Takhyeong Kim (김탁형)

Takhyeong Kim (김탁형)

M.S. Student, Graduate School of Data Science, Pusan National University

I am a Master’s student at the Graduate School of Data Science, Pusan National University, Korea, and a member of BAELAB advised by Prof. Hyerim Bae.

My research focuses on data-driven decision making for container terminal operations, in particular reducing rehandling in import container yards through survival analysis of container dwell time and learning-based stacking policies.

Citations:

Email: glorytak74@pusan.ac.kr / glorytak74@naver.com

📌 Research Interests

  • Container Terminal Operations: stacking of import containers in the yard, rehandling reduction
  • Survival Analysis: discrete-time survival models, conditional residual survival curves for container dwell time
  • Port Logistics Data: covariate modeling based on EDI messages
  • Reinforcement Learning: learning-based container stacking policies

🔥 News

  • 2026.08:  🎉 Our paper on container dwell time prediction is published in Transportation Research Part E.
  • 2026.01:  🇸🇬 Attended AAAI 2026 in Singapore.
  • 2025.11:  🎤 Gave an oral presentation at the 2025 Fall Conference of the Korean Institute of Industrial Engineers (KIIE).
  • 2025.08:  🇬🇧 Attended the Oxford Machine Learning Summer School (OxML), MLx Representation Learning & GenAI.

📝 Publications

TR-E 2026
sym

Generative AI and Machine learning collaboration for container dwell time prediction via data standardization

Minseop Kim*, Takhyeong Kim, Taekhyun Park, Hanbyeol Park, Hyerim Bae

Transportation Research Part E: Logistics and Transportation Review, vol. 216, 105171, 2026. [DOI]

JCR 2025 Q1 · top 2% in Economics (12/626) · JIF 9.3

* indicates first author.

🛠 Projects

3D Simulator
sym

Yard Simulator — browser-based 3D visualization of container terminal yard operations

Built with three.js; replays yard activity (vessel calls, quay cranes, stacking and retrieval) and overlays colour modes for container flow, tier and predicted dwell time. Clicking a container opens its EDI event timeline together with the survival-model estimate of its remaining dwell time.

[Screenshot] [Demo video]

💬 Conference Presentations

🎖 Honors and Awards

📖 Educations

  • M.S. in Data Science, Graduate School of Data Science, Pusan National University, Busan, Korea (2025.03 - 2026.02)
  • B.S. in Technology Data Engineering, Division of Systems Management and Engineering (Industrial Engineering), Pukyong National University, Busan, Korea (2018.03 - 2024.02)
  • Oxford Machine Learning Summer School (OxML), MLx Representation Learning & GenAI track, University of Oxford, UK (2025.08)

💻 Work Experience