MediPriority is an AI-driven healthcare management system designed to streamline the patient care journey from pre-consultation to post-consultation. Leveraging advanced AI technologies, MediPriority aims to improve patient outcomes, enhance efficiency, and reduce the administrative burden on healthcare providers. Key features include multi-agent AI systems for various tasks, dynamic urgency scoring, visual analysis, personalized AI avatars, and seamless integration with everyday tools like Google Calendar.
GitHubAI Avatar Maker is a Flutter-based application that allows users to create realistic human avatars using AI technology. By collecting user input and feeding it into a powerful AI model, the app generates human-like images based on the given prompt. The cloud architecture behind this app enables users to generate these images with a simple click, ensuring a smooth and efficient experience with features like realistic avatar generation, cloud driven and user friendly interface.
Smart AI Based Food RAG is an intelligent food search system that
utilizes cutting-edge technologies to provide users with efficient and
intuitive text and image search capabilities. The system combines the
power of Retrieval Augmented Generation (RAG) techniques, computer
vision, and natural language processing to enable users to discover
and explore food items seamlessly.
DigiManuf is an AI-powered Digital Twin Ecosystem designed to
revolutionize the manufacturing industry by enabling real-time
monitoring, predictive maintenance, anomaly detection, and intelligent
order management. By leveraging advanced technologies such as
Artificial Intelligence, IoT, Cloud Computing, Big Data Analytics, and
Graph Databases, DigiManuf provides an efficient and scalable solution
for optimizing distributed manufacturing environments.
In the 2024 Amazon ML Hackathon, our team achieved an impressive rank of 64th out of over 75,000 participants from across India. Our project focused on Feature Extraction from Images, utilizing advanced machine learning techniques to extract critical product information directly from images. This capability is essential in fields such as healthcare and e-commerce. Our solution leverages the MiniCPM-Llama3-V-2.5 model, a cutting-edge vision-language model that integrates visual processing capabilities with natural language understanding.
GitHubDosepacker Inc. runs a large automated warehouse, where robots (called autobots) move products from one place to another. However, the system recently started facing issues like traffic jams and collisions, slowing down operations. Our goal was to create a smart system to control these autobots, helping them move safely and efficiently within the warehouse without bumping into each other or obstacles. Our mission was to guide Autobots across a matrix grid from their starting point (A) to their destination (B), avoiding obstacles and each other.
GitHubUnlocking the Secrets Behind Your Favorite Songs with AI! TuneInsight is an AI-powered web app that identifies the song you're playing and provides detailed information. Using either an open-source AI model or Assembly AI, TuneInsight delivers a seamless song recognition experience, all through a simple, responsive web interface.
A smart, CrewAI-powered chatbot that helps you manage your Google Calendar using natural language text commands. This assistant is built around a single agent that performs multiple scheduling tasks using various tools using the crewai for the agentic framework and also gemini api.
This project contains three state-of-the-art models fine-tuned on the PubLayNet dataset for precise figure localization in technical PDFs, including scientific documents and financial reports. The models solve challenges where traditional techniques and zero-shot vision APIs fail due to fragmented outputs or misaligned coordinates.
GitHubThis repository contains an Apache Airflow pipeline for Credit Card Fraud Detection. The pipeline automates the end-to-end machine learning workflow, from data ingestion to model training, evaluation, and deployment to the cloud.
This algorithm design demonstrates a sophisticated approach to solving the complex problem of delivery route optimization. It balances multiple competing constraints while maintaining efficiency and practical applicability.
A smart CrewAI-powered voice assistant that helps you manage your Google Calendar using natural voice conversations. It uses AssemblyAI for speech recognition and Eleven Labs for speech synthesis, enabling seamless voice-to-voice scheduling.