Research & Projects

In 2024, my two teammates and I developed an interview practice platform for the HackIllinois hackathon. The platform utilizes natural language processing and an open-source machine learning model to offer real-time feedback on users' interview responses. We integrated Google Gemini's API for content analysis. I handled the backend development using Python and Flask and incorporated HuggingFace to deploy the machine learning model, making the solution robust and scalable.

"Zombie Shooter" is a mixed-reality game where users shoot at approaching zombies for an interactive and immersive experience. With a focus on game development, I used Meta Quest 3 for the project. The final project included multiple zombie types, user-controlled projectiles, and dynamic gameplay based on the user's score.

Gaze interaction presents a promising avenue in Virtual Reality (VR) due to its intuitive and efficient user experience. Yet, the depth control inherent in our visual system remains underutilized in current methods. In this study, we introduce FocusFlow, a hands-free interaction method that capitalizes on human visual depth perception within the 3D scenes of Virtual Reality. We first develop a binocular visual depth detection algorithm to understand eye input characteristics. We then propose a layer-based user interface and introduce the concept of a “Virtual Window” that offers an intuitive and robust gaze-depth VR interaction despite the constraints of visual depth accuracy and precision spatially at further distances.

You can find a link to the paper here.

Virtual Reality (VR) allows complete immersion in virtual environments. People have used VR in many applications, including training healthcare professionals in a timely and cost-effective manner. Effectively incorporating clinical feedback into simulation design to ensure the usability of the software is a challenge. This paper discusses a pipeline developed for efficient participatory design for creating a VR-based electrocardiogram training simulator. 

You can find a link to the paper here.

With the vast number of courses offered at UIUC and the wide variation in average GPA, instructor quality, prereqs, and number of GenEds fulfilled, picking the best course to take is hard.

Cherry aims to solve this to make course picking super easy. Just open Cherry and see a list of all the courses at UIUC sorted by highest to lowest GPA. You can search by departments and even filter courses based on Gen-Eds you'd like to fulfill, with many more planned features coming soon!