Kyunghee Roh

Kyunghee Roh

M.S. Student

Korea University

My name is Roh Kyunghee, and I am a master’s student in the Department of Mathematics (MDS) at Korea University and researching artificial intelligence at AIML@K.

I’m interested in Bayesian Optimization and Computer Vision.

I graduated from the Department of Physics at Konkuk University. After studying Quantum Mechanics, I realized that physics was not my path.

Interests
  • Bayesian Optimization
  • Computer Vision
Education
  • M.S. in Mathematics (MDS), 2025 (expected)

    Korea University

  • B.S. in Physics, 2024

    Konkuk University

Research Focus

What I am currently focusing on in my research

My current research focus involves extracting keypoint coordinates from video frames of exercise movements, such as squats, barbell lifts, and overhead presses. I am utilizing the Temporal Shift Module (TSM) to detect speed changes in these movements. I am conducting experiments with various backbone models, including MobileNetV2, ResNet50, ResNet101, HRNetw32, and HRNetw48, to design a model that minimizes latency and maintains performance for real-time operation on mobile devices. A key aspect of my research is finding the optimal backbone model that balances PCKh and latency, while also investigating methods to enhance overall performance

Research Goal

What I aim to achieve with my research

Our backbone model MobileNet V2 demonstrates a PCKh of 86.278 and a latency of 34.5ms when tested on a Galaxy Note 8. The objective of this research is to improve the AI model used for analyzing exercise motions to achieve a PCKh of 90 or more and reduce latency to under 30ms. To ensure practical application, I will evaluate the model’s performance and usability in real-world scenarios, incorporating user feedback for continuous refinement. Additionally, I intend to expand the exercise motion dataset, developing a model robust to the inherent variability of real-world data. Finally, I am committed to the goal of releasing the developed AI fitness application in October 2025

Research Experience

The key research achievements and experiences

 
 
 
 
 
🏋🏻‍♂️ AI Health Trainer
January 2025 – Present
As an intern, I’m working on creating an AI fitness application to recognize human motion, count repetitions, and identify speed variations
 
 
 
 
 
📊 Bayesian Optimization
September 2024 – December 2024
Through our lab’s journal club, I engaged in in-depth study of Bayesian Optimization, Gaussian Process, and Knowledge Gradient
 
 
 
 
 
📱 Semiconductor Processing
August 2024 – September 2024
In the Samsung AI Challenge 2024, I tackled a model-based optimization challenge aimed at determining the optimal parameters for semiconductor processing
 
 
 
 
 
🚙 Autonomous Driving
March 2024 – June 2024
I published a paper in KCC that analyzes the I/O data of AI algorithms for autonomous vehicles and proposes improvements to the storage system for each model
 
 
 
 
 
🪢 Jump Rope
August 2023 – February 2024
I developed an ML classification model for single/double jump rope using time-series sensor data