hardikroutray / ECG Public

Notifications You must be signed in to change notification settings
Fork 10
Star 15

Perform image and time series classification of various cardiovascular conditions as well as COVID-19 using Electrocardiogram data.

bestecgclassifier.herokuapp.com/

15 stars 10 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 84 Commits
CSV_data_v1		CSV_data_v1
CSV_data_v2		CSV_data_v2
CroppedECGImages/ECGImagesofCOVID-19Patients_cropped		CroppedECGImages/ECGImagesofCOVID-19Patients_cropped
CroppedECGImages_data_v2		CroppedECGImages_data_v2
app/images		app/images
data_v1		data_v1
data_v2		data_v2
modules		modules
playground		playground
.gitignore		.gitignore
CNN2D_ECG.ipynb		CNN2D_ECG.ipynb
Cropping_Atithi.ipynb		Cropping_Atithi.ipynb
Data-processing.ipynb		Data-processing.ipynb
ECG_1dCNN.ipynb		ECG_1dCNN.ipynb
ECG_project.ipynb		ECG_project.ipynb
ECG_to_csv.ipynb		ECG_to_csv.ipynb
Iftah_Classification Analysis.ipynb		Iftah_Classification Analysis.ipynb
Iftah_Classification Analysis_full_features.ipynb		Iftah_Classification Analysis_full_features.ipynb
Iftah_Classification Analysis_long_lead.ipynb		Iftah_Classification Analysis_long_lead.ipynb
Iftah_ECG_to_time_series.ipynb		Iftah_ECG_to_time_series.ipynb
Multi-Lead-DataFrame-Update-Copy1_0528.ipynb		Multi-Lead-DataFrame-Update-Copy1_0528.ipynb
Multi-Lead-DataFrame-Update.ipynb		Multi-Lead-DataFrame-Update.ipynb
Multi_lead_1dCNN.ipynb		Multi_lead_1dCNN.ipynb
Procfile		Procfile
README.md		README.md
movie.mp4		movie.mp4
muti-lead-dataFrame.csv		muti-lead-dataFrame.csv
requirements.txt		requirements.txt
setup.sh		setup.sh

Repository files navigation

Links to model notebooks

2D CNN 1D CNN

ECG

We classify various cardiovascular conditions from Electrocardiogram (ECG) images [1]. We also study the ECG of COVID-19 patients to identify potential cardiac injury due to SARS CoV 2. We perform both image and time series classification. Our 1D CNN model using time series achieves 95 % accuracy in classifying cardiac disorders including COVID-19.