November 8
@
12:00 PM
–
1:00 PM
This talk showcases recent research on modeling and analyzing the geometric shapes of objects and long sequences of shapes, with applications in operations research. These applications include modeling human performance in motion-and-time studies, creating human digital twins for smart manufacturing, and monitoring product shape quality. The main challenge is that the space of shapes is non-Euclidean, high-dimensional, and curved, which makes traditional vector space techniques inapplicable. Modeling a stochastic process in this complex space, representing probabilistic changes in shapes over time, adds to the difficulty. We introduce some innovative flattening techniques to approximate the stochastic process in curved space by translating it into a vector space. Additionally, we discuss the application of these techniques to motion-and-time studies in operations research and product quality engineering in advanced manufacturing.
Bio: Prof. Chiwoo Park is a Professor in the Department of Industrial and Systems Engineering at the University of Washington. He earned his B.S. degree in Industrial Engineering from Seoul National University in 2001 and his Ph.D. in Industrial Engineering from Texas A&M University in 2011. Before joining the University of Washington in 2024, he was a Professor at Florida State University. Prof. Park’s research focuses on machine learning and data science, particularly their applications in advanced manufacturing and physical science. He is known for his work on shape data analysis, surrogate modeling, experimental design, and the development of digital twins for cyber-physical systems. His contributions to the field have earned him several honors, including the Ralph E. Powe Junior Faculty Award and the Brainpool Fellowship.