Hello, π my name is
Gurmukh Kharod
From PROBLEM to PRODUCT.
This Java app, supports the following:
Perform CRUD operations on packages, and save packages in JSON format, using GSON.
Apply OOP Design Patterns to support multiple package types.
Implement the user interactivity in an IntelliJ Swing App GUI.
Use Spring Boot + API Endpoints to store packages onto a web server.
This Full-Stack Multiplatform Embedded Systems App, supports the following:
Implements a gesture-based multiplayer gaming platform using BeagleY-AI embedded boards.
Uses MediaPipe with OpenCV for hand tracking done in real-time, and cross compiled with Bazel,
Players use real-world gestures to battle each other on a React Web Client, with state synchronization maintained through a Node.js Http WebSocket server.
Developed a real-time solar flare prediction dashboard that combines PyTorch and Scikit-learn models for forecasting.
Integrated NOAA SWPC and NASA SDO APIs to fetch live solar imagery and 7-day X-ray flux data.
Built a responsive React + Python full-stack system with data visualizations, video rendering, and automated peak analysis.
Built a proximity-based communications mobile app where the buildings are GeoJSON chat rooms - walk into Library, you auto-join the Library chat.
Real-time WebSocket broadcasts (help, study, coffee, lost & found) with offline queue & replay so posts sync when back online.
Clean mobile UX with live zone processing, satellite toggle, several intuitive pages and chat functionalities.
Built during Storm Hacks 2025, a 24-hour hackathon with a team of 4 using agile, iterative development.
The following React-based game fetches real planetary data from NASA APIs for an interactive space experience.
Players can explore a vast universe, moving around using arrow keys or W/A/S/D.
Clicking on planets will collect them and increase the score, making exploration rewarding.
All celestial objects in the game are real exoplanets and asteroids from NASA data.
Check out the application running via Netlify.
This Python Machine Learning and Statistics App utilizes NumPy, Scikit-learn and Pandas for efficient data manipulation and analysis.
It processes data from multiple CSV files to identify trends in various financial statistics over several years.
Employs statistical fundamentals and machine learning techniques, including linear regression and polynomial regression, to predict future financial trends.