Emerging Research in Industrial and Systems Engineering: Perspectives from PhD Students
Abstract: Join us for a special seminar showcasing cutting-edge research by three outstanding PhD candidates in Industrial and Systems Engineering. This session brings together scholars from Rutgers University and Lehigh University, highlighting diverse approaches and innovative solutions to challenges in optimization, data science applications, and energy forecasting. Don’t miss this chance to explore the work of the next generation of researchers and connect with peers across institutions.
Each candidate will deliver a 20-minute presentation:
Robust Optimization for Complex Decision-making, by Man Yiu (Tim) Tsang
Abstract: An inexact column-and-constraint generation (i-C&CG) method offering computationally efficient solutions to large-scale two-stage robust optimization problems with applications in financial risk management and transportation systems. Bio: A Ph.D. candidate in Industrial and Systems Engineering at Lehigh University under Prof. Karmel S. Shehadeh, Tim specializes in data-driven stochastic optimization for applications in financial risk management, healthcare, and transportation systems. His work has earned the Van Hoesen Family Best Publication Award and recognition in the Junior Faculty Interest Group Paper Prize.
Advanced Inference Techniques for Higher-order Graphical Models, by Yakun Wang
Abstract: Binary polynomial optimization and linear programming relaxations for solving higher-order undirected graphical models with applications in image restoration and errorcorrecting code decoding. Bio: A third-year Ph.D. candidate in the Department of Industrial and Systems Engineering at Lehigh University, working with Prof. Aida Khajavirad. He received his MSc from Lehigh University and his BSc from Southwest Jiaotong University in China. His research interest lies in mixed-integer nonlinear optimization for data science applications.
Multivariate Spatio-temporal Forecasting for Offshore Wind Energy, by Feng Ye
Abstract: A novel statistical deep learning method for modeling wind speeds across space, time, and height to enhance wind energy forecasting for ultra-scale offshore turbines. Bio: A Ph.D. candidate in Industrial & Systems Engineering at Rutgers University, Feng develops statistical and machine learning methods to improve offshore wind energy forecasting. His research, in collaboration with RUCOOL, has received multiple awards, including Best Paper in the Energy Systems Track (2023 IISE Annual Meeting) and the QCRE Best Student Poster Award (2024 IISE Annual Meeting).
Click here to read the full abstracts and speakers’ bios.