Abstract: Unmanned aerial vehicles (UAVs) can improve emergency medical service (EMS) logistics by quickly delivering medical interventions with the help of bystanders. We formulate a Markov decision process to jointly optimize the dispatching and redeployment of UAVs and ambulances in real-time. To tackle the curse of dimensionality, we adopt an approximate dynamic programming approach with neural network-based value function approximations.  Our approach outperforms existing benchmarks and provides guidance for effectively incorporating UAVs into EMS operations. By highlighting the potential advantages of using UAVs, we hope to encourage their wider adoption in EMS practice. Following the above focused technical talk, I will talk about more recent research developments in my lab, including (1) supervised learning based recommendation module for smart dispatch system; and (2) UAV-bystander teaming at the scene of emergency response.

Bio: Nan Kong is Professor and Deputy Head of the Weldon School of Biomedical Engineering at Purdue University. He is also Associate Director for Health Systems at the Purdue’s Regenstrief Center for Healthcare Engineering. He graduated with a B.S. degree in Automation from Tsinghua University, China, in 1999 and a Ph.D. degree in Industrial Engineering from the University of Pittsburgh in 2006. He joined the BME faculty at Purdue in August 2007 and has developed an active research program in the areas of healthcare analytics and systems optimization. He has been funded as Principle Investigator by grants from NSF, NIH, and Air Force with several other co-Investigator grants from CMS and AHRQ. He is an active member of INFORMS and IISE.

Zoom link: https://purdue-edu.zoom.us/j/99326083199?pwd=TjhqaE1TYkZ2RG1RMkt6S1JZbGk1UT09

Free coffee and snacks will be provided.