During 2022 Research award ceremony, Dr. Park received two awards, first time in NCAT award history two awards given to one faculty: Outstanding Young Investigator Award and Intellectual Property Award.
I make proactive dynamic distributed decisions by integrating different types of resources (aerial + ground + CAV, electric vehicles) and modality (on-demand + walk), sensing (mobile + fixed) under uncertainties caused by heterogenous users (informed + uninformed) and mutually dependent events (assuming non i.i.d).
The new foundational approach analyzes unobserved heterogeneity in transportation data as mixture of multimodal multivariate traffic parameters simultaneously sampled from more than one peak in probability distribution and more than one variable among travel time, flow, density, jam density, headway data, etc. For example, instead of a realization of travel time of nearby links for online updating route choice, I analyze each cell as multivariate multimodal probability distributions, aggregate all cells in a network, group cells with similar type mixture distribution across different far distance, non-contagious locations, and approximate the posterior when I have new observations.
Online multimodal learning can improve the mobility prediction in the backend cloud source (passive) or we can optimize the route or mobile sensing (active) to maximize the improvement in the uncertainty in prediction have been applied for smart technologies in resilient, equitable, and sustainable cities issued for two patents (US Patent 10,743,198 for mobile sensing and US Patent 11,046,247 for in-vehicle monitoring).
This new approach can understand the dynamics of network behavior and monitor the resilience of infrastructure to enable intelligent decision-making. Deep semantic learning could extract spatiotemporal interactions between heterogeneous agents, predict the future network behaviors considering dynamic changes from disruptions, and enhance city resilience by systematically responding to events, optimize energy-aware mobility, and minimize social inequity’s disproportionate impact on underserved communities in a sustainable manner. The city accessibility was significantly improved by integrating mobility preference of vulnerable road users on mixed sidewalks and on-transit reliability. Safe and effective evacuation plans were developed by considering the motion of pedestrian dynamics subject to social forces.
Hyoshin “John” Park, Ph.D., assistant professor of computational data science and engineering (CDSE) at North Carolina Agricultural and Technical State University, was recently awarded a patent to solve traffic congestion using optimized relocation and placement of portable sensors.
Park noted while the potential benefits are great for optimized sensor deployment, the challenges associated with solving traffic demand patterns can obscure opportunities for researchers to create innovations in the field. His patent taps into one of those challenging innovations and prioritizes a proactive approach for mitigating traffic congestion.
Traditionally, cities deploy localized sensors, such as embedded loop sensors and cameras, at traffic intersections to trigger traffic signals. The intersections using these sensors are typically the city’s most frequently congested and most prone to experience queue spillback when a turn lane exceeds its capacity. The localized sensors help, yet are incapable of evaluating the larger transportation network.
Park’s patent, called “Transportation Infrastructure Location and Redeployment,” offers a cost-effective, efficient and flexible solution that prioritizes the larger network of traffic, as opposed to localized sensors.
“The algorithm uses portable sensors to assess the traffic flow in nearby intersections, detect queue spillback and make changes to the timing of the traffic signals as necessary. All of these will help to ease the flow of traffic and make traffic more efficient,” said Park.
Smaller portable sensors, unlike permanently embedded sensors, can easily be positioned at traffic intersections and moved at regular intervals – weekly or monthly – to better detect new congestion trends and build a historical data log of the intersections across a city. From there, the city’s traffic trends can be fed as input data to a simulation of that city modeled as a network of interconnected roads. This enables the timing of traffic signals to be adjusted to improve the flow of larger areas of the city, instead of focusing only on the individual road or intersection. This strategy is able to improve drivers’ experiences as traffic patterns evolve throughout the year, including during major events like festivals, sporting events and concerts.
The sensors work by collecting basic data from the onboard equipment in vehicles and transmitting that data to road-side sensors, which are integrated with the traffic signal controllers, and are in turn integrated with the larger road network.
“The power of the coordinated approach is that green-light phases can be evenly distributed at intersections in real-time to enable open flows of traffic where needed, thus reducing network delays and improving the efficiency of traffic flow,” said Park.
Park hopes to leverage the patent’s innovations across North Carolina and the nation by collaborating with the many local and federal partnerships he has established during his time at A&T.
“For this task of employing sensors across a greater, connected transportation network, synchronously commanded robots, drones and autonomous vehicles would be ideal future capabilities of this patent,” said Park.
He focuses on “LEarning, Active sensing, Robust optimizatioN” (LEARN) research and has built an extensive list of state and federal relationships through nearly a dozen research grants since joining CDSE, including the Departments of Transportation for North Carolina, Virginia and the United States; the National Science Foundation; the NASA Jet Propulsion Laboratory and more.
Park aims to apply his traffic flow innovations to assist cities in adjusting to changes in vehicular traffic, particularly as vehicles on the roadways become more autonomous and interconnected. For the state and federal agencies Park works with, finding cost-effective traffic solutions will undoubtedly be a boon to local, state and national economies looking to save costs in the aftermath of the economic decline in 2020.
Written by Alexander Saunders
End of content
No more pages to load