We got our inspiration from visiting India, which is heavily populated with mosquitoes. We wanted to make a tool that would confirm that we did not get any diseases or permanent damage from the mosquitoes.
A user can upload an image of a cell on our website, which is sent to our Machine Learning algorithm and evaluated to determine if the cell is infected with malaria or not and the percent accuracy of the detection.
We built the algorithm using Machine Learning and Python. We trained it using a dataset from an online dataset website, Kaggle. We built the website for users with html and css.
The Machine Learning algorithm failed a couple of times, and we had to keep improving on our model and retraining it.
We are proud to have finally finished a working model of the Malaria Detector, along with a website that handles user interface and makes sure that a user can work through our model and get their result with ease.
We learned a lot about web apps and python, specifically for Machine Learning.
In the future, we would like to create a web app to help user experience and combine the model and website to make the results generate even faster.
Log in or sign up for Devpost to join the conversation.