4.7 Article

Toward safer highway work zones: An empirical analysis of crash risks using improved safety potential field and machine learning techniques

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Information Systems

StrongSORT: Make DeepSORT Great Again

Yunhao Du et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2023)

Article Physics, Multidisciplinary

Real-time risk assessment model for multi-vehicle interaction of connected and autonomous vehicles in weaving area based on risk potential field

Yanli Ma et al.

Summary: To evaluate the operational risk of connected and autonomous vehicles (CAVs) in weaving areas, this study defines the 'multi-vehicle interaction risk potential field' based on the similarity between vehicle risk and potential field. A real-time risk assessment model is developed and a surrogate safety measure R is proposed. The model is validated by comparing R value and traffic conflict indicator (TTCi) in car-following and cut-in scenarios, showing that R can more effectively represent CAVs' operational risk during multi-vehicle interactions in weaving areas.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2023)

Article Engineering, Civil

Effect of Construction Work Zone on Rear-End Conflicts by Vehicle Type under Heterogeneous Traffic Conditions

Omkar Bidkar et al.

Summary: This study analyzes traffic safety by comparing the conflict probabilities in work zones (WZ) and regular sections. The analysis uses vehicle trajectory data and mathematical models to show that WZ sections have lower conflict probabilities, likely due to variations in speed and acceleration. The findings can assist highway authorities in implementing effective safety measures to reduce conflicts and accidents in work zones.

JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS (2023)

Article Transportation

Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model

Junhua Wang et al.

Summary: This study examines real-time crash prediction in freeway work zones using machine learning approaches. The Convolutional Neural Network performs slightly better than the Binary Logistic Regression model in crash prediction. However, the Binary Logistic Regression model is able to estimate the impact of affecting variables on the probability of crashes and identify factors related to risks in work zones.

INTERNATIONAL JOURNAL OF TRANSPORTATION SCIENCE AND TECHNOLOGY (2022)

Article Engineering, Civil

Dynamic Driving Risk Potential Field Model Under the Connected and Automated Vehicles Environment and Its Application in Car-Following Modeling

Linheng Li et al.

Summary: This paper proposes a new dynamic driving risk potential field model that considers the dynamic effect of a vehicle's acceleration and steering angle in the connected and automated vehicles (CAVs) environment. The simulation results show that the model accurately describes car-following behavior and outperforms other classical models in frequent oscillation phases. Additionally, the model is successfully used to deduce safety conditions for vehicle lane-changing.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Article Engineering, Electrical & Electronic

A novel method for calibration and verification of roadside millimetre-wave radar

Changlong Zhang et al.

Summary: The novel calibration method for roadside millimetre-wave radar uses high-definition maps and vehicle trajectory data to provide global positioning for radar detection targets, avoiding the dangers associated with traditional calibration methods. Experimental verification demonstrated that the proposed method meets lane-level precision requirements for V2X applications.

IET INTELLIGENT TRANSPORT SYSTEMS (2022)

Article Engineering, Civil

Safety Impact of Connected Vehicles on Driver Behavior in Rural Work Zones under Foggy Weather Conditions

Eric Adomah et al.

Summary: This study investigates the safety benefits of CV Work Zone Warning applications on driver behavior during foggy weather conditions. Results show that an increase in CV Market Penetration Rates enhances the safety performance of the work zone area, reducing crash risks under foggy conditions.

TRANSPORTATION RESEARCH RECORD (2022)

Article Ergonomics

A high-resolution trajectory data driven method for real-time evaluation of traffic safety

Yuping Hu et al.

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 Ergonomics

Application of explainable machine learning for real-time safety analysis toward a connected vehicle environment

Chen Yuan et al.

Summary: This research analyzes real-time safety through disaggregate study and explores the benefits of connected vehicles. Machine learning is used to obtain a reliable real-time safety model and the results show that the Random Forest model performs the best. The study also introduces explainable machine learning methods to improve model interpretability and reveals the impact of traffic flow features on real-time safety. The experimental results demonstrate that the model performance is enhanced with an increase in the CV Market Penetration Rate (CV-MPR).

ACCIDENT ANALYSIS AND PREVENTION (2022)

Article Public, Environmental & Occupational Health

A deep generative approach for crash frequency model with heterogeneous imbalanced data

Hongliang Ding et al.

