00756214

Component

https://doi.org/10.3141/1643-02

http://scholar.google.com...ARAN&publication_year=1998

Artificial neural networks are increasingly employed in prediction modeling and are particularly advantageous when the relationship between the response and the predictor variables is complex. For the purposes of prediction, neural networks are to be trained with data that are accurately compiled. Frequently, the data collected either from field or laboratory observations are noisy in nature. The effect of noisy data on the predictive capability of neural networks has been studied. Present serviceability rating (PSR) of pavements is the attribute to be predicted. Six noisy databases are created and are employed to train the neural networks to predict PSR. Regression equations are developed with the same noisy databases, and the predictions from neural networks are compared with those of regression. The results show that the neural networks predict PSR as accurately as regression models with a given noisy data. In addition, neural networks are trained with data containing no noise. If no noise is present in the data, neural networks predict PSR accurately while properly capturing the effect of each explanatory variable on the response variable.

This paper appears in Transportation Research Record No. 1643, Pavement Management and Monitoring of Traffic and Pavements.

English

p. 7-13

1998

Transportation Research Record

0309065151

Figures (5) ; References (18) ; Tables (5)

Accuracy; Alternatives analysis; Field studies; Forecasting; Interference; Laboratories; Neural networks; Pavement performance; Regression analysis

Field data

Data and Information Technology; Design; Highways; Pavements; I22: Design of Pavements, Railways and Guideