Smart-Farm Education Program

A hands-on education program, commissioned by the Yangpyeong Education Office through the museum, where students work with an IoT smart farm and AI crop diagnosis. It was taught as a demo class to 5 high-school students in August 2026 and is scheduled to run in October 2026 for a cohort of 15 Yangpyeong high-school students, selected by application.

I planned and built it solo: a Next.js web app with server API routes on Vercel, and Arduino (C++) firmware for the class's 15 ESP32 student boards (one per student), which write sensor readings straight to Supabase. Students move through four STEPs (weather, AI vision, IoT and camera) and watch sensor values change in real time. In the capstone they code if-then automation rules and run them on the real board. They also train a model themselves inside the browser with TensorFlow.js transfer learning on MobileNet v2, so the epoch and loss numbers they watch come from their own run.