As a researcher in transportation and traffic studies with an emphasis on statistical, data-driven, and data science methods, my work centers on two main research interests: travel behavior analysis (behavioral economics) and the analysis of traffic flow operations. Travel behavior analysis is crucial for guiding transportation policies and investments, akin to understanding travelers' (consumer) behavior in the market economy of the transportation network. This research provides valuable insights for decision-making, resource allocation, and strategy development to meet dynamic user demands. The other aspect of my research focuses on big data, employing data fusion methods to gain a more comprehensive understanding of traffic flow phenomenon. Despite the prevalence of innovative, complex, and costly data collection methods in scholarly publications, there's a wealth of underutilized data prepared through more economical means, often dismissed without fully exploring the potential of data fusion methods.
Travel behavior analysis is the application of behavioral economics in the context of transportation planning, which typically concerns predicting future urban and regional development using methods like four-step or activity-based approaches. While these plans focus on factors like population, employment, and traffic flow, I aim to delve deeper. My interest lies in exploring the nuanced factors influencing the balance between supply and demand in transport networks, considering people's preferences and constraints. I am inspired by understanding the dynamic equilibrium driven by the choices of different demographic groups based on their specific activity needs.
Lane-level Routable Digital Maps
Routable digital maps provide navigational guidance by representing roads and pathways digitally. Their importance lies in enhancing real-time navigation, traffic management, and location-based services. Lane-level precision adds a crucial layer of detail, allowing for precise route planning, especially in complex traffic scenarios and urban environments. This detailed mapping ensures accurate navigation, minimizes congestion and supports emerging technologies like autonomous vehicles, where precise lane information is vital for safe and efficient transportation.
With experience, we can gain cognition of the features of any object in general. Also, objects are only known as they are experienced and not exactly as they are (cognition is not perfect). Whenever we experience more features of an object or gain multiple experiences from certain features of that object, our cognition of it gets more comprehensive, and the conviction of this understanding expands (Immanuel Kant 1781). Data fusion is a well-known method that leads to more reliable cognition based on experience from various measurement sources and results in producing more consistent, accurate, and useful information (Hall and Llinas, 1997). I introduced two methods based on data fusion and big data mining to approximate trajectory data. Based on these approximated trajectories, I showcased the empirical analysis and discrete choice modeling of lane-changing behavior.
At the heart of modern transportation networks, motorway traffic flow is a complex and dynamic system. It encompasses vehicle movement, driver interactions, and the multifaceted factors influencing road travel efficiency, safety, and sustainability. At its core, motorway traffic flow entails the study of vehicle operations within road networks and their interactions. Driver maneuvers encompass both longitudinal actions, guiding vehicles along their path, and lateral maneuvers, typically involving lane changes within motorway networks. Despite their significance, there is a noticeable gap in research on lateral vehicle movements in the existing literature. Many empirical and modeling explorations of these maneuvers are facilitated thanks to reconstructed trajectories based on the methods developed in my research.
Studying pedestrians and walking is crucial in transportation studies as it addresses sustainable mobility and urban livability. Understanding pedestrian behavior informs the design of pedestrian-friendly infrastructure, enhancing safety and accessibility. Land use planning plays a pivotal role in influencing the built environment. Effective planning can motivate walking through well-designed urban spaces, providing convenient access to destinations and fostering a sense of community. Integrating walking considerations into transportation studies contributes to holistic urban planning, promoting active transportation, reducing congestion, and creating healthier, more vibrant cities. I am involved in several data analysis explorations regarding walking.
Machine Learning Application on Transportation
Machine learning and AI in transportation have transformed urban mobility by extracting insights from vast datasets, predicting congestion, and optimizing systems. Utilizing neural networks and AI algorithms can help forecast travel times, identify anomalies, and enhance traffic management. Real-time data from sensors, GPS, and social media enable timely information for commuters. They also drive innovative transportation solutions like autonomous vehicles, fostering urban network efficiency, sustainability, and resilience.
Operational Research and Optimization
Applying Operations Research (OR) and optimization methods in traffic and transportation studies is pivotal for enhancing efficiency and sustainability. These mathematical techniques provide robust tools to tackle complex challenges, such as traffic flow optimization, route planning, and resource allocation. OR models enable the evaluation of diverse scenarios, optimizing traffic signal timings, transit schedules, and logistics operations. Through mathematical optimization, decision-makers can minimize congestion, reduce travel times, and improve overall system performance. These methods play a crucial role in designing resilient transportation networks, ensuring optimal resource utilization, and advancing the development of intelligent transportation systems. By leveraging OR techniques, researchers and policymakers can address the intricate dynamics of urban mobility, facilitating more brilliant, more adaptive, and sustainable transportation solutions.