Article
Green & Sustainable Science & Technology
Xiaofeng Lou, Changhai Peng
Summary: Integrated transportation system planning is crucial for the future development of transportation, and utilizing big data technology to analyze traffic data is a new trend in urban traffic planning.
ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY
(2022)
Article
Computer Science, Information Systems
Zhibing Yang, Zhiqiang Xie, Zhiqun Hou, Chunhou Ji, Zhanting Deng, Rong Li, Xiaodong Wu, Lei Zhao, Shu Ni
Summary: As urbanization accelerates, traffic congestion in cities has become a problem. In this study, a CNN approach based on multichannel feature extraction using mobile phone signaling data was proposed to accurately identify urban residents' travel patterns. Experimental results using mobile phone signaling and field research data in Kunming, China showed that the method achieved an accuracy of 84.7%. This method provides a feasible way of identifying travel patterns in the context of smart cities and big data, supporting urban transport planning and management.
Article
Green & Sustainable Science & Technology
Qiang Liu, Jianguang Xie, Fan Ding
Summary: This article introduces a data-driven feature-based learning application utilizing mobile phone data to detect segment traffic status. The application, evaluated through a large-scale field experiment using actual data in Jiangsu, China, performed well and can be considered as an emerging solution for traffic state monitoring.
Article
Ergonomics
Tong Liu, Zhibin Li, Pan Liu, Chengcheng Xu, David A. Noyce
Summary: This study evaluated crash risks in different traffic phases based on surrogate safety measures and vehicle trajectory data. Synchronized flow and wide moving jam were identified as the most dangerous phases, while high density and low speed were associated with high crash risk. The best crash risk prediction performance was achieved by integrating traffic phases and parameters.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Green & Sustainable Science & Technology
Madhar M. M. Taamneh, Salah Taamneh, Ahmad H. H. Alomari, Musab Abuaddous
Summary: Distracted driving, mainly caused by smartphone use, is a significant factor in road crashes worldwide. Machine learning techniques, such as oversampling and undersampling, are effective in identifying the main factors behind this behavior, despite the imbalanced data. The results showed that ID3, J48, and MLP methods outperformed other ML methods, and DL methods performed well on undersampled data. Road classification, driver age group, driver gender, vehicle type, and driver seatbelt usage were identified as factors influencing cell phone use.
Article
Green & Sustainable Science & Technology
Linlin Wu, Guangming Shou, Zaichun Xie, Peng Jing
Summary: Due to their wide coverage, low acquisition cost, and large data quantity, mobile phone signaling data are suitable for fine-grained and large-scale estimation of traffic conditions. However, the high level of data noise makes it difficult to achieve accurate estimation. This paper proposes an improved density peak clustering algorithm (DPCA) to filter data noise and establishes a traffic state estimation model based on mobile phone feature data using denoising data and the long short-term memory model (LSTM).
Article
Environmental Studies
Zhenghong Peng, Guikai Bai, Hao Wu, Lingbo Liu, Yang Yu
Summary: This study introduces a method to recognize the travel mode of urban residents using big data such as mobile phone data, by analyzing important location points and travel trajectories, utilizing an online map API to analyze means of travel, and comparing the two. The method can be applied in GIS platform to obtain traffic flow of various means during peak hours, and has potential for applications in urban planning and traffic management.
ENVIRONMENT AND PLANNING B-URBAN ANALYTICS AND CITY SCIENCE
(2021)
Article
Mathematics, Interdisciplinary Applications
Chen Zhao, An Zeng, Chi Ho Yeung
Summary: The study re-examined human mobility patterns using comprehensive cell-phone position data and found that individuals exhibit origin-dependent and path-preferential patterns in their short time-scale mobility. These behaviors are more prominent with higher temporal resolution data, but have been overlooked in most previous studies.
Article
Environmental Studies
Liang Ding, Ziqian Huang, Chaowei Xiao
Summary: Urban planning has a significant impact on human spatial activities, but existing evaluation methods often neglect the role of people and their demands. This study analyzes the spatial pattern of employment in Changchun, China and evaluates the implementation effect of employment space in the master plan using human activity patterns. The results highlight the need for post-implementation evaluation of urban planning, and the importance of utilizing big data to assess whether the plan has achieved its goals.
Article
Chemistry, Multidisciplinary
Hong Xu, Jin Zhao
Summary: Based on the analysis of cell phone data, this paper proposes a method to mine the travel characteristics of residents and the regional traffic connections, and suggests a modification plan for urban road network planning. The study discovers a spatial development pattern of traffic connections in Wuxue city and provides a new approach to obtain spatio-temporal information for urban road planning using cell phone data.