Summary: A deep generative approach called augmented variational autoencoder is proposed to address the problem of imbalanced crash data. The approach generates synthetic crash data to measure the association between crashes and possible explanatory factors. The study uses comprehensive traffic and crash data from Hong Kong and compares the performance of the proposed method with a conventional data synthesis technique. The results indicate that the augmented variational autoencoder method performs better in terms of statistical fit, prediction accuracy, and identification of explanatory factors, especially for fatal and severe injury crashes. The study findings are important for the development of crash frequency models and provide insights for researchers and practitioners.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2022)

Article Physics, Multidisciplinary

Applying an interpretable machine learning framework to the traffic safety order analysis of expressway exits based on aggregate driving behavior data

Hang Qi et al.

Summary: In order to improve traffic safety, this study uses interpretable machine learning to analyze traffic order based on multi-source data. The results show that the XGBoost method can accurately predict traffic order levels and the congestion index has a significant impact on traffic order. Additionally, the number of lanes, advance guide signs, and weather conditions also have different effects on traffic order under different traffic conditions.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2022)

Article Environmental Sciences

Comparing Resampling Algorithms and Classifiers for Modeling Traffic Risk Prediction

Bo Wang et al.

Summary: Road infrastructure has a significant impact on road traffic safety, but predicting the traffic risk of different road sections remains a challenge. This study investigated a real-world expressway and developed a traffic crash risk prediction model using collected data from 2013 to 2020. The results showed that data balancing algorithms improved the performance of classifiers.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2022)

Review Ergonomics

A review of naturalistic driving study surrogates and surrogate indicator viability within the context of different road geometries

Jack Pinnow et al.

Summary: Advancements in data collection have led to vast vehicular databases, but identifying conventional vehicle collisions remains challenging due to their rarity. Surrogate indicators are commonly used to identify such events, with performance varying based on the data collection method and road geometry.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Article Ergonomics

Improved traffic safety at work zones through animation-based variable message signs

Mustafa Almallah et al.

Summary: The study demonstrated that the proposed VMS system led to speed reduction, early lane changing maneuvers, and larger headways between vehicles in work zones compared to the control condition. Participants in the VMS condition significantly reduced their traveling speeds and initiated lane changing maneuvers earlier than in the control condition. Additionally, the VMS system effectively encouraged drivers to keep larger headways with merging vehicles.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Review Engineering, Civil

Review of Methods for Estimating Construction Work Zone Capacity

Ali H. Mashhadi et al.

Summary: Road reconstruction and resulting work zones are major causes of traffic congestion on freeways. Accurate prediction of construction work zone capacity is essential for traffic engineers to estimate traffic flow characteristics. This paper provides a critical review of three approaches to estimating construction work zone capacities, presenting the most commonly considered factors and their frequency, as well as a detailed examination of the approaches, their objectives, and weaknesses, along with recommendations for future research. This work can assist researchers in the field of work zone capacity estimation by consolidating previous methodologies.

TRANSPORTATION RESEARCH RECORD (2021)

Article Engineering, Civil

Risk Evaluation for Conflicts between Crossing Pedestrians and Right-Turning Vehicles at Intersections

Feifei Xin et al.

Summary: The study proposed a quantitative method for evaluating the conflict risk between pedestrians and right-turning vehicles at intersections based on micro-level behavioral data obtained from video detection. Using MATLAB, several conflict indicators were extracted automatically to identify and classify conflicts, leading to the proposal of practical traffic management and control measures to reduce pedestrian crossing risks.

TRANSPORTATION RESEARCH RECORD (2021)

Review Ergonomics

A systematic mapping review of surrogate safety assessment using traffic conflict techniques

Ashutosh Arun et al.

Summary: The traditional reliance on police-reported crash data for road safety assessment has limitations, leading to the need for a unified framework to integrate surrogate safety assessment methodologies and conflict measures in order to better understand road user risk. (Word count: 331)

ACCIDENT ANALYSIS AND PREVENTION (2021)

Article Environmental Sciences

Improve Aggressive Driver Recognition Using Collision Surrogate Measurement and Imbalanced Class Boosting

Ke Wang et al.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2020)

Article Transportation Science & Technology

Probabilistic field approach for motorway driving risk assessment

Freddy A. Mullakkal-Babu et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Article Physics, Multidisciplinary

A novel lane-changing model of connected and automated vehicles: Using the safety potential field theory

Linheng Li et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2020)

Article Ergonomics

Risk perception and the warning strategy based on safety potential field theory

Linheng Li et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Article Ergonomics

Real-time conflict-based Bayesian Tobit models for safety evaluation of signalized intersections

Yanyong Guo et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Article Engineering, Civil

Real-Time Crash Risk Prediction using Long Short-Term Memory Recurrent Neural Network

Jinghui Yuan et al.

