☆ 4.6 Article

A hybrid modelling framework of machine learning and extreme value theory for crash risk estimation using traffic conflicts

ANALYTIC METHODS IN ACCIDENT RESEARCH (2022)

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 Engineering, Civil

Assessing a Connected Environment's Safety Impact During Mandatory Lane-Changing: A Block Maxima Approach

Yasir Ali et al.

Summary: This study uses an Extreme Value Theory approach to estimate and compare crash risk during mandatory lane-changing manoeuvres in connected and traditional environments. The results show that crash risk is significantly reduced in the connected environment, especially in the perfect communication condition.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2023)

添加到收藏夹

Article Transportation Science & Technology

How many are enough?: Investigating the effectiveness of multiple conflict indicators for crash frequency-by-severity estimation by automated traffic conflict analysis

Ashutosh Arun et al.

Summary: Traffic conflict techniques provide a viable alternative for assessing safety in emerging technologies with limited crash data. This study explores the benefits of using multiple conflict indicators and finds that careful selection of compatible indicators, rather than increasing their number, enhances the predictive performance of conflict-based models.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

添加到收藏夹

Article Ergonomics

Transferability of multivariate extreme value models for safety assessment by applying artificial intelligence-based video analytics

Ashutosh Arun et al.

Summary: This study investigates the transferability of multivariate peak-over threshold models for estimating crash frequency-by-severity. Two transferability approaches are proposed and compared. Results show that the threshold calibration approach provides the most accurate and precise predictions of crash frequency-by-severity for target sites.

ACCIDENT ANALYSIS AND PREVENTION (2022)

添加到收藏夹

Article Public, Environmental & Occupational Health

An Extreme Value Theory approach to estimate crash risk during mandatory lane-changing in a connected environment

Yasir Ali et al.

Summary: This study examines and quantifies mandatory lane-changing crash risk in traditional and connected environments using an Extreme Value Theory approach. Findings indicate that the connected environment significantly reduces crash risk compared to the baseline condition, with the highest risk reduction observed in the perfect communication condition. The study also confirms the veracity of Peak Over Threshold models in estimating crash risk using traffic conflict data.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

NaNOD: A natural neighbour-based outlier detection algorithm

Abdul Wahid et al.

Summary: Outlier detection is a crucial task in data mining applications. A new unsupervised density-based outlier detection algorithm is proposed in this study to address the weaknesses of existing algorithms. By utilizing adaptive parameter acquisition and weighted kernel density estimation, along with two types of nearest neighbors and Gaussian kernel function, the proposed algorithm demonstrates improved outlier detection performance.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Ergonomics

Validating the Bayesian hierarchical extreme value model for traffic conflict-based crash estimation on freeway segments with site-level factors

Lai Zheng et al.

Summary: This study validates a Bayesian hierarchical extreme value model for crash estimation from traffic conflicts, demonstrating that including site-level factors improves model performance. Results show that traffic volume, segment length, and grade are significant factors negatively impacting lane change safety on freeway segments.

ACCIDENT ANALYSIS AND PREVENTION (2021)

添加到收藏夹

Article Ergonomics

Random parameters Bayesian hierarchical modeling of traffic conflict extremes for crash estimation

Chuanyun Fu et al.

Summary: The study proposes a random parameters Bayesian hierarchical extreme value modeling approach to estimate rear-end crashes from traffic conflicts, demonstrating superior accuracy and precision compared to other methods. This superiority may be attributed to the RP model's ability to better account for unobserved heterogeneity.

ACCIDENT ANALYSIS AND PREVENTION (2021)

添加到收藏夹

Article Ergonomics

Multi-type Bayesian hierarchical modeling of traffic conflict extremes for crash estimation

Chuanyun Fu et al.

Summary: This study proposes a multi-type Bayesian hierarchical extreme value modeling approach, which can accurately estimate the crashes caused by traffic conflicts. Compared to single-type models, the standard errors of parameters in the multi-type model are smaller, resulting in more accurate crash estimates.

ACCIDENT ANALYSIS AND PREVENTION (2021)

添加到收藏夹

Article Public, Environmental & Occupational Health

Stop or go decisions at the onset of yellow light in a connected environment: A hybrid approach of decision tree and panel mixed logit model

Yasir Ali et al.

