a/README.md b/README.md
1 
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 1 
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
2 
[![Website shields.io](https://img.shields.io/website-up-down-green-red/http/shields.io.svg)](http://bestecgclassifier.herokuapp.com)
 2 
[![Website shields.io](https://img.shields.io/website-up-down-green-red/http/shields.io.svg)](http://bestecgclassifier.herokuapp.com)
3 

  3
  





  4
  

  4
  





  5
  
# Links to model notebooks

  5
  
# Links to model notebooks






  6
  
[2D CNN](https://github.com/hardikroutray/ECG/blob/main/scripts/CNN2D_ECG.ipynb)   

  6
  
[2D CNN](https://github.com/hardikroutray/ECG/blob/main/scripts/CNN2D_ECG.ipynb)   






  7
  
[1D CNN](https://github.com/hardikroutray/ECG/blob/main/scripts/Multi_lead_1dCNN.ipynb) 

  7
  
[1D CNN](https://github.com/hardikroutray/ECG/blob/main/scripts/Multi_lead_1dCNN.ipynb) 






  8
  
<!-- [Random Forest] (https://github.com/hardikroutray/ECG/blob/main/Multi-Lead-DataFrame-Update-Copy1_0528.ipynb)

  8
  
<!-- [Random Forest] (https://github.com/hardikroutray/ECG/blob/main/Multi-Lead-DataFrame-Update-Copy1_0528.ipynb)






  9
  
[Misc] (https://github.com/hardikroutray/ECG/blob/main/Iftah_Classification%20Analysis_full_features.ipynb)

  9
  
[Misc] (https://github.com/hardikroutray/ECG/blob/main/Iftah_Classification%20Analysis_full_features.ipynb)






  10
  
 -->

  10
  
 -->





  11
  

  11
  





  12
  

  12
  





  13
  

  13
  





  14
  
# ECG

  14
  
# ECG





  15
  

  15
  





  16
  
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.

  16
  
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.





  17
  

  17
  





  18
  

  18
  





  19
  
# Application

  19
  
# Application






  20
  
https://bestecgclassifier.herokuapp.com/

  20
  
https://bestecgclassifier.herokuapp.com/





  21
  

  21
  





  22
  

  22
  





  23
  
# Preprocessing

  23
  
# Preprocessing





  24
  

  24
  





  25
  
![alt text]( https://github.com/hardikroutray/ECG/blob/main/app/images/data_prep1.png )

  25
  
![alt text]( https://github.com/hardikroutray/ECG/blob/main/app/images/data_prep1.png?raw=true)





  26
  

  26
  





  27
  
# Best Performance (95 % Accuracy)

  27
  
# Best Performance (95 % Accuracy)





  28
  

  28
  





  29
  
Time series classification using 1D CNN <br>

  29
  
Time series classification using 1D CNN <br>






  30
  
![alt text](https://github.com/hardikroutray/ECG/blob/main/app/images/1d_CNN_vis.png)

  30
  
![alt text](https://github.com/hardikroutray/ECG/blob/main/app/images/1d_CNN_vis.png?raw=true)





  31
  

  31
  





  32
  

  32
  





  33
  

  33