01592010

Component

https://doi.org/10.3141/2551-08

A connected vehicle–based winter road surface condition (RSC) monitoring solution that combines vehicle-based image data with data from a road weather information system is described. The proposed solution was intended as an improvement to a smartphone-based system evaluated in previous research. Three machine learning classification methods—namely, artificial neural networks, random trees, and random forests—were evaluated for potential application in the connected vehicle–based system for RSC monitoring. Field data collected during the 2014–2015 winter season were used for model calibration and validation. Results showed that all models improved the accuracy of the smartphone-based RSC classification substantially, with random forest having the highest classification performance. The models, however, were found to lack transferability; therefore, individual models will require local calibration before being used at any location.

01594661

16-5865

English

pp 62–72

2016

Transportation Research Record: Journal of the Transportation Research Board

9780309441230

Print

Figures (3) ; Maps; Photos; References (18) ; Tables (9)

Calibration; Data collection; Machine learning; Mobile communication systems; Neural networks; Road weather information systems; Smartphones; Weather conditions; Winter maintenance

Data and Information Technology; Highways; Operations and Traffic Management; Vehicles and Equipment

TRIS, TRB, ATRI

Jan 12 2016 6:35PM

• Accuracy of Ice Melting Capacity Tests: Review of Melting Data for Sodium Chloride
• Assessing Driver Speed Choice in Fog with the Use of Visibility Data from Road Weather Information Systems
• Chemical Melting of Ice: Effect of Solution Freezing Point on the Melting Rate
• Design and Performance Monitoring of Snow-Supporting Structures for the Milepost 151 Avalanche near Jackson, Wyoming
• Development of a Sensor Platform for High-Accuracy Mapping of Roadway Lane Markings
• Energy-Regenerative Shock Absorber for Transportation Vehicles Based on Dual Overrunning Clutches: Design, Modeling, and Simulation
• Expanding the Road Weather Information System for Avalanche Support
• Fire Risk Assessment for Highway Bridges in South Korea
• Modeling Effects of Precipitation on Vehicle Speed: Floating Car Data Approach
• Optimizing Environmental Sensor Station Locations for Road Weather Management: Overview and a Generalized Modeling Framework
• Piecewise Multiple Linear Models for Pavement Marking Retroreflectivity Prediction Under Effect of Winter Weather Events
• Proactive Strategy for Variable Speed Limit Operations on Freeways Under Foggy Weather Conditions
• Statistical Analysis for Assessing Highway Maintenance Level of Service
• Superhydrophobic Coatings on Asphalt Concrete Surfaces: Toward Smart Solutions for Winter Pavement Maintenance
• Use of Social Media by Transportation Agencies for Traffic Management