{"id":21410276,"url":"https://github.com/busyyang/ecgnet","last_synced_at":"2025-08-08T04:11:18.328Z","repository":{"id":201344443,"uuid":"224153037","full_name":"busyyang/ECGNet","owner":"busyyang","description":"ECGNet复现论文P-QRS-T localization in ECG using deep learning","archived":false,"fork":false,"pushed_at":"2019-12-06T10:06:18.000Z","size":110,"stargazers_count":16,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-14T03:01:22.240Z","etag":null,"topics":["cnn-1d","deeplearning","ecg","fcn","keras"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/busyyang.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-11-26T09:31:18.000Z","updated_at":"2025-05-24T07:23:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"1e0a21b5-51e4-4d1e-a33b-424dde0f9cb7","html_url":"https://github.com/busyyang/ECGNet","commit_stats":null,"previous_names":["busyyang/ecgnet"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/busyyang/ECGNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/busyyang%2FECGNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/busyyang%2FECGNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/busyyang%2FECGNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/busyyang%2FECGNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/busyyang","download_url":"https://codeload.github.com/busyyang/ECGNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/busyyang%2FECGNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269361516,"owners_count":24404387,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-08T02:00:09.200Z","response_time":72,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn-1d","deeplearning","ecg","fcn","keras"],"created_at":"2024-11-22T17:39:01.445Z","updated_at":"2025-08-08T04:11:18.302Z","avatar_url":"https://github.com/busyyang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"ECG R-wave and P-wave localization in paper:\n~~~\n@InProceedings{Abrishami2018,\n  author    = {H. {Abrishami} and M. {Campbell} and C. {Han} and R. {Czosek} and X. {Zhou}},\n  title     = {P-{QRS}-T localization in {ECG} using deep learning},\n  booktitle = {Proc. IEEE EMBS Int. Conf. Biomedical Health Informatics (BHI)},\n  year      = {2018},\n  pages     = {210--213},\n  month     = mar,\n  doi       = {10.1109/BHI.2018.8333406}\n}\n~~~\nSince the code of this paper is not open, I implemented the code according this paper with `keras` framework.\n# Data preprocess\nData preprocessed in MATLAB. Download data files from `https://www.physionet.org/content/qtdb/1.0.0/` with `download_QTDB.m`. PC will get `xxxann.mat` for Y and `xxxdata.mat` for X.\\\nFor input data to keras conveniently, `Segmentor.m` will segment all recording into complexes and position of P-wave and R-wave is also saved in `segmentors.mat`.\\\nif you load `segmentor.mat` into matlab. You will get `segs` with 96863 by 300 and `anns` with dimention of 96863 by 2 in workspace. That mean there are 96863 complexes with length of 300 sampling points.\\\n`ann[:,1]` presents position of P-wave. `ann[:,2]` presents position of R-wave. More detail can be found in paper. \n\n# models\nfor fully-connected net usage:\n~~~python\n    python ./paper_models_codes/denseNet_P_R_localization.py\n~~~\nfor 1D CNN usage:\n~~~python\n    python ./paper_models_codes/ECGNet.py\n~~~\nfor 1D CNN with dropout usage:\n~~~python\n    python ./paper_models_codes/ECGNet_Dropout.py\n~~~\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbusyyang%2Fecgnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbusyyang%2Fecgnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbusyyang%2Fecgnet/lists"}