Summary: This study examines driver decisions at the onset of yellow traffic lights when they are assisted with advance information about traffic light changes. The analysis shows that drivers in the connected environment are less likely to proceed through intersections at the onset of yellow light compared to the baseline condition. However, at the individual driver-level, the impact of the connected environment on driver decisions is mixed, with female drivers found to have a higher propensity for yellow light running in the connected environment than male drivers.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

An extreme value theory based approach for calibration of microsimulation models for safety analysis

Yanyong Guo et al.

Summary: This study proposes an innovative calibration approach for microsimulation models using extreme value theory (EVT) and Genetic algorithm to match the extreme value distribution of simulated conflicts with field-measured conflicts. The results show considerable matching of estimated GP distributions between simulated conflicts and field-measured conflicts, recommending this approach for simulation-based safety evaluation of signalized intersections.

SIMULATION MODELLING PRACTICE AND THEORY (2021)

添加到收藏夹

Article Public, Environmental & Occupational Health

A bivariate extreme value model for estimating crash frequency by severity using traffic conflicts

Ashutosh Arun et al.

Summary: Estimating crash frequency by severity levels using traffic conflicts is relatively unexplored, but this study fills the gap by jointly modeling crash frequency indicators and crash severity indicators with bivariate Extreme Value method, demonstrating superior statistical fit and precise estimations. The study reveals that the bivariate approach is more advantageous than the univariate approach, and combining TTC and MTTC indicators with Delta-V provides comparable results in predicting crash frequencies by severity levels. Sharing information between similar traffic sites improves the accuracy and precision of prediction.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2021)

添加到收藏夹

Article Computer Science, Theory & Methods

Unsupervised outlier detection in multidimensional data

Atiq Ur Rehman et al.

Summary: The paper proposes novel statistical techniques for detecting outliers in a dataset, which are shown to be efficient in terms of performance, ease of implementation, and computational complexity. Additionally, the use of transforming data to a unidimensional distance space for outlier detection allows for computational efficiency and feasibility even in high-dimensional datasets.

JOURNAL OF BIG DATA (2021)

添加到收藏夹

Article Ergonomics

Comparison of threshold determination methods for the deceleration rate to avoid a crash (DRAC)-based crash estimation

Chuanyun Fu et al.

Summary: There is a growing interest in using traffic conflicts as a surrogate measure for safety, with the deceleration rate to avoid a crash (DRAC) being one of the indicators. This study aims to compare different threshold determination approaches for DRAC-based crash estimation using Bayesian hierarchical extreme value modeling, with a focus on the truncated normal distribution N(8.45, 1.4(2))I(4.23, 12.68) of the maximum available deceleration rate (MADR) which outperforms other methods in terms of accuracy and precision.

ACCIDENT ANALYSIS AND PREVENTION (2021)

添加到收藏夹

Article Transportation Science & Technology

A novel approach for real time crash prediction at signalized intersections

Lai Zheng et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

添加到收藏夹

Article Environmental Sciences

Analyzing Factors Associated with Fatal Road Crashes: A Machine Learning Approach

Ali J. Ghandour et al.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2020)

添加到收藏夹

Article Transportation Science & Technology

Comparing the usefulness of real-time driving aids in a connected environment during mandatory and discretionary lane-changing manoeuvres

Yasir Ali et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

添加到收藏夹

Article Public, Environmental & Occupational Health

Multivariate Bayesian hierarchical modeling of the non-stationary traffic conflict extremes for crash estimation

Chuanyun Fu et al.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2020)

添加到收藏夹

Article Public, Environmental & Occupational Health

A bivariate Bayesian hierarchical extreme value model for traffic conflict-based crash estimation

Lai Zheng et al.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2020)

添加到收藏夹

Article Public, Environmental & Occupational Health

Is an informed driver a better decision maker? A grouped random parameters with heterogeneity-in-means approach to investigate the impact of the connected environment on driving behaviour in safety-critical situations

Anshuman Sharma et al.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2020)

添加到收藏夹

Article Engineering, Civil

Comparison of Traffic Conflict Indicators for Crash Estimation using Peak Over Threshold Approach

Lai Zheng et al.

TRANSPORTATION RESEARCH RECORD (2019)

添加到收藏夹

Article Transportation Science & Technology

From univariate to bivariate extreme value models: Approaches to integrate traffic conflict indicators for crash estimation

Lai Zheng et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2019)

添加到收藏夹

Article Transportation

Collision prediction in roundabouts: a comparative study of extreme value theory approaches

Federico Orsini et al.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2019)

添加到收藏夹

Article Ergonomics

A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data

Chen Wang et al.

