Committee Chair

Sartipi, Mina

Committee Member

Liang, Yu (Hugh); Cox, Christopher; Wu, Dalei

Department

Dept. of Computer Science and Engineering

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

As urbanization accelerates, cities face mounting challenges in transportation efficiency, safety, and sustainability. This dissertation explores the integration of Digital Twin (DT) technology, Connected Vehicle Communication (C-V2X), and Electric Vehicle (EV) infrastructure optimization to advance smart city mobility solutions. The research presents a comprehensive framework leveraging real-time data analytics, machine learning, and simulation technologies to enhance urban transportation systems. The first component focuses on Digital Twin-driven traffic simulation, which enables scenario testing, predictive modeling, and real-time decision-making. A key contribution is the calibration of traffic simulation models using real-world speed data, facilitating optimized traffic management, transit planning, and road safety assessments. The study includes BTE-Sim, a fast simulation environment for public transit, and a Digital Twin-based road diet analysis for Chattanooga’s Frazier Avenue, demonstrating how simulation can enhance urban mobility. The second component investigates C-V2X technology for pedestrian safety, particularly in vehicle-to-pedestrian (V2P) communication. The research conducts a comparative study of V2P architectures and pre-crash scenarios, along with field tests evaluating LTE, DSRC, WiFi, and Bluetooth-based safety systems. These findings contribute to the development of intelligent transportation networks that improve pedestrian protection through real-time communication technologies. The third component explores machine learning techniques for EV charging infrastructure optimization, leveraging embedding vector representations, matrix factorization, and clustering methods. By analyzing real-world EV charging station data, the study uncovers key utilization patterns, proposes location optimization strategies, and introduces Non-Intrusive Load Monitoring (NILM) techniques for identifying EV charging events in residential settings. This dissertation advances the scientific and practical understanding of next-generation urban mobility systems, providing a scalable, data-driven framework for intelligent transportation planning, enhanced road safety, and sustainable EV infrastructure development. The methodologies and findings offer valuable insights for policymakers, urban planners, and transportation engineers, contributing to the realization of smart, connected, and sustainable cities.

Acknowledgments

I am profoundly grateful to my PhD advisor, Dr. Mina Sartipi, for her invaluable guidance, steadfast support, and extraordinary patience throughout my doctoral journey. From the very outset, Dr. Sartipi's insightful advice significantly shaped the direction and depth of my research. My deepest gratitude goes to Dr. Sartipi, not only as an advisor but also as a mentor whose influence over the past four years has been pivotal. Words alone cannot adequately convey my appreciation for her unwavering academic and personal support. Her exceptional patience fostered an environment where I felt free to explore ideas, learn constructively from mistakes, and express myself openly. Dr. Sartipi's mentorship has immeasurably enhanced the quality of my research and profoundly impacted my growth as a researcher and an individual, for which I will always remain sincerely thankful. I would also like to express my gratitude to my committee members, Dr. Christopher Cox, Dr. Yu Liang, and Dr. Dalei Wu, for their valuable feedback and insightful guidance throughout this process. Additionally, I thank my colleagues at CUIP, whose contributions have significantly enriched my academic experience. A special thank you to Victoria Hirschberg, Assistant Vice President and Chief Economic Development Director at the University of Tennessee System, for her constant support and motivation. I am also deeply appreciative of Austin Harris, Deputy Director and CTO at CUIP, for his endless encouragement and support. Last but not least, my heartfelt thanks go to my beloved wife, Mahshid Malazizi, for her unwavering support, patience, and understanding throughout this journey.

Degree

Ph. D.; A dissertation submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Doctor of Philosophy.

Date

5-2025

Subject

Battery charging stations (Electric vehicles); Digital twins (Computer simulation); Intelligent transportation systems; Smart cities; Urban transportation; Vehicle-infrastructure integration

Keyword

Machine Learning; Smart City; ITS; Artificial intelligence;

Document Type

Doctoral dissertations

DCMI Type

Text

Extent

xxi, 392 leaves

Language

English

Rights

http://rightsstatements.org/vocab/InC/1.0/

License

http://creativecommons.org/licenses/by/4.0/

Share

COinS