TRANSPORTATION RESEARCH RECORD (2019)

Article Ergonomics

A feature learning approach based on XGBoost for driving assessment and risk prediction

Xiupeng Shi et al.

ACCIDENT ANALYSIS AND PREVENTION (2019)

Article Computer Science, Information Systems

Construction and Simulation of Rear-End Conflicts Recognition Model Based on Improved TTC Algorithm

Huimin Ge et al.

IEEE ACCESS (2019)

Article Engineering, Civil

Effect of Adverse Weather Conditions on Vehicle Braking Distance of Highways

Ali Abdi Kordani et al.

CIVIL ENGINEERING JOURNAL-TEHRAN (2018)

Article Ergonomics

Time-varying mixed logit model for vehicle merging behavior in work zone merging areas

Jinxian Weng et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

Article Ergonomics

Key risk indicators for accident assessment conditioned on pre-crash vehicle trajectory

X. Shi et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

Article Ergonomics

Development of a lane change risk index using vehicle trajectory data

Hyunjin Park et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

Article Ergonomics

Analysis of passenger-car crash injury severity in different work zone configurations

Mohamed Osman et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

Article Engineering, Industrial

Effects of stationary work zones on motorway crashes

Francesca La Torre et al.

SAFETY SCIENCE (2017)

Proceedings Paper Computer Science, Information Systems

Data Management Challenges in Production Machine Learning

Neoklis Polyzotis et al.

SIGMOD'17: PROCEEDINGS OF THE 2017 ACM INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA (2017)

Article Transportation Science & Technology

Characteristics of lateral vehicular interactions in heterogeneous traffic with weak lane discipline

Anuj Kishor Budhkar et al.

JOURNAL OF MODERN TRANSPORTATION (2017)

Article Engineering, Civil

Modeling Vehicle Merging Behavior in Work Zone Merging Areas During the Merging Implementation Period

Jinxian Weng et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2016)

Article Transportation Science & Technology

Driving safety field theory modeling and its application in pre-collision warning system

Jianqiang Wang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2016)

Article Transportation Science & Technology

Large-scale automated proactive road safety analysis using video data

Paul St-Aubin et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2015)

Article Ergonomics

A tree-structured crash surrogate measure for freeways

Yan Kuang et al.

ACCIDENT ANALYSIS AND PREVENTION (2015)

Article Transportation Science & Technology

Effectiveness of graphic-aided portable changeable message signs in reducing vehicle speeds in highway work zones

Yilei Huang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2014)

Article Ergonomics

Analysis of work zone rear-end crash risk for different vehicle-following patterns

Jinxian Weng et al.

ACCIDENT ANALYSIS AND PREVENTION (2014)

Article Ergonomics

Modeling work zone crash frequency by quantifying measurement errors in work zone length

Hong Yang et al.

ACCIDENT ANALYSIS AND PREVENTION (2013)

Article Transportation Science & Technology

Time headway variable and probabilistic modeling

Duy-Hung Ha et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2012)

Article Ergonomics

Evaluation of rear-end crash risk at work zone using work zone traffic data

Qiang Meng et al.

ACCIDENT ANALYSIS AND PREVENTION (2011)

Article Engineering, Civil

A Taxonomy and Analysis of Camera Calibration Methods for Traffic Monitoring Applications

Neeraj K. Kanhere et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2010)

Article Engineering, Civil

Joint Merge and Its Impact on Merging Speeds in Lane Reduction Areas of Construction Zone

Wakeel I. A. Idewu et al.

TRANSPORTATION RESEARCH RECORD (2010)

Article Engineering, Civil

Highway Work Zone Risk Factors and Their Impact on Crash Severity

Yingfeng Li et al.

JOURNAL OF TRANSPORTATION ENGINEERING (2009)

Article Engineering, Civil

Replication of Work Zone Capacity Values in a Simulation Model

Indrajit Chatterjee et al.

TRANSPORTATION RESEARCH RECORD (2009)

Article Economics

Car following theory with lateral discomfort

Banihan Gunay

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL (2007)

Article Transportation Science & Technology

Modelling lane changing and merging in microscopic traffic simulation

P Hidas

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2002)