I am a fifth-year Ph.D. Candidate in the Department of Industrial and Systems Engineering at the University of Wisconsin-Madison. I am fortunate to be a member of the Lab for System Informatics and Data Analytics under the supervision of Professor Kaibo Liu.
Before coming to Madison, WI, I received a Bachelor of Business Administration and a Bachelor of Economics in Statistics from Korea University, Seoul, South Korea.
[Google Scholar] [LinkedIn] [CV] (Last updated: Feb, 2025)
Contact: yhuh8@wisc.edu
My research focuses on establishing novel AI and ML methods for the modeling, analysis, control, and prediction of complex engineering systems.
I am particularly dedicated to developing reliable and accurate data-driven solutions that leverage both prior domain knowledge and cutting-edge ML methods. These solutions offer clear and explainable insights into the underlying system dynamics and have been used in a wide range of applications, including manufacturing, energy systems, healthcare, and material science.
I have a strong passion for studying and applying new methodologies, including modern approaches like large language models (LLMs), to address emerging challenges and develop innovative data-driven solutions. I also have extensive experience in Bayesian statistics, ranging from traditional Bayesian modeling to recent approaches like Bayesian neural networks and uncertainty quantification.
I am currently seeking for opportunities in industry starting in Summer, 2025 (Expected Graduation Date: June, 2025)
Looking for job titles: Applied Scientist, Data Scientist, Machine Learning Researcher, Statistician, Research Scientist
Research Interests
Statistical modeling of complex engineering systems and processes
Explainable & engineering-informed ML and deep learning methods
Explainable degradation modeling, diagnosis, and prognostics using AI
Industrial data science and data-driven decision making
Education
Ph.D. Industrial and Systems Engineering, University of Wisconsin-Madison 2020 - Current
Minor: Computer Science
M.S. Statistics, University of Wisconsin-Madison 2023 - 2024
B.B.A. Business Administration, Korea University 2014 - 2020
B.E. Statistics, Korea University 2014 - 2020
Leave of absence due to mandatory military service 2015 - 2016
Work Experience
Amazon.com Summer, 2024
Applied Scientist Intern, Amazon Pharmacy Science Team
Skills
Statistical Models: Bayesian statistics, Markov Chain Monte Carlo, Bayesian Neural Networks, Uncertainty Quantification, Hierarchical Bayesian Modeling, Gaussian Processes, Deep Survival Models, Large Language Models (BERT, T5, Llama 3, Mistral)
Programming: Python (Pytorch, TensorFlow, Scikit-learn, Huggingface, SciPy), R, SQL, Matlab, AWS Sagemaker, Stan
Publications
Published or Accepted
Ye Kwon Huh, Minhee Kim, Kaibo Liu, and Shiyu Zhou "An Integrated Uncertainty Quantification Model for Longitudinal and Time-to-event Data", published in IEEE Transactions on Automation Science and Engineering, 2024
Ye Kwon Huh, Minhee Kim, Katie Olivas, Todd Allen and Kaibo Liu, "Degradation Modeling using Bayesian Hierarchical Piecewise Linear Models: A case study to predict void swelling in irradiated materials", published in Journal of Quality Technology, 2024
Ying Fu, Ye Kwon Huh, and Kaibo Liu "Degradation Modeling and Prognostic Analysis Under Unknown Failure Modes", to be published on IEEE Transactions on Automation Science and Engineering, 2025
Ye Kwon Huh, Ying Fu, Kaibo Liu, "A Bayesian spike-and-slab sensor selection approach for high-dimensional prognostics", conditionally accepted, IEEE Transactions on Automation Science and Engineering, 2025
Under review
Bruno P. Serrao, Ye Kwon Huh, Eliot Ciuperca, Elvan Sahin, Kaibo Liu, Juliana Pacheco Duarte "A Quantitative Analysis of ATF Surface Characteristics on Critical Heat Flux using Machine Learning", Under Review, Nuclear Engineering and Design, 2025
Ying Fu, Ye Kwon Huh, Kaibo Liu, "Dynamic sensor selection for remote prognostics", Under Review, IISE Transactions, 2025
In preparation
Ye Kwon Huh, Kaibo Liu, "An uncertainty-informed neural network-based prognostic model for multi-type data", To be submitted to IISE Transactions, 2025