RESEARCH

RESEARCH INTEREST

My research interests include large-scale optimization and decision analysis, stochastic networks and simulation modeling, and artificial intelligence and machine learning, with applications to smart and sustainable systems. I am particularly interested in improving the resilience of large-scale transportation and supply chain or logistics systems, developing emergency management planning under uncertainty, and designing sustainable systems that matter to society.

SELECTED GRANTS

PI, Enhancing AIT-based Passenger Screening Processes and Security Through Integrated Stochastic Optimization and Artificial Intelligence Strategies, Department of Homeland Security (DHS), 2025 - 2027.
PI, AWS Cloud to Table Initiative: Decision-Support Models for Resilient Food Supply Chains under Uncertain Disruptions, Amazon Web Services (AWS), 2025 - 2026.
PI, Integrated Deep Reinforcement Learning and Large-Scale Optimization for Enhancing Last-Mile Logistics with Future Mobility Technologies, Jungseok Logistics Foundation (JLF), 2025 - 2026.
Co-PI, Texas 9-1-1 Funding Analysis and Public Opinion Survey, Texas 9-1-1 Alliance Rapid Grant, 2024 - 2025.
Co-PI, Data-driven Disruptive Event Modeling to Improve Operational Resilience in Modernized and Decarbonized Smart Grids, Mizzou College of Engineering Seed Grant, 2024 - 2025.
PI, Optimal Deployment of Capacitated Fast Charging Stations for Electric Vehicles on a Directed Highway Network, Mizzou Research Council Grant, 2024 - 2025.
PI, Disaster Assessment from Satellite Imagery using Improved Generative Adversarial Network and UNet, National Aeronautics and Space Administration (NASA) EPSCoR Research Initiation Grant (RIG), 2022 - 2024.
PI, An Integrated Simulation-based Optimization Model for Solving Multi-Objective Dynamic Facility Layout Problems, Black Hills Stock Show Foundation, 2022 - 2023.
PI, Collaborative Research: Leveraging the Resilience and Recovery through the Analysis of Spatial-Temporal Data-Driven Aerial Imagery, National Aeronautics and Space Administration (NASA) EPSCoR Research Grant, 2020 - 2023.

Stochastic Optimization & Artificial Intelligence

My research develops decision-making methods for complex systems that must operate under uncertainty. By integrating stochastic optimization, artificial intelligence, machine learning, and simulation, this research aims to support reliable, adaptive, and data-informed decisions in transportation, logistics, emergency response, manufacturing, energy, and autonomous systems.

A main focus is to design optimization models and algorithms that can learn from data, represent uncertain system behavior, and generate high-quality decisions in real time or near real time. These methods address challenges such as uncertain demand, disrupted infrastructure, changing travel conditions, limited resources, human behavior, and evolving system risks.

Computer Vision or Image Processing

Our research in computer vision and image processing focuses on developing AI-enabled methods that transform visual data into actionable information for smart, sustainable, and resilient systems. We work with images and videos collected from drones, satellites, mobile sensors, surveillance cameras, and other sensing platforms to support automated scene understanding, object detection and tracking, semantic segmentation, anomaly detection, infrastructure inspection, disaster damage assessment, and transportation system monitoring.

This research area combines deep learning, image enhancement, multimodal data fusion, uncertainty-aware prediction, and real-world system analytics. The goal is not only to build accurate computer vision models, but also to connect visual data with simulation, optimization, and decision-support frameworks for practical engineering and societal impact.

Artificial Intelligence-Driven Simulation

This research area develops AI-enhanced simulation models to analyze, predict, and improve the performance of complex systems under uncertainty. By combining machine learning, agent-based simulation, digital twins, simulation-optimization, and data-driven decision support, we study how transportation, logistics, emergency response, manufacturing, supply chain, and autonomous systems behave in dynamic real-world environments.

The goal is to create simulation models that can learn from real-world data, adapt to changing conditions, and evaluate what-if scenarios before costly or high-risk decisions are made in practice. These models can help answer critical questions such as how people evacuate during disasters, how autonomous vehicles and drones should be deployed, how supply chains respond to disruptions, and how infrastructure systems can be operated more efficiently and resiliently.

Resilient Transportation & Emergency Response

This research area focuses on developing data-driven decision-support models to improve transportation system resilience before, during, and after disruptive events such as hurricanes, floods, earthquakes, infrastructure failures, and large-scale emergencies. The goal is to help communities, agencies, and responders make faster, more reliable, and more equitable decisions under uncertainty.

Our work integrates stochastic optimization, simulation modeling, artificial intelligence, machine learning, and geospatial analytics to support emergency planning and real-time response operations. Key research problems include evacuation planning, emergency vehicle routing, shelter and resource allocation, infrastructure damage assessment, network restoration, and post-disaster accessibility analysis. These problems are complex because disruptions evolve dynamically, transportation networks can become partially damaged or congested, and human behavior during emergencies is uncertain.

Smart Logistics & Autonomous Systems

My research in Smart Logistics and Autonomous Systems focuses on developing data-driven, optimization-based, and simulation-enabled decision-support methods for complex logistics, transportation, and infrastructure systems. The goal is to design intelligent systems that can operate reliably under uncertainty, adapt to changing environments, and support timely decisions in high-impact applications such as last-mile delivery, supply chain operations, emergency response, disaster recovery, and smart mobility.

This research integrates large-scale stochastic optimization, artificial intelligence and machine learning, agent-based simulation, and autonomous systems modeling to address emerging challenges involving drones, robots, unmanned ground vehicles, connected vehicles, and intelligent infrastructure. Key research questions include how to coordinate heterogeneous autonomous vehicles, how to optimize logistics operations under uncertain demand and disruptions, how to combine simulation and optimization for real-time decision-making, and how to use AI-enabled sensing and prediction to improve system resilience, efficiency, and safety.

RESEARCH SPONSORS

THANKS to our project sponsors:

Page updated

Report abuse