Developed an AI model leveraging Generative Adversarial Networks to enhance 1.5T MRI scans to 3T scans and up, improving accessibility while reducing costs. Engineered a fast and efficient image processing pipeline with FastAPI, achieving up to 50 epochs in an hour for training models. Applied insights from Cycle-Free CycleGAN using invertible generators to refine unsupervised image enhancements. Leveraged advanced AI techniques to improve diagnostic accuracy and accessibility in healthcare.

Implemented multivariate Kalman Filter in C for state estimation in GTXR flight computer, integrating a complementary filter for acceleration and angular velocity resulting in decreased estimation errors. Created Java matrix operations library to enhance understanding of Kalman Filter mathematics, with data handling in both Euler angle and quaternion formats.

Diagnosed and repaired hardware issues, including PCB damage, to fully restore a malfunctioning Fujifilm XS-10 studio camera. Utilized Embedded C programming and real-time operating systems to develop custom firmware implementing computer vision solutions using OpenCV, resulting in a 20% enhancement in accuracy and restoration of studio-grade functionality.

Platform enhancing collaboration among healthcare and biomedical researchers, used by Emory University, Georgia Tech, and Morehouse. Features include user profiles, project management, mentorship activities, and real-time notifications. Developed with a team under Emory University's School of Medicine leadership.

Restaurant discovery platform for Atlanta featuring exploration, reviews, and filtering by distance, ratings, and cuisine. Includes user registration, favorite saving, and rating capabilities. Developed for CS2340 course at Georgia Tech.

Developed intelligent Pac-Man agents using reinforcement learning and A* algorithms for optimal pathfinding and ghost avoidance. Implemented various AI techniques to solve the classic game with different strategies.

Engineered a real-time auditory feedback system to support visually impaired individuals learning to code. Implemented sonification techniques to represent syntax errors, indentation, function execution, and loop iterations using distinct auditory cues. Integrated adaptive feedback based on user proficiency and provided optional tactile feedback via wearable devices. The system aims to reduce cognitive load and improve accessibility in programming education.

Developed a full-stack portfolio website to showcase projects in AI, robotics, web development, and embedded systems. Features include an About Me section, tech stack overview, contact information, and detailed project listings. Designed with accessibility, responsiveness, and performance in mind to highlight work as a Georgia Tech CS student.