Scientific CUDA benchmarking framework: 4 implementations x 3 power modes x 5 matrix sizes on Jetson Orin Nano. 1,282 GFLOPS peak, 90% performance @ 88% power (25W mode), 99.5% accuracy validation, edge AI deployment guide.

Intelligent hardware innovation practice, Spring 2020

A DIY digital Stylophone built with a Raspberry Pi Pico.

openObserver makes it easy to develop and run embedded software that runs complex machine learning models

🔍 Analyze CUDA matrix multiplication performance and power consumption on NVIDIA Jetson Orin Nano across multiple implementations and settings.

This is a page for a homemade ph sensor. This is a great activity for high school students or those wanting to learn embeded systems.

Embedded Systems project

This system would help a 'running car' to detect the concrete type of an obstacle and then take different approaches according to the 'type' detected by multi-sensor fusion and CV.

캡스톤디자인: 스마트 통합보관함

This project demonstrates how to control the **brightness of an LED** connected to the **ESP8266** using **Pulse Width Modulation (PWM)** in **MicroPython**. The LED gradually fades in and out, creating a smooth brightness transition.

Leveraging ml to calibrate my custom built pyranometer

About Detection of fringe patterns in self-mixing based interferometric signals using EfficientDet and YOLOv5 object-detection model and deploying the model on Jetson Nano