Traffic Volume Estimation in Multimodal Urban Networks Using Cell Phone Location Data

Xing, Jiping; Liu, Zhiyuan; Wu, Chunliang; Chen, Shuyan

doi:10.1109/mits.2019.2919593

Cited by 24 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we filtered out the significant influencing factors by Pearson correlation analysis. In pedestrian crash estimation, the Pearson correlation coefficient can be used to judge whether the variables changed along a trajectory, and then to determine the linear relationship between variables of a fixed distance type [ 44 ]. Before correlation analysis, the scatter plot can be drawn first, then the hypothesis of the correlation coefficient can be tested, the correlation coefficient between variables can be calculated, and the relationship between related variables can be described.…”

Section: Methodsmentioning

confidence: 99%

A Geographical and Temporal Risk Evaluation Method for Red-Light Violations by Pedestrians at Signalized Intersections: Analysis and Results of Suzhou, China

Xing

Zhang

Cheng

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Red-light violations of pedestrians crossing at signal intersections is one of the key factors in pedestrian traffic accidents. Even though there are various studies on pedestrian behavior and pedestrian traffic conflicts, few focus on the risk of different crosswalks for the violating pedestrian group. Due to the spatio-temporal nature of violation risk, this study proposes a geographical and temporal risk evaluation method for pedestrian red-light violations, which combines actual survey and video acquisition. First, in the geographical-based risk evaluation, the pedestrian violation rate at signal intersections is investigated by Pearson correlation analysis to extract the significant influencing factors from traffic conditions, built environment, and crosswalk facilities. Second, in the temporal-based risk evaluation, the survival analysis method is developed to quantify the risk of pedestrian violation in different scenarios as time passes by. Finally, this study selects 16 typical signalized intersections in Suzhou, China, with 881 pedestrian crosswalk violations from a total size of 4586 pedestrians as survey cases. Results indicate that crossing distance, traffic volume on the crosswalk, red-light time, and crosswalk-type variables all contribute to the effect of pedestrian violation from a geographical perspective, and the installation of waiting refuge islands has the most significant impact. From the temporal perspective, the increases in red-light time, number of lanes, and traffic volume have a mitigating effect on the violations with pedestrian waiting time increases. This study aims to provide a development-oriented path by proposing an analytical framework that reconsiders geographical and temporal risk factors of violation. The findings could help transport planners understand the effect of pedestrian violation-related traffic risk and develop operational measures and crosswalk design schemes for controlling pedestrian violations occurring in local communities.

show abstract

Section: Methodsmentioning

confidence: 99%

A Geographical and Temporal Risk Evaluation Method for Red-Light Violations by Pedestrians at Signalized Intersections: Analysis and Results of Suzhou, China

Xing

Zhang

Cheng

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“… Source: author’s own collaboration based on [ 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 ]. …”

Section: Literature Review: New Mobility Business Modelsmentioning

confidence: 99%

Business Innovations in the New Mobility Market during the COVID-19 with the Possibility of Open Business Model Innovation

Turoń

Kubik

2021

Journal of Open Innovation: Technology, Market, and Complexity

View full text Add to dashboard Cite

The current difficult situation in the world caused by the spread of the COVID-19 virus has led to the development of problems in many branches of the economy. However, it has significantly affected transport, which on the one hand, is the bloodstream of the economy and, on the other hand, creates a threat for virus infection. Thus, in various countries, different mobility-related restrictions during pandemic policies around the world have been introduced. What is more, plans for initiatives after lockdown have also started to appear. Moreover, not have only cities introduced appropriate management policies, but companies have also started providing logistics services, especially those offering new mobility solutions. We found a literature and research gap indicating the recording or combination of the different types of business practices and innovations used worldwide in new mobility companies in the case of a pandemic situation. Therefore, this article is dedicated to the business innovations that appear in the new mobility industry during the COVID-19 pandemic in connection to post-pandemic transportation plans in Asia, Europe, and America. In this work, we conducted two-level research based on the desk research and expert research methodologies. From the business point of view, the results show that car-sharing systems (most organizational practices) and ride-sharing services (most safety practices) have most adapted their business models to pandemic changes. In turn, bike-sharing services have implemented the fewest business practices and innovations. From the urban transport systems point of view, the results show that European authorities have proposed the most plans and practice projects for new mobility after the pandemic compared to Asia and America. The obtained results indicate, however, that business practices do not coincide with the authorities’ plans for transport after the pandemic. Moreover, the results show a lack of complementarity between the developed practices and a reluctance to create open innovations in the new mobility industry. The article supports the management of new mobility systems in times of pandemic and in post-COVID reality.

show abstract

“…These solutions are not efficient due to coverage limitations and effort required in terms of installation and maintenance. To cope with these problems [2,8,10,12,18,22,23] propose the use of mobile subscriber data in traffic flow estimation. In [8,10,18] the cell dwelling time and global positioning system (GPS) coordinates of a mobile subscriber are used to estimate the traffic congestion.…”

Section: Related Workmentioning

confidence: 99%

“…With today's heavy usage of streaming and social media services however, voice calls are hardly representative of the traffic density, which limits the accuracy of such an approach. The authors in [23] use the travel trajectory of different mobile subscribers to detect in-vehicle users and henceforth compute the number of vehicles on a specific road. Tracking individual mobile users however is highly contentious and in most countries any user-identifiable or user-sensitive information limits the real-time usage of such data.…”

Section: Related Workmentioning

confidence: 99%

Traffic Flow Estimation using LTE Radio Frequency Counters and Machine Learning

Yaghoubi¹,

Catovic²,

Gusmao³

et al. 2021

Preprint

View full text Add to dashboard Cite

As the demand for vehicles continues to outpace construction of new roads, it becomes imperative we implement strategies that improve utilization of existing transport infrastructure. Traffic sensors form a crucial part of many such strategies, giving us valuable insights into road utilization. However, due to cost and lead time associated with installation and maintenance of traffic sensors, municipalities and traffic authorities look toward cheaper and more scalable alternatives. Due to their ubiquitous nature and wide global deployment, cellular networks offer one such alternative. In this paper we present a novel method for traffic flow estimation using standardized LTE/4G radio frequency performance measurement counters. The problem is cast as a supervised regression task using both classical and deep learning methods. We further apply transfer learning to compensate that many locations lack traffic sensor data that could be used for training. We show that our approach benefits from applying transfer learning to generalize the solution not only in time but also in space (i.e., various parts of the city). The results are very promising and, unlike competing solutions, our approach utilizes aggregate LTE radio frequency counter data that is inherently privacy-preserving, readily available, and scales globally without any additional network impact.

show abstract

Traffic Volume Estimation in Multimodal Urban Networks Using Cell Phone Location Data

Cited by 24 publications

References 22 publications

A Geographical and Temporal Risk Evaluation Method for Red-Light Violations by Pedestrians at Signalized Intersections: Analysis and Results of Suzhou, China

A Geographical and Temporal Risk Evaluation Method for Red-Light Violations by Pedestrians at Signalized Intersections: Analysis and Results of Suzhou, China

Business Innovations in the New Mobility Market during the COVID-19 with the Possibility of Open Business Model Innovation

Traffic Flow Estimation using LTE Radio Frequency Counters and Machine Learning

Contact Info

Product

Resources

About