01587330

Component

https://doi.org/10.3141/2589-15

The pavement performance model is a basic part of the pavement management system. The prediction accuracy of the model depends on the number of effective variables and the type of mathematical method that is used for modeling the pavement performance. In this paper, the capability of the support vector machine (SVM) method is analyzed for predicting the future of the pavement condition. Five kernel types of SVM algorithm are formed and nine input variables of the proposed models are extracted from the range of effective variables on the pavement condition. The international roughness index is used as the pavement performance index. The results show that the Pearson VII Universal kernel can accurately predict pavement performance in its life cycle.

01589874

16-2741

English

pp 135–145

2016

Transportation Research Record: Journal of the Transportation Research Board

9780309369916

Print

Figures (7) ; References (59) ; Tables (1)

Algorithms; Mathematical prediction; Pavement management systems; Pavement performance; Pavements

International Roughness Index; Pearson VII Universal kernel

Support vector machines

Design; Highways; Pavements

TRIS, TRB, ATRI

Jan 12 2016 5:07PM

• Computational Technique for Detecting Errors in Network-Level Pavement Condition Data
• Developing a Correlation Between the Pavement Condition Ratings Used by Five Federal Lands Management Agencies
• Evaluating Needs of Road Maintenance in Sweden with the Mixed Proportional Hazards Model
• Global Procedure for Temperature Adjustment of Measured Pavement Deflection Data: Based on the Long-Term Pavement Performance Seasonal Monitoring Program
• Hybrid Modeling Approach for Quantifying Maintenance and Rehabilitation Treatment Effectiveness of Asphalt Pavements
• Imperfect Preventive Maintenance Strategy for Flexible Pavements Based on Threshold Reliability, Cost Optimization, and Mechanistic–Empirical Analysis
• Influence of Pavement Condition Data Variability on Network-Level Maintenance Decision
• Informing Roadway Sustainability Practices by Using Greenroads Certified Project Data
• Methodology for Determining Performance Life of Hot-Mix Asphalt Mixtures
• Model Development, Field Section Characterization, and Model Comparison for Excess Vehicle Fuel Use Attributed to Pavement Structural Response
• Rational Procedure for Determination of Rut Depth Intervention Level in Network-Level Pavement Management
• Road Section Length Variability on Pavement Management Decision Making for Ontario, Canada, Highway Systems
• Seed-Based Approach for Automated Crack Detection from Pavement Images
• Three-Stage Least Squares Analysis of Postrehabilitation Pavement Performance
• Use of Connected Vehicles to Characterize Ride Quality
• Use of Three-Dimensional Pavement Surface Data to Analyze Crack Deterioration: Pilot Study on Georgia State Route 26
• Validation of Dynamic Simulation of Slow-Moving Surface Deflection Measurements