Article
Ergonomics
Junhua Wang, Ting Fu, Qiangqiang Shangguan
Summary: Trajectory data of road users is crucial for transportation engineering and traffic safety research. With the development of sensing and tracking technologies, it is now possible to track the real-time trajectory data of all road users on the entire road. We have published a data sharing platform that provides open wide-area vehicle trajectory data, which can be used for research in road transportation engineering, road safety, and connected and autonomous vehicle applications.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Physics, Multidisciplinary
Yu Han, Mingyu Zhang, Yanyong Guo, Le Zhang
Summary: This paper proposes a streaming-data-driven method for estimating freeway traffic state based on probe vehicle trajectory data. The method reconstructs the flow and density of the freeway section by estimating the numbers of normal vehicles between consecutive probe vehicles. The speed of shockwaves is assumed to be stochastic, and its posterior distribution is estimated using Bayesian regression. The method achieves good estimation accuracy even with low penetration rates. It is also compared to a state-of-the-art method in a simulation study and shows comparable performance without spacing information in the trajectory data.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Chemistry, Analytical
Shiting Ding, Zhiheng Li, Kai Zhang, Feng Mao
Summary: This study selects representative sequential pattern mining algorithms and evaluates their performance on taxi trajectory data. The results demonstrate that contiguous constraint-based algorithms show good performance in terms of balanced RAM consumption and execution time.
Article
Energy & Fuels
Wen -Long Shang, Mengxiao Zhang, Guoyuan Wu, Lan Yang, Shan Fang, Washington Ochieng
Summary: This paper proposes a traffic energy consumption model based on the macro-micro data, which combines data from fixed-location sensors and Connected and Automated Vehicles (CAVs) to accurately estimate traffic energy consumption. The model constructs vehicle trajectories using nonparametric kernel smoothing algorithm and variational theory. Experimental results show that the proposed method not only reflects the characteristics of traffic kinematic waves caused by congestion, but also minimizes errors caused by the macro-micro transformation, leading to significantly improved accuracy in energy consumption estimation.
Article
Transportation Science & Technology
Mohammadhossein Bahari, Ismail Nejjar, Alexandre Alahi
Summary: Vehicle trajectory prediction can be approached from knowledge-driven or data-driven perspectives, each with its own advantages and limitations. This paper proposes a method that effectively combines these perspectives by using residuals to adjust trajectory predictions from a knowledge-driven model, ultimately achieving more realistic outputs with improved accuracy and generalization performance.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Green & Sustainable Science & Technology
Ruoxi Jiang, Shunying Zhu, Hongguang Chang, Jingan Wu, Naikan Ding, Bing Liu, Ji Qiu
Summary: This study compared the applicability of TTC, PET, DRAC, and the newly proposed T-i indicators in highway safety estimation through conflict-accident correlation analysis. The results showed that T-i indicator had the highest correlation, overcoming the limitations of conventional indicators.
Article
Engineering, Electrical & Electronic
Lei Chen, Xiaorong Xie, Mingshu Song, Yongguang Li, Yanjun Zhang
Summary: This research designs a novel finite impulse response (FIR) filter, named the multi-tone FIR (MTFIR) filter, to estimate the magnitude and frequency of high-frequency oscillation (HFO) in a fast and accurate way for early warning and mitigation. Performance tests show that the proposed MTFIR filter estimator is more accurate than the conventional FIR filter, the interpolated discrete Fourier transform, and the P-class harmonic phasor estimator in HFO magnitude and frequency estimation. The response time of the proposed estimator is shorter than 20 ms, meeting the IEEE/IEC standard requirement.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Engineering, Civil
Rongjian Dai, Chuan Ding, Xinkai Wu, Bin Yu, Guangquan Lu
Summary: This study proposes a two-dimensional control strategy for isolated signalized intersections, which optimizes traffic signals, lane settings, and vehicle trajectories in a mixed traffic environment. The proposed algorithm outperforms the actuated control in terms of vehicle travel time under both under-saturated and over-saturated traffic conditions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Peng Zhang, Jun Zheng, Hailun Lin, Chen Liu, Zhuofeng Zhao, Chao Li
Summary: This study aims to improve the efficiency of information collection and extraction in the current intelligent transportation system by using Artificial Intelligence (AI) and Deep Learning methods to mine and analyze vehicle trajectory data. It proposes a method of mining driving behavior characteristics based on Convolutional Neural Network (CNN) and vehicle trajectory. The combined model of trajectory mining is constructed and applied to the short-term prediction of traffic flow, and the accuracy of the models is verified using real traffic data.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Enrique Saldivar-Carranza, Howell Li, Jijo Mathew, Margaret Hunter, James Sturdevant, Darcy M. Bullock
Summary: This paper introduces a method of using vehicle trajectory data to produce traffic signal performance measures, and demonstrates its application through a case study. The technology can effectively improve the efficiency and performance of traffic signal operations.
