signal\nbefore further analysis. With advances of new branch of machine learning,\ncalled deep learning, new methods are available that promises state-of-the-art\nperformance for this task. We present a novel approach to denoise\nelectrocardiographic signals with deep recurrent denoising neural networks. We\nutilize a transfer learning technique by pretraining the network using\nsynthetic data, generated by a dynamic ECG model, and fine-tuning it with a\nreal data. We also investigate the impact of the synthetic training data on the\nnetwork performance on real signals. The proposed method was tested on a real\ndataset with varying amount of noise. The results indicate that four-layer deep\nrecurrent neural network can outperform reference methods for heavily noised\nsignal. Moreover, networks pretrained with synthetic data seem to have better\nresults than network trained with real data only. We show that it is possible\nto create state-of-the art denoising neural network that, pretrained on\nartificial data, can perform exceptionally well on real ECG signals after\nproper fine-tuning.","url_abs":"http://arxiv.org/abs/1807.11551v3","url_pdf":"http://arxiv.org/pdf/1807.11551v3.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":[{"paper_slug":"deep-recurrent-neural-networks-for-ecg-signal","repo_url":"https://github.com/fperdigon/DeepFilter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"ecg-denoising","task_name":"ECG Denoising"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ecg-denoising-on-qt-nstdb","task":"ECG Denoising","dataset":"QT-NSTDB","model":"DRNN","rank_in_archive_order":4,"of":4,"metrics":{"CosSim":"0.746 ±0.192","MAD":"0.648 ±0.390","PRD(%)":"118.969 ±101.215","SSD":"11.492 ±15.536"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.11551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11551"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fperdigon/DeepFilter","reach":null}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bdd3137e6fa9c6f3","entry":"FIRRemoveHF","repo":"fperdigon/DeepFilter","repo_kind":"listed","path":"digitalFilters/dfilters.py","file_url":"https://github.com/fperdigon/DeepFilter/blob/HEAD/digitalFilters/dfilters.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd3137e6fa9c6f3"}},{"code_sha256_prefix":"45cf94c941e604f3","entry":"IIRRemoveBL","repo":"fperdigon/DeepFilter","repo_kind":"listed","path":"digitalFilters/dfilters.py","file_url":"https://github.com/fperdigon/DeepFilter/blob/HEAD/digitalFilters/dfilters.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45cf94c941e604f3"}},{"code_sha256_prefix":"ae4eaa7086168a85","entry":"FIRRemoveBL","repo":"fperdigon/DeepFilter","repo_kind":"listed","path":"digitalFilters/dfilters.py","file_url":"https://github.com/fperdigon/DeepFilter/blob/HEAD/digitalFilters/dfilters.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae4eaa7086168a85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}