APPLIED SCIENCES-BASEL
(2022)
Article
Ergonomics
Yuping Hu, Ye Li, Helai Huang, Jaeyoung Lee, Chen Yuan, Guoqing Zou
Summary: This paper proposes a method for real-time evaluation of road safety based on high-resolution trajectory data, which combines traffic states and conflicts to explore the internal relationship. Machine learning methods are applied for real-time evaluation. The results show that the proposed method can accurately estimate conflict risk, contributing to the improvement of real-time traffic safety and safety management.
ACCIDENT ANALYSIS AND PREVENTION
(2022)
Article
Green & Sustainable Science & Technology
Bingsheng Huang, Fusheng Zhang
Summary: With the increase in travel demands, the air pollution caused by transportation, especially traffic congestion, is becoming more serious. This paper proposes a method for effectively analyzing and identifying oversaturation states, which has important implications for alleviating traffic congestion and reducing vehicle carbon emissions.
Article
Environmental Sciences
Bing He, Jinxing Hu, Kang Liu, Jianzhang Xue, Li Ning, Jianping Fan
Summary: Exploring the characteristics of park visitors and the factors influencing their mobility is crucial for managing urban parks. In this study, we analyzed data from 56 parks in Shenzhen in 2019. The results showed significant variations in recreational activities among different population subgroups, with older adults and teenagers traveling shorter distances and making fewer trips compared to younger adults. The functional layout of the built environment around the parks was found to impact recreational trips, with areas rich in urban functions attracting more visitors. Furthermore, remote sensing data on urban vegetation proved to be an effective factor in characterizing park attractiveness. The integration of human activity and remote sensing data provides a comprehensive understanding of urban park use and preferences, which is important for future park planning.
Article
Ergonomics
Marco H. Benedetti, Li Li, Sijun Shen, Neale Kinnear, M. Kit Delgado, Motao Zhu
Summary: This study examines the association between handheld phone bans and self-reported talking on hands-free and handheld cellphones while driving. The findings suggest that handheld bans are associated with less talking on handheld phones and more talking on hands-free phones.
JOURNAL OF SAFETY RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoyi Jia, Xiaoyu Dong, Meng Chen, Xiaohui Yu
Summary: This paper proposes a novel Imputation Model for traffic Congestion data, CIM, based on joint matrix factorization to estimate missing congestion values. Experimental results show that modeling the periodicity, road similarity, and temporal coherence of congestion patterns simultaneously is effective.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Civil
Shuo Feng, Yiheng Feng, Haowei Sun, Yi Zhang, Henry X. Liu
Summary: A customized testing scenario library for a specific CAV model is generated through an adaptive process to compensate for the performance dissimilarities and leverage each test of the CAV.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Yiheng Feng, Shihong Ed Huang, Wai Wong, Qi Alfred Chen, Z. Morley Mao, Henry X. Liu
Summary: This study proposes a comprehensive analysis framework to address the cybersecurity problem in the traffic signal control system with connected vehicle technology. A case study is conducted to demonstrate the impact of data spoofing attacks and the corresponding mitigation measures.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Editorial Material
Energy & Fuels
Arno Eichberger, Zsolt Szalay, Martin Fellendorf, Henry Liu
Article
Engineering, Civil
Zachary Jerome, Xingmin Wang, Shengyin Shen, Henry X. Liu
Summary: This paper evaluates the new guidelines for traffic signal intervals published by ITE and proposes a new kinematic equation based on observed vehicle trajectories. The study finds that the previous equation overestimates the required duration for left-turning vehicles due to its assumptions about deceleration timing and rate. The proposed equation provides a more accurate estimation of yellow change and clearance intervals.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Engineering, Civil
Yan Zhao, Wai Wong, Jianfeng Zheng, Henry X. Liu
Summary: This paper proposes a maximum likelihood estimation method for queue length estimation using historical probe vehicle data, solved iteratively by the EM algorithm. Validation results show that the method can accurately estimate the parameters, enabling cycle by cycle estimation of queue lengths.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Operations Research & Management Science
Xiaozheng He, Jian Wang, Srinivas Peeta, Henry X. Liu
Summary: This paper presents a discrete day-to-day signal retiming problem to fine-tune the green splits in a traffic network and reduce congestion and travel time.