ACCIDENT ANALYSIS AND PREVENTION (2019)

添加到收藏夹

Article Ergonomics

Validating the bivariate extreme value modeling approach for road safety estimation with different traffic conflict indicators

Lai Zheng et al.

ACCIDENT ANALYSIS AND PREVENTION (2019)

添加到收藏夹

Article Public, Environmental & Occupational Health

Bayesian hierarchical modeling of traffic conflict extremes for crash estimation: A non-stationary peak over threshold approach

Lai Zheng et al.

ANALYTIC METHODS IN ACCIDENT RESEARCH (2019)

添加到收藏夹

Article Ergonomics

Applying machine learning approaches to analyze the vulnerable road-users' crashes at statewide traffic analysis zones

Md Sharikur Rahman et al.

JOURNAL OF SAFETY RESEARCH (2019)

添加到收藏夹

Article Transportation Science & Technology

A combined use of microscopic traffic simulation and extreme value methods for traffic safety evaluation

Chen Wang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

添加到收藏夹

Article Ergonomics

Bivariate extreme value modeling for road safety estimation

Lai Zheng et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Using Extreme Value Theory for Vehicle Level Safety Validation and Implications for Autonomous Vehicles

Daniel Asljung et al.

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES (2017)

添加到收藏夹

Article Transportation

16 Safety analysis of passing maneuvers using extreme value theory

Haneen Farah et al.

IATSS RESEARCH (2017)

添加到收藏夹

Article Engineering, Civil

Investigating the Heterogeneity of Postencroachment Time Thresholds Determined by Peak over Threshold Approach

Lai Zheng et al.

TRANSPORTATION RESEARCH RECORD (2016)

添加到收藏夹

Article Ergonomics

Decisions and actions of distracted drivers at the onset of yellow lights

Md. Mazharul Haque et al.

ACCIDENT ANALYSIS AND PREVENTION (2016)

添加到收藏夹

Article Transportation

Evaluation of Peak Over Threshold Approach for Road Safety Estimation

Lai Zheng et al.

JOURNAL OF TRANSPORTATION SAFETY & SECURITY (2015)

添加到收藏夹

Article Ergonomics

Freeway safety estimation using extreme value theory approaches: A comparative study

Lai Zheng et al.

ACCIDENT ANALYSIS AND PREVENTION (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Ensemble based sensing anomaly detection in wireless sensor networks

Daniel-Ioan Curiac et al.

EXPERT SYSTEMS WITH APPLICATIONS (2012)

添加到收藏夹

Article Computer Science, Information Systems

Isolation-Based Anomaly Detection

Fei Tony Liu et al.

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA (2012)

添加到收藏夹

Article Ergonomics

Use of crash surrogates and exceedance statistics to estimate road safety

Andrew P. Tarko

ACCIDENT ANALYSIS AND PREVENTION (2012)

添加到收藏夹

Article Ergonomics

Analyzing angle crashes at unsignalized intersections using machine learning techniques

Mohamed Abdel-Aty et al.

ACCIDENT ANALYSIS AND PREVENTION (2011)

添加到收藏夹

Article Ergonomics

Outline for a causal model of traffic conflicts and crashes

Gary A. Davis et al.

ACCIDENT ANALYSIS AND PREVENTION (2011)

添加到收藏夹

Article Engineering, Civil

Multiple Applications of Multivariate Adaptive Regression Splines Technique to Predict Rear-End Crashes at Unsignalized Intersections

Kirolos Haleem et al.

TRANSPORTATION RESEARCH RECORD (2010)

添加到收藏夹

Article Computer Science, Information Systems

Distance-Based Outlier Detection: Consolidation and Renewed Bearing

Gustavo H. Orair et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2010)

添加到收藏夹

Review Statistics & Probability

Minimum covariance determinant

Mia Hubert et al.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS (2010)

添加到收藏夹

Article Computer Science, Theory & Methods

Anomaly detection

Varun Chandola et al.

ACM COMPUTING SURVEYS (2009)

添加到收藏夹

Article

Outliers detection with the minimum covariance determinant estimator in practice

C. Fauconnier et al.

Statistical Methodology (2009)

添加到收藏夹

Article Engineering, Civil

Derivation and Validation of New Simulation-Based Surrogate Safety Measure

Kaan Ozbay et al.

TRANSPORTATION RESEARCH RECORD (2008)

添加到收藏夹

Article Ergonomics

The extreme value theory approach to safety estimation

Praprut Songchitruksa et al.

ACCIDENT ANALYSIS AND PREVENTION (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.