Application of a Machine Learning–Based Sampling Method in Extreme Value Theory for Crash Risk Estimation of a Freeway Segment

Surrogate safety measures (SSM) have been used extensively in traffic safety studies for crash risk estimation. Most SSM-based studies employing extreme value theory (EVT) use the peak over threshold (POT) approach to detect anomalies or extreme events during safety-critical situations. This study investigated the efficacy of unsupervised machine learning (ML)-based anomaly detection methods as an extreme event sampling approach compared with the conventional POT sampling approach by developing bivariate EVT models for rear-end crash risk estimation on a freeway segment. Three widely used SSMs, namely time-to-collision (TTC), modified time-to-collision (MTTC), and deceleration rate to avoid crash (DRAC), were considered for the bivariate EVT modeling. Video data were collected from the selected segment of the I-40 expressway in Memphis, Tennessee. Among three SSMs, the combination of MTTC and DRAC bivariate EVT models provided the most accurate crash risk estimation (within the 99% confidence interval of the observed crashes), applying the traditional POT sampling approach, and ML-based isolation forest (iForest) and one-class support vector machine (OCSVM) sampling approaches. ML-based OCSVM sampling method provided a 21% crash estimation accuracy improvement over the POT and iForest sampling methods. Based on these findings, it can be concluded that unsupervised ML anomaly detection can be an effective sampling approach, reducing subjectivity in the threshold selection encountered in the POT sampling method. Safety improvement programs aim to maximize outcomes with limited resources, and an accurate estimation of the expected number of crashes helps engineers prioritize high-impact improvement locations.

• Publication year

  2025

• Venue

  Transportation Research Record

• Publication date

  2025-09-08

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1177/03611981251355511
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Assessing factors influencing the occurrence of traffic conflicts: a vehicle-by-vehicle approach

  2024cited by this paper
• A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond

  2023cited by this paper
• A conflict-based safety assessment technique for rear-end crash risk at signalized intersections in a lower-middle-income country: A comparison between homogeneous and heterogeneous traffic conditions

  2023cited by this paper
• Drivers’ Decision-Making When Experiencing a Traffic Conflict: A Scoping Review

  2023cited by this paper
• Assessing traffic conflict/crash relationships with extreme value theory: Recent developments and future directions for connected and autonomous vehicle and highway safety research

  2023influential reference
• Presentation of machine learning methods to determine the most important factors affecting road traffic accidents on rural roads

  2022cited by this paper
• How many are enough?: Investigating the effectiveness of multiple conflict indicators for crash frequency-by-severity estimation by automated traffic conflict analysis

  2022influential reference
• A hybrid modelling framework of machine learning and extreme value theory for crash risk estimation using traffic conflicts

  2022cited by this paper
• Transferability of multivariate extreme value models for safety assessment by applying artificial intelligence-based video analytics.

  2022cited by this paper
• Application of Bivariate Extreme Value models to describe the joint behavior of temporal and speed related surrogate measures of safety.

  2021influential reference
• Unsupervised outlier detection in multidimensional data

  2021cited by this paper
• Classifying travelers' driving style using basic safety messages generated by connected vehicles: Application of unsupervised machine learning

  2021cited by this paper
• A systematic review of traffic conflict-based safety measures with a focus on application context

  2021cited by this paper
• Investigating fatal and injury crash patterns of teen drivers with unsupervised learning algorithms

  2021cited by this paper
• A bivariate extreme value model for estimating crash frequency by severity using traffic conflicts

  2021cited by this paper
• A review of surrogate safety measures and their applications in connected and automated vehicles safety modeling.

  2021influential reference
• Multivariate Bayesian hierarchical modeling of the non-stationary traffic conflict extremes for crash estimation

  2020cited by this paper
• On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice

  2020cited by this paper
• On the use of clustering analysis for identification of unsafe places in an urban traffic network

  2020cited by this paper
• A bivariate Bayesian hierarchical extreme value model for traffic conflict-based crash estimation

  2020influential reference
• Comparison of Performance of Data Imputation Methods for Numeric Dataset

  2019cited by this paper
• Combining Statistical and Machine Learning Techniques in IoT Anomaly Detection for Smart Homes

  2019cited by this paper
• Validating the bivariate extreme value modeling approach for road safety estimation with different traffic conflict indicators.

  2019cited by this paper
• A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data.

  2019cited by this paper
• Comparison of Traffic Conflict Indicators for Crash Estimation using Peak Over Threshold Approach

  2019influential reference
• Evaluation Metrics for Unsupervised Learning Algorithms

  2019cited by this paper
• Automated Architecture Design for Deep Neural Networks

  2019cited by this paper
• From univariate to bivariate extreme value models: Approaches to integrate traffic conflict indicators for crash estimation

  2019influential reference
• Temporal instability and the analysis of highway accident data

  2018cited by this paper
• Unsupervised Learning

  2018cited by this paper
• Bivariate extreme value modeling for road safety estimation.

  2018influential reference
• Simple online and realtime tracking with a deep association metric

  2017cited by this paper
• A Piecewise Hybrid of ARIMA and SVMs for Short-Term Traffic Flow Prediction

  2017cited by this paper
• Hybrid traffic prediction scheme for intelligent transportation systems based on historical and real-time data

  2017cited by this paper
• ExtRemes 2.0: An extreme value analysis package in R

  2016cited by this paper
• Traffic conflict techniques for road safety analysis: open questions and some insights

  2014cited by this paper
• Surrogate safety measures as aid to driver assistance system design of the cognitive vehicle

  2014cited by this paper
• Modeling dependence between extreme rainfall and storm surge to estimate coastal flooding risk

  2014cited by this paper
• Freeway safety estimation using extreme value theory approaches: a comparative study.

  2014cited by this paper
• Crashes and crash-surrogate events: exploratory modeling with naturalistic driving data.

  2012cited by this paper
• Isolation-Based Anomaly Detection

  2012cited by this paper
• Estimation of rear-end vehicle crash frequencies in urban road tunnels.

  2012cited by this paper
• Use of crash surrogates and exceedance statistics to estimate road safety.

  2012influential reference
• Outline for a causal model of traffic conflicts and crashes.

  2011cited by this paper
• Near Crashes as Crash Surrogate for Naturalistic Driving Studies

  2010cited by this paper
• The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives

  2010cited by this paper
• Outliers detection with the minimum covariance determinant estimator in practice

  2009cited by this paper
• SURROGATE MEASURES OF SAFETY

  2009cited by this paper
• Probabilistic Framework for Automated Analysis of Exposure to Road Collisions

  2008cited by this paper
• Calibration and validation of simulated vehicle safety performance at signalized intersections.

  2008influential reference
• One class support vector machine for anomaly detection in the communication network performance data

  2007influential reference
• The extreme value theory approach to safety estimation.

  2006influential reference
• A comparison of headway and time to collision as safety indicators.

  2003cited by this paper
• An Introduction to Statistical Modeling of Extreme Values

  2001cited by this paper
• LOF: identifying density-based local outliers

  2000cited by this paper
• Bivariate extreme value theory: Models and estimation

  1988cited by this paper
• evd: Extreme Value Distributions

  year unknowncited by this paper

• No citing papers are available for this paper.