{"id":22521572,"url":"https://github.com/r13i/ecg-classify","last_synced_at":"2025-08-03T20:31:15.071Z","repository":{"id":187680692,"uuid":"148888609","full_name":"r13i/ecg-classify","owner":"r13i","description":"Classifying Heartbeat Arrhythmia using novel features (Auto-regressive coefficients \u0026 RR inter-beat distance)","archived":false,"fork":false,"pushed_at":"2020-05-01T16:29:37.000Z","size":1601,"stargazers_count":30,"open_issues_count":1,"forks_count":7,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-04-24T12:15:15.943Z","etag":null,"topics":["auto-regressive-coefficients","beats","ecg","heartbeat","heartbeats-classification","machine-learning","python","qrs","rr-interval-features","signal-processing","veb-beats","waves-autoregressive-features"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/r13i.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":"2018-09-15T09:35:44.000Z","updated_at":"2023-11-18T07:20:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"fb17d1d9-74a7-4f45-b56c-9012789c7196","html_url":"https://github.com/r13i/ecg-classify","commit_stats":null,"previous_names":["r13i/ecg-classify","redouane-dev/ecg-classify"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r13i%2Fecg-classify","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r13i%2Fecg-classify/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r13i%2Fecg-classify/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r13i%2Fecg-classify/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/r13i","download_url":"https://codeload.github.com/r13i/ecg-classify/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228562317,"owners_count":17937234,"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","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":["auto-regressive-coefficients","beats","ecg","heartbeat","heartbeats-classification","machine-learning","python","qrs","rr-interval-features","signal-processing","veb-beats","waves-autoregressive-features"],"created_at":"2024-12-07T05:12:04.988Z","updated_at":"2024-12-07T05:12:05.483Z","avatar_url":"https://github.com/r13i.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ecg-classify\nClassifying Heartbeat Arrhythmia using novel features (AR coefficients + RR distance).\n\nFull explanation available in [this notebook](./ecg_prototyping.ipynb) (You can explore it on your browser!).\n\n### Introduction\nIn this project, I implement a heartbeat arrhythmia classification algorithm to separate normal heartbeats (N) from Ventricular Ectopic Beats (VEB). This work is based on the paper _\"Heartbeats classification using QRS and T waves autoregressive features and RR interval features\", Adnane M, Belouchrani A._ (see references).\n\nThe features used to train the model are:\n- Auto-regressive coefficients of the QRS complex and T wave of the electrocardiogram.\n- RR interbeat distance.\n\n\nNormal Beats: ![Normal Beats](./img/img_N.png)\nVEB Beats: ![VEB Beats](./img/img_VEB.png)\n\n\n### Procedure\n#### Pre-processing\n- A 3rd order high-pass Butterworth filter is used to eliminate DC componant and baseline wander.\n- A 3rd order band-reject Butterworth filter is used to eliminate the 60 Hz AC interference.\n- A 4th order low-pass Butterworth filter is used to high-freq artifacts like EMG noise.\n\n#### Features Extraction\n- We use the Levinson algorithm to extract AR coefficients from ECG signal.\n- A basic substraction gives the RR interdistance.\n\n#### Training Day\nSVM classifiers give good results for now. I'll stick to them while trying to improve hyper-parameters before going to anything else (e.g. Neural Nets).\n\n\n### Result\nFor the time being (2017), results are reaching those obtained by state-of-the-art methods with accuracy metric 97.02% (overall), and 98.86% for subject specific scheme (See references).\n\n\n### Dataset\n- [MIT/BIH Arrhythmia Database](https://www.physionet.org/physiobank/database/mitdb/)\n\n\n### References\n- [Adnane M, Belouchrani A. Heartbeats classification using QRS and T waves autoregressive features and RR interval features. Expert Systems. 2017;34:e12219.](https://doi.org/10.1111/exsy.12219)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr13i%2Fecg-classify","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr13i%2Fecg-classify","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr13i%2Fecg-classify/lists"}