What it does

Identifies whether a cell if infected by malaria

How I built it

  • Using convolutional neural network, we trained over 5000 images and constructed a model with 96.5% of accuracy.
  • The model is then connected to a web application, such that user can use it online.
  • The web application is built with Softheon API and Google Cloud Platform.

Challenges I ran into

  • Building a model, and improve its accuracy
  • Connect python with front end

Accomplishments that I'm proud of

  • Great accuracy improvement: our original model only has 50% of accuracy.
  • Building a website with nice APIs

What's next for Hack Your Cell

  • Higher accuracy
Share this project:

Updates