Current Research:
Robot-hand-object interaction, using Reinforcement Learning
pipelines in
NVIDIA Isaac Sim for dexterous robot hand manipulation and policy training.
Real-Time Focused Sign Language Translation System
ML research under SMU Postdoc Dr. Inam Khan on anomaly detection; built meta-classifier for robotic e-waste grasping
Predict, visualize, and interpret air quality using NASA and open environmental data, making atmospheric science actionable for people. Personalized action steps based on health conditions and personal risk levels, with community clean air initiative outreach.
Estimate hand and object poses from data collected in a multi-camera system. Developed an end-to-end pipeline for simultaneously tracking hand and object poses from collected recordings as commonly used in AR/VR (XR), robotic and computer vision, security, etc.
I collaboratively integrated AI features into math games for the world’s largest educational game platform for blind children, reaching over 200,000 blind and visually impaired players worldwide, including 1 in 5 blind children in the U.S.
AI GIS uses various NASA Earth observation data for actionable insights for farmers, real-time visualization of soil moisture, drought, flooding, and climate risks tailored to each farm.
Personalized recommendations based on user preferences of climate factors such as temperature, precipitation, sea level, and extreme weather events. The Livability Index assists with informed decisions about where to live, work, or invest.
Using YOLOv3 and transfer learning, Perceptron, CNN, detecting 18,000 images of backgrounds, cars, or trucks in various weather and lighting conditions to improve safety in autonomous vehicles.
Aggregates real-time wildfire data to identify hotspots, assess risks to forests/nearby communities, and Wireless Emergency Alerts with live fire maps for guidance route.
IOS Social Media App with recognition board, veteran health resources, and community event planner for veterans to connect, share stories, and access support networks.
Educational app that begins with users taking pictures of everyday objects and generating origin stories with images. Users can then choose more specific, unique subjects related to the story generated, and the traverse through interactive stories as the process repeats.
The app streamlines homework tracking by extracting each student’s assignments from a shared spreadsheet and displaying them in a clean interface. It improves privacy and usability by eliminating the need to scroll through a class-wide list with added security.
Placeholder: multi-modal dataset and baseline models.
Various 2D and 3D games in Unity: Othello, Rollaball, Asteroids, Connect 4, Dodges, Mazes, Puzzles, tower of hanoi
Data Structure implementations