TRANSPORTATION RESEARCH RECORD
(2021)
Article
Transportation Science & Technology
Da Yang, Yuezhu Wu, Feng Sun, Jing Chen, Donghai Zhai, Chuanyun Fu
Summary: In this study, a new method for accident detection and classification based on multi-vehicle trajectory data is proposed. A Deep Convolutional Neural Network model is developed to recognize an accident and classify its type, achieving high accuracy rates. The results indicate that this method outperforms existing methods using different data, providing a fast and accurate way to identify accidents and determine liability.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Engineering, Civil
Enrique D. Saldivar-Carranza, Howell Li, Saumabha Gayen, Mark Taylor, James Sturdevant, Darcy M. Bullock
Summary: Many agencies use Automated Traffic Signal Performance Measures (ATSPMs) to evaluate traffic signal efficiency. This paper analyzes the differences between traditional detector-based calculations and connected vehicle (CV)-based calculations of arrivals on green (AOG) at intersections in Utah. It is found that detector-based calculations tend to overestimate AOG in oversaturated conditions, while they can underestimate AOG in undersaturated scenarios with short queues. Therefore, CV trajectories should be used to measure AOG during periods with long queues, oversaturated conditions, or both.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Transportation Science & Technology
Zhen Yang, Yiheng Feng, Henry X. Liu
Summary: A cooperative driving framework was proposed for urban arterials, combining centralized and distributed control concepts to optimize signal timing plans and improve traffic flow. By utilizing a hierarchical model design and implementation-ready traffic control solutions, the study demonstrated both mobility and fuel economy benefits of the cooperative driving framework.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Engineering, Civil
Jihao Deng, Lei Gao, Xiaohong Chen, Quan Yuan
Summary: Traffic congestion is a major concern for policymakers in large cities worldwide. In order to combat congestion, individual-based active travel demand management (ATDM) has been proposed as a more efficient policy alternative. However, the factors influencing individuals' routing choices during commuting in response to ATDM incentives are still mostly unknown. By analyzing a desensitized one-week travel trajectory dataset of 5641 personal electric vehicles, this study identifies the major influencing factors of commuting route stability and provides suggestions for targeting responsive commuters. The findings contribute to the understanding of individual route choices and can help urban managers develop more refined ATDM policies to alleviate traffic congestion in the future.
Article
Transportation
Lei Wei, Peng Chen, Yu Mei, Jian Sun, Yunpeng Wang
Summary: This study proposed a hierarchical control framework based on vehicle trajectory data to alleviate network traffic bottleneck congestion. By tracing vehicle trajectories, the bottleneck-related sub-network (BRS) was identified and a multi-layered control approach was used to optimize traffic distribution and balance traffic pressure. Experimental results demonstrated the effectiveness of the framework in relieving network traffic congestion.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Economics
Songyot Kitthamkesorn, Anthony Chen, Seungkyu Ryu, Sathaporn Opasanon
Summary: The study introduces a new mathematical model to determine the optimal location of park-and-ride facilities, addressing the limitations of traditional models and considering factors such as route similarity and user heterogeneity.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2024)