01476159

Component

https://doi.org/10.3141/2386-04

http://scholar.google.com...-Aty&publication_year=2013

This study proposes a new and promising machine learning technique to enhance the reliability of real-time risk assessment on freeways. Stochastic gradient boosting (SGB) is used to identify hazardous conditions on the basis of traffic data collected from multiple detection systems such as automatic vehicle identification (AVI), remote traffic microwave sensors (RTMS), real-time weather stations, and roadway geometry. SGB’s key strengths lie in its capability to fit complex nonlinear relationships; it handles different types of predictors and accommodates missing values with no need for prior transformation of the predictor variables or elimination of outliers, as with real-time applications. Boosting multiple simple trees together overcomes the poor prediction accuracy of single-tree models and provides fast and superior predictive performance. Three models are calibrated: a full model that augments all available data and another two models to compare explicitly the prediction performance of traffic data collected from different sources (AVI and RTMS) at the same location. The results from the preliminary analysis as well as the calibrated models indicate that crash prediction by AVI is comparable to that by RTMS data. Moreover, the full model achieves superior classification accuracy by identifying about 89% of crash cases in the validation data set with only a 6.5% false positive rate. Because of its superior classification performance and its minimal required data preparation, SGB is recommended as a promising technique for real-time risk assessment.

01514599

13-0410

English

pp 26–34

2013

Transportation Research Record: Journal of the Transportation Research Board

9780309287036

Print

Figures (5) ; References (21) ; Tables (1)

Automatic vehicle identification; Crash risk forecasting; Mountain roads; Risk assessment; Stochastic processes; Traffic data; Weather conditions

Remote traffic microwave sensors

Colorado

Data and Information Technology; Highways; Safety and Human Factors; I82: Accidents and Transport Infrastructure

TRIS, TRB, ATRI

Feb 5 2013 12:13PM

• Analysis of Crash Severity Based on Vehicle Damage and Occupant Injuries
• Assessment of Exposure Proxies for Macroscopic Road Safety Prediction
• Crash Databases in Australasia, the European Union, and the United States: Review and Prospects for Improvement
• Developing Truck Corridor Crash Severity Index
• Effects of Public Rest Areas on Fatigue-Related Crashes
• Evaluation of Postencroachment Time as Surrogate for Opposing Left-Turn Crashes
• Evolutionary Game Theoretic Approach to Rear-End Events on Congested Freeway
• Examining Heterogeneity of Driver Behavior with Temporal and Spatial Factors
• Exploring Behavioral Responses of Motorists to Risk-Based Charging Mechanisms
• Feasibility of Incorporating Reliability Analysis in Traffic Safety Investigation
• Full Bayes Before-and-After Evaluation of Traffic Safety Improvements in City of Edmonton, Canada
• Hot-Spot Identification: Categorical Binary Model Approach
• Identification of Crash-Contributing Factors: Effects of Spatial Autocorrelation and Sample Data Size
• Identifying Primary and Secondary Crashes from Spatiotemporal Crash Impact Analysis
• Motion Prediction Methods for Surrogate Safety Analysis
• On-Duty Struck-By Crashes: Characteristics and Contributing Factors
• Safety and Operational Benefits of Variable Speed Limits Under Different Traffic Conditions and Driver Compliance Levels
• Safety Evaluation of Horizontal Curves on Rural Undivided Roads
• Screening Naturalistic Driving Study Data for Safety-Critical Events
• Surrogate Safety Measure for Simulation-Based Conflict Study