Yooseok Lim

Hi! I am currently working as a researcher at Seoul National University Hospital.

I am focused on advancing healthcare and medical AI, with a primary interest in Reinforcement Learning. I believe these methods are powerful tools for developing advanced medical solutions that can meaningfully contribute to improving society.

I received an MS in Industrial and Information Systems Engineering from Soongsil University in South Korea in 2024. Fortunately, I was advised by Prof. Sujee Lee (currently at SKKU).

Email  /  GitHub  /  Google Scholar  /  CV

Under Review and Revision

An Uncertainty-Aware Reinforcement Learning Framework for Safer Drug Dosing

Research Trends in the Adoption of Digital Twins in Healthcare: Applying Structural Topic Modeling

Preprints

MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation

MORE-CLEAR is a multimodal offline RL framework that integrates clinical notes and structured data using LLMs, gated fusion, and cross-modal attention, achieving better survival estimates and policy performance than single-modal methods.

OMG-RL: Offline Model-based Guided Reward Learning for Heparin Treatment

This study proposes Offline Model-based Guided Reward Learning (OMG-RL) to develop a reward function that captures clinicians’ intentions for reinforcement learning-based medication dosing.

Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm

This study proposes a reinforcement learning (RL)-based personalized heparin dosing policy for ICU patients to ensure optimal dosing and minimize complications.

Intelligent Repetition Counting for Unseen Exercises: A Few-Shot Learning Approach with Sensor Signals

This study introduces a method using a deep metric-based few-shot learning approach to accurately count repetitions of both known and novel exercises.

Publications

Multimodal sensor fusion models for real-time exercise repetition counting with IMU sensors and respiration data

This study develops an automatic exercise repetition counting model using a multi-modal deep learning approach. The model leverages data from smart earbuds with IMU sensors and respiratory audio recordings, enabling accurate tracking across 30 different exercise types.

Machine learning-derived model for predicting poor post-treatment quality of life in Korean cancer survivors

Many cancer survivors experience poor quality of life (QOL) even after completing treatment. In this study, we developed predictive models using machine learning (ML) to identify poor QOL in post-treatment cancer survivors in South Korea.

Industry Projects

Development of an AI Model and Service Concept Based on Canine Activity Data

Development of a Course Recommendation System Based on Natural Language Data

Development of a Counting Algorithm Based on Human Activity Data

Personal Projects

3D Medical Segmentation

This project implements 3D medical segmentation algorithms.

Traffic Sign Detection

This project tackles traffic sign detection using multiple models across two datasets. It emphasizes cross-dataset evaluation to assess how well a model generalizes to different data distributions, addressing the challenge of distributional shifts.

Autonomous Driving Temperature Measurement Robot

Development of an autonomous driving robot using computer vision, reinforcement learning, and edge computing technologies

Design and source code from this site