Seungsukam Portfolio

SEUNGSU KAM(감승수)

UNIST PhD Student. 불규칙 시계열 · 이상탐지 · 연속시간 모델링 · 종단 생존분석.

👤 About

I am a Ph.D. student in Industrial Engineering at UNIST under the supervision of Professor Sungil Kim. My work involves Neural Differential Equations, Conditional Density Estimation, and Survival Analysis, which I apply to problems such as real-time anomaly detection, astronomical object anomaly classification, longitudinal patient outcome prediction, and personalized thyroid hormone dosage recommendation.

🔬 Research Interests

⏱ Time Series Analysis 🔎 Anomaly Detection ⌛ Continuous-time Modeling 📊 Longitudinal Survival Analysis

🛠 Project

🌌 Real-Time Quasar Anomaly Detection

실시간 퀘이사 이상 탐지

Real-Time Physics-Informed Anomaly Detection

🔭 Irregular Astronomical Time Series Anomaly Detection

불규칙 천체 시계열 이상치 탐지

Irregular TS Neural DE Classification

📊 Longitudinal Multi-risk Survival Analysis

종단 생존분석

Longitudinal Multi-risk Survival

💊 Thyroid Hormone Dosage Recommendation

갑상선 항진증 환자 복용량 추천

Hyperthyroidism Recommendation Healthcare

📑 Papers

(2025) Comprehensive review of neural differential equations for time series analysis, Oh, Y.; Kam, S.; Lee, J.; Lim, D.; Kim, S.; Bui, A., arXiv

(2024) (Short) Neural Langevin-type Stochastic Differential Equations for Astronomical time series Classification under Irregular Observations, Oh, Y.; Kam, S.; Lim, D.; Kim, S., ICLR Workshop

(2024) (Short) Enhancing Astronomical time series Classification with Neural Stochastic Differential Equations under Irregular Observations, Oh, Y.; Kam, S.; Lim, D.; Kim, S., AAAI Workshop, workshop

🎤 Presentation

(2024) Advancing Irregular Time Series Classification in Astronomy with Neural Stochastic Differential Equations, Oh, Y.; Kam, S.; Lim, D.; Kim, S., INFORMS Workshop on Data Science 2024, workshop

(2024) Optimal and Personalized Initial Dose Determination for Patients with Thyroid Hormone Disorders Using Deep Learning-Based Survival Analysis, Kam, S.; Cho, J.; Shin, K.; Moon, J.; Kim, S., IISE2025

(2024) Addressing Spatial Gaps in XCO2 Monitoring: A Machine Learning Approach for South Korea, Cho, H.; Kam, S.; Jeon, B.; Lee, K.; Kim, S., KIIE, Record

(2024) Assessing User Retention of Connected Home Appliances: Survival Analysis, Cho, H.; Kam, S.; Hur, C.; Kim, S., KIIE, Record

(2023) Optimal and Personalized Dose Determination for Patients with Thyroid Hormone Disorders Using Deep Learning-Based Survival Analysis, Kam, S.; Cho, J.; Shin, K.; Moon, J.; Kim, S., KIIE, DBpia

(2023) Real-Time Detection of Changing-State Active Galactic Nuclei using a Deep Learning Approach, Kam, S.; Yoo, J.; Shin, M.; Kim, S., KIIE, Record