Shloka Shah

Software Development Engineer at HackerRank
Computer Science Undergraduate | B.Tech at Sardar Patel Institute Of Technology | 2021
Winter Intern'21 at HackerRank | GHCI'20 Scholar | SIH'20 Finalist
Mumbai, India
Deep Learning | ML Enthusiast | Web Development | Data Science | AWS

Segro

Considering the current scenario in our country, we see that waste disposal, segregation and collection, collectively is one of the biggest challenges faced by the authorities. This application provides for an end to end solution for waste classification, collection and disposal.

 

Features

   1. Waste Classification into six categories i.e paper,cardboard,metal,plastic,glass,trash.

   2. CNN ResNet Architecture and YOLOv3 for Waste Classification.

 
Snow
Forest

   3. Truck Route Optimization using the Travelling Salesman Problem.The algorithm is a dynamic approach to find the shortest and the most optimal route between the source and the destination.

    The figure below shows route being generated using TSP for the bins which have crossed the threshold level ( It is the level of waste inside the compartment of a bin, above which the bin will send a threshold-cross notification to the server that compartment is ready to be collected ).

 

Technology Stack

   1. Django Rest Framework (API for backend)

   2. Flutter (Mobile Application)

   3. Image Classification with CNN and YOLOv3

Application Demo

   1. The flow of the image shows the simulation where the bins are getting filled in a locality. All the bins having color of yellow or red will be collected.