Hi! I'm Xiang Chen, a third-year student at the University of Pennsylvania studying Computer Science and Robotics. I am passionate about software engineering, particularly web development, AI/ML, and data science. I have multiple projects showcasing these skills, and I'm always interested to learn new technologies!
Developed a skill exchange platform that allows users to search and filter other users on the website to learn and teach skills amongst each other. Developed as part of my Software Engineering class, this project creates a platform that fosters community and allows individuals to learn and grow with each other.
Led a team of 5 to build a real-time monitoring application using Electron, utilizing serial communication between Javascript and Arduino for streamlined sensor data collection through a collection of dashboards. Final iteration allowed for millisecond reporting across various sensors simultaneously (load cell, temperature, etc).
GPA: 3.9
GPA: 3.50
Developed a machine learning model trained on 100k+ patient dataset to accurately assess patient risk of diabetes based on multiple factors. Initial models were made based on logistic regresison and decision trees to set baseline numbers and evaluate the importance of different features. The model was trained using Pytorch and evaluated using various metrics such as accuracy, precision, recall, and F1 score. The final neural network model achieved an accuracy of 95% on the test set, demonstrating its effectiveness in predicting diabetes risk. This project showcases my ability to apply machine learning techniques to real-world healthcare data and provides valuable insights for early intervention and prevention strategies.
Developed a full-stack budgeting platform to enable real-time tracking and management of personal expenses. The backend was built using Bun and Hono, achieving a 50% reduction in response time compared to traditional Node.js setups. Designed and implemented a PostgreSQL database with normalized schemas to improve data retrieval efficiency by 20%. The frontend was developed using React, providing a responsive and seamless user experience for real-time budget updates. This project showcases my passion and ability to build high-performance, full-stack web applications with a focus on speed, usability, and system design.
Developed an AI-powered image generation pipeline that creates personalized “spirit animal” overlays based on user-submitted images and poses. The system uses ControlNet and Stable Diffusion for generating high-fidelity, pose-aligned outputs, with additional preprocessing and inpainting handled through OpenCV. Built a real-time web application to allow users to interactively generate, upscale, and stylize their images using pretrained models (e.g., Van Gogh-inspired filters). Integrated seamless background removal and overlay to ensure natural blending with original images. This project combines generative AI, computer vision, and real-time deployment to build engaging, user-facing applications.
Apart from being a web developer, I enjoy most of my time being outdoors. In the winter, I am an avid skier and novice ice climber. During the warmer months here in Colorado, I enjoy mountain biking, free climbing, and kayaking.
When forced indoors, I follow a number of sci-fi and fantasy genre movies and television shows, I am an avid ballroom dancer, and I spend a large amount of my free time exploring the latest technologies in the web development world.