HomeResearch

Research

제조·물류·의료·교통 등 다양한 산업 도메인에서 진행한 데이터 분석·머신러닝 연구 프로젝트입니다.

Predictive Maintenance and Remaining Useful Life Prediction for Collaborative Robots in Shipbuilding
2026.03 –Predictive Maintenance and Remaining Useful Life Prediction for Collaborative Robots in ShipbuildingDeveloping predictive-maintenance and remaining-useful-life (RUL) prediction models for collaborative robots operating in shipyard manufacturing, as part of a national multimodal foundation model R&D program.
User-Centered Evaluation of Public Transit Route Recommendations
2026.03 –User-Centered Evaluation of Public Transit Route RecommendationsEvaluating whether public-transit route recommendations provide practically useful choices for users.
Risk-Aware Imitation Learning with Environmental Context for AIS
2025.08 –Risk-Aware Imitation Learning with Environmental Context for AISImitation-learning anomaly detection for AIS augmented with environmental data so the model separates risky behavior from weather-driven detours.
Hybrid Prompt Agent for Conversational Maritime AIS Data Analysis
2025.06 – 2025.08Hybrid Prompt Agent for Conversational Maritime AIS Data AnalysisA Hybrid Prompt Agent enabling natural-language analysis of maritime AIS data by combining query classification with dynamic prompting.
A robust, generalizable foundation model for bioelectrical signals
2024.10 –A robust, generalizable foundation model for bioelectrical signalsDeveloping a foundation model that generalizes across heterogeneous bioelectrical signal domains.
Physics-Informed AI for Robust Ship Fuel Consumption Prediction
2024.03 –Physics-Informed AI for Robust Ship Fuel Consumption PredictionA ship fuel-consumption prediction model that accounts for environmental factors.
Fault Detection via Domain-Knowledge-Based Training Data Refinement
2023.07 – 2024.10Fault Detection via Domain-Knowledge-Based Training Data RefinementA domain knowledge–based data refinement methodology for detecting defective products that cannot be filtered out in the LQC process.
Data-driven user engagement metrics for updatable home appliances
2023.06 – 2024.05Data-driven user engagement metrics for updatable home appliancesDeveloping a new metric for measuring customer satisfaction based on user activity data.
Deep Learning for the Behavior of Linear Compressor Pistons
2022.12 – 2023.12Deep Learning for the Behavior of Linear Compressor PistonsDeep learning–based sensorless control of linear compressor pistons with over 90% performance improvement.
Domain Knowledge-Informed Functional Outlier Detection for LQC
2022.01 – 2022.12Domain Knowledge-Informed Functional Outlier Detection for LQCAn ST-based method using failure-pattern knowledge to detect tiny anomalies in manufacturing time-series data.
Personalized Dose Determination for Thyroid Hormone Disorders
2022.01 – 2025.12Personalized Dose Determination for Thyroid Hormone DisordersOptimal, personalized dose determination using deep learning–based survival analysis.
Active Thyroid-Associated Orbitopathy Detection on Eye Photographs
2021.08 – 2021.12Active Thyroid-Associated Orbitopathy Detection on Eye PhotographsA deep learning–based system for early monitoring and diagnosis of thyroid eye disease before irreversible damage.
Prediction of Traffic Congestion Propagation
2021.01 – 2024.02Prediction of Traffic Congestion PropagationModeling and quantifying time-lagged accident-induced congestion using causal inference and bootstrap uncertainty analysis.
Real-Time Changing-State Quasar Detection
2021.01 – 2025.12Real-Time Changing-State Quasar DetectionReal-time detection of changing-state quasars using a Mixture Density Network.
CNN-based Gas Mixture Classification
2020.03 – 2020.07CNN-based Gas Mixture ClassificationA CNN-based multi-channel time-series method for accurate classification of gas mixtures using electronic-nose sensor data.
Maritime Anomaly Detection
2020.01 – 2022.01Maritime Anomaly DetectionAn ST-based method using failure-pattern knowledge to detect tiny anomalies in manufacturing time-series data.