A better understanding of long-range temporal dependence of traffic flow time series

Feng, Shuo; Wang, Xingmin; Sun, Haowei; Zhang, Yi; Li, Li

doi:10.1016/j.physa.2017.10.006

Cited by 32 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, some scholars used MF-DFA to examine the highway traffic flow time series in Beijing, Shanghai and other places and discovered that the long-range dependence behavior is ubiquitous in time series of road traffic flows. Moreover, the length of the time scale was significantly impacted on the multifractal characteristics of traffic flow sequences [30][31][32].…”

Section: Literature Reviewmentioning

confidence: 99%

Long-Range Dependence and Multifractality of Ship Flow Sequences in Container Ports: A Comparison of Shanghai, Singapore, and Rotterdam

Liu

Jayetileke

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

The prediction of ship traffic flow is an important fundamental preparation for layout and design of ports as well as management of ship navigation. However, until now, the temporal characteristics and accurate prediction of ship flow sequence in port are rarely studied. Therefore, in this study, we investigated the presence of long-range dependence in container ship flow sequences using the Multifractal Detrended Fluctuation Analysis (MF-DFA). We considered three representative container ports in the world—including Shanghai, Singapore, and Rotterdam container ports—as the study sample, from 1 January 2013 to 31 December 2017. Empirical results suggested that the ship flow sequences are deviated from normal distribution, and the sequences with different time scales exhibited varying degrees of long-range dependence. Furthermore, the ship flow sequences possessed a multifractal nature, where the larger the time scale of ship flow time series, the stronger the multifractal characteristics are. The weekly ship flow sequence in the port of Singapore owned the highest degree of multifractality. Furthermore, the multifractality presented in the ship flow sequences of container ports are due to the correlation properties as well as the probability density function of the ship flow sequences. The study outlines the importance of adopting these features for an accurate modeling and prediction for maritime ship flow series.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Long-Range Dependence and Multifractality of Ship Flow Sequences in Container Ports: A Comparison of Shanghai, Singapore, and Rotterdam

Liu

Jayetileke

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Following the same notation as in Section 2, for a specific time-of-day (TOD), we represent the traffic volumes of d locations in N days by a matrix X ∈ R d×N , of which the element x ij represents the traffic volume at location i on day j. Many studies have shown that the traffic volume data have strong spatiotemporal correlations and contain low-rank structures (Qu et al, 2009;Tan et al, 2013;Coogan et al, 2017;Feng et al, 2018). We apply the PPCA model proposed by Tipping and Bishop (1999) and Roweis and Ghahramani (1999) to capture the low-rank structure of the traffic volume data.…”

Section: Distribution Of Whole-population Traffic Volumes Based On Th...mentioning

confidence: 99%

A probabilistic model for missing traffic volume reconstruction based on data fusion

Yan,

Zhao,

Liu

2021

Preprint

View full text Add to dashboard Cite

Traffic volume information is critical for intelligent transportation systems. It serves as a key input to transportation planning, roadway design, and traffic signal control. However, the traffic volume data collected by fixed-location sensors, such as loop detectors, often suffer from the missing data problem and low coverage problem. The missing data problem could be caused by hardware malfunction. The low coverage problem is due to the limited coverage of fixed-location sensors in the transportation network, which restrains our understanding of the traffic at the network level. To tackle these problems, we propose a probabilistic model for traffic volume reconstruction by fusing fixed-location sensor data and probe vehicle data. We apply the probabilistic principal component analysis (PPCA) to capture the correlations in traffic volume data. An innovative contribution of this work is that we also integrate probe vehicle data into the framework, which allows the model to solve both of the above-mentioned two problems. Using a real-world traffic volume dataset, we show that the proposed method outperforms state-of-the-art methods for the extensively studied missing data problem. Moreover, for the low coverage problem, which cannot be handled by most existing methods, the proposed model can also achieve high accuracy. The experiments also show that even when the missing ratio reaches 80%, the proposed method can still give an accurate estimate of the unknown traffic volumes with only 10% probe vehicle penetration rate. The results validate the effectiveness and robustness of the proposed model and demonstrate its potential for practical applications.

show abstract

“…There are also other models proposed to estimate the traffic state using the CV. Unlike the loop detector data, which is more convenient to use a Eulerian expression, the CV data can be directly used in the Lagrangian coordinates ( 15 ). Zheng et al proposed a stochastic traffic model in Lagrangian coordinates and used the Kalman filter to construct the complete trajectories using a fusion of detector and CV data ( 16 ).…”

Section: Potential Applicationsmentioning

confidence: 99%

Data Infrastructure for Connected Vehicle Applications

Wang

Shen

Bezzina

et al. 2020

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Ann Arbor Connected Vehicle Test Environment (AACVTE) is the world’s largest operational, real-world deployment of connected vehicles (CVs) and connected infrastructure, with over 2,500 vehicles and 74 infrastructure sites, including intersections, midblocks, and highway ramps. The AACVTE generates a massive amount of data on a scale not seen in the traditional transportation systems, which provides a unique opportunity for developing a wide range of connected vehicle (CV) applications. This paper introduces a data infrastructure that processes the CV data and provides interfaces to support real-time or near real-time CV applications. There are three major components of the data infrastructure: data receiving, data pre-processing, and visualization including the performance measurements generation. The data processing algorithms include signal phasing and timing (SPaT) data compression, lane phase mapping identification, trajectory data map matching, and global positioning system (GPS) coordinates conversion. Simple performance measures are derived from the processed data, including the time–space diagram, vehicle delay, and observed queue length. Finally, a web-based interface is designed to visualize the data. A list of potential CV applications including traffic state estimation, traffic control, and safety, which can be built on this connected data infrastructure is discussed.

show abstract

A better understanding of long-range temporal dependence of traffic flow time series

Cited by 32 publications

References 33 publications

Long-Range Dependence and Multifractality of Ship Flow Sequences in Container Ports: A Comparison of Shanghai, Singapore, and Rotterdam

Long-Range Dependence and Multifractality of Ship Flow Sequences in Container Ports: A Comparison of Shanghai, Singapore, and Rotterdam

A probabilistic model for missing traffic volume reconstruction based on data fusion

Data Infrastructure for Connected Vehicle Applications

Contact Info

Product

Resources

About