NETWORKS & SPATIAL ECONOMICS
(2022)
Article
Transportation Science & Technology
Xingmin Wang, Yafeng Yin, Yiheng Feng, Henry X. Liu
Summary: This study proposes a new framework for max pressure control using reinforcement learning algorithms, considering phase switching loss and optimizing parameters. Simulation results show that the proposed control method outperforms traditional max pressure control. This research is of great significance for real-world implementations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Engineering, Civil
Rusheng Zhang, Zhengxia Zou, Shengyin Shen, Henry X. Liu
Summary: This paper introduces a newly developed and deployed roadside cooperative perception system with an edge-cloud structure and multiple kinds of sensors. The performance of the system is analyzed using data collected from the field, and its potential in applications such as traffic volume monitoring and road safety warning is demonstrated.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Transportation Science & Technology
Jun Hua, Guangquan Lu, Henry X. Liu
Summary: This study establishes a driving behavior model framework to explain drivers' approaching behaviors to signalized intersections, and obtains probabilities and distributions through simulations. The results demonstrate the validity of the proposed model and its applicability to drivers with different desired risks.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Engineering, Civil
Xingmin Wang, Zachary Jerome, Chenhao Zhang, Shengyin Shen, Vivek Vijaya Kumar, Henry X. Liu
Summary: This paper proposes a trajectory data processing pipeline for urban traffic network applications, which includes matching, splitting, and distance extraction steps, as well as smoothing and filtering algorithms to reduce noise and errors. The processed data is used to calculate various mobility performance indices for comprehensive evaluations. The proposed methods are efficient, robust, and scalable, and can be applied to large-scale urban traffic networks.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Multidisciplinary Sciences
Shuo Feng, Haowei Sun, Xintao Yan, Haojie Zhu, Zhengxia Zou, Shengyin Shen, Henry X. Liu
Summary: A critical bottleneck for autonomous vehicle development and deployment is the high costs required to validate safety in real-world driving. Researchers have developed an intelligent testing environment using AI-based agents to accelerate the safety validation process without bias. Their approach reduces testing time by orders of magnitude and can also be applied to other safety-critical autonomous systems.
Article
Engineering, Civil
Zhen Yang, Rusheng Zhang, Gaurav Pandey, Neda Masoud, Henry X. Liu
Summary: This work proposes a hierarchical vehicle behavior prediction framework that incorporates traffic signal information and models the interaction between vehicles. The framework predicts vehicle behaviors in two stages: discrete intention prediction and continuous trajectory prediction. It is designed to capture the difference among human drivers with parameterized driver characteristics.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Zhen Yang, Jun Ying, Junjie Shen, Yiheng Feng, Qi Alfred Chen, Z. Morley Mao, Henry X. Liu
Summary: This paper proposes a method to detect GPS spoofing attacks on connected vehicles (CVs) and autonomous vehicles (AVs) using domain knowledge in transportation and vehicle engineering. A computational-efficient driving model is constructed by learning from historical trajectories, and a statistical method is developed to measure the dissimilarities between observed and predicted trajectories for anomaly detection. The proposed method is validated on real-world datasets and shown to detect almost all attacks with low false positive and false negative rates.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yujie Feng, Jiangtao Wang, Yasha Wang, Xu Chu
Summary: As a crucial part of public health system, population health monitoring plays a significant role in shaping health policies. However, the high cost of traditional data collection methods has led to the proposal of sparse-sampling-completion algorithms. Existing data-completion methods primarily focus on adjacent-spatial correlations, which may not accurately infer missing prevalence data in neighboring areas due to cost constraints. To address this problem, we propose a novel deep-learning-based prevalence inference model, SDA-GAIN (Spatial-attention and Demographic-augmented Generative Adversarial Imputation Network), which improves accuracy by learning health semantic space similarities between cross-space areas. SDA-GAIN utilizes a Transformer-based model to learn healthy semantic similarities and a GAN-based model for high-accuracy completion, with the addition of demographic data to enhance the model's ability in learning better health semantic representation through CNN. Extensive experiments demonstrate that SDA-GAIN outperforms other state-of-the-art approaches at low sampling rates (<30%), leading to significant cost savings. Moreover, the visualization of health semantic similarity learned by SDA-GAIN closely resembles real-life situations.
IEEE TRANSACTIONS ON BIG DATA
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Jingxuan Yang, Honglin He, Yi Zhang, Shuo Feng, Henry X. Liu
Summary: This paper proposes an adaptive testing method using sparse control variates, which evaluates the performance of CAVs by adaptively utilizing testing results. It reduces estimation variance by adjusting testing results based on multiple linear regression techniques and optimizes regression coefficients for the CAV under test. The method applies sparse control variates to critical variables of testing scenarios and has been validated in high-dimensional overtaking scenarios, achieving a 30 times acceleration in the evaluation process.
2022 IEEE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2022)
