Skip to content

Theophylline/ecg_classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SVM Classification of Arrythmias from Single Lead ECG Recordings

In this project, a Support Vector Machine (SVM) is used to classify normal and abnormal rhythms from ECG Recordings.

ECG recordings are obtained from https://www.physionet.org/challenge/2017/. The training set contains 5154 normal ECGs and 3328 abnormal ECGs, which can further be broken down into 771 atrial fibrillations (AF) and 2557 other abnormal rhythms (O). Noisy recordings are excluded in this project.

A model for ECG segmentation has already been trained (/misc/hmm_model.dll). You can use it to extract your own features.

For more details, please see the Jupyter Notebook.

PS: in case the notebook doesn't render on GitHub, please use this link: https://nbviewer.jupyter.org/github/Theophylline/ecg_classifier/blob/master/ecg_svm.ipynb

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published