My Projects

University Dissertation Project - Recommendation Systems

A web application that helps students take notes and receive personalized study material recommendations using NLP. Backend built using Flask, MySQL, and Google NLP API.

Object Detection with YOLOv9

Detects objects within a defined ROI, allowing detection in specific areas of the scene. The system uses OpenCV and Ultralytics YOLOv9 for object detection.

Unity Race Game

A fast-paced racing game developed in Unity using C# as part of a university group project. Inspired by Mario Kart, the game features power-ups, AI opponents, lap tracking, and arcade-style gameplay.

Sentiment Analysis

This project is a Sentiment Analysis system built using Natural Language Processing (NLP). It analyses user-provided text and identifies the emotional tone and sentiment behind it.

Gita App With Chatbot

An AI-powered mobile application built with React Native and RAG (Retrieval-Augmented Generation).

Study Chatbot

A study RAG and intnet chatbot, flexible conversational AI for education and research. Combining NLP, RAG, LLM, and web search to provide accurate and context-aware responses.

Mood To Action Recommender

This project implements a hybrid, AI-driven, content-based recommendation system that uses natural language processing to infer a user’s emotional state and intent from free-text input.

Secure Notes REST API with Authentication

A secure REST API built Authentication that allows users to create, read, update, and delete personal notes using JWT-based authentication through Firebase and Firebase Realtime Database.

Brain Tumor MRI Detection

A deep learning project for multi-class brain tumor classification from MRI images using Transfer Learning (EfficientNetB0) and explainable AI with Grad-CAM.

Pneumonia Detection

A deep learning-based medical imaging system that detects pneumonia from chest X-ray images using EfficientNet and visualizes model decisions using Grad-CAM.

Bishal Roy