The problem Clean-Fit solves

Two of the major problems of our Indian society are cleanliness (rather the lack thereof) and the deteriorating health of our citizens. It’s time we accept that in the coming time, cleanliness and health are going to be the parameters for measuring the success of a “Smart City”. Thus we have developed a way so that the citizens of our country can not only exercise but do it in a fun way, and that too while cleaning up the city. The citizens will be provided with a dedicated path for them to cover during their jogging time, and this path will lead through some carefully deliberated parts of the town, where they can pick up trash while jogging. The incentive of cleaning their city alongside maintaining their health is complementary to the effort of building a strong and clean “Smart City”.In a way, it relieves the burden on the sanitation workers of the city, creates awareness about health, hygiene and cleanliness, and at last, helps people contribute to the well being of their city in a tangible way.

Challenges we ran into

In the machine learning part, running the model was a daunting task, as data from two different datasets were joined together to be run on a deep learning model. Improving accuracy also was an obstacle, which was overcome by running a pipeline function to check its accuracy with other regression standards. Searching for sites to scrap Delhi cities’ data also became a problem in the middle stages of the project. Finally, a site was found which had the names of all Delhi cities along with coordinates of each and every city.
Integration of Backend with ML was a bit challenging at first but after several cups of coffee and tons of bugs later, we were able to finally integrate it.
We tried various map libraries and APIs but they were all too heavy for our project. So we are using 2 different map APIs, pigeon-maps for front-end purposes and map-box to generate the route.
We also faced some issues while redirecting our GoDaddy subdomain to point to our Heroku domain and we were still working on it, though we originally wanted to deploy our project to Google Cloud we were not able to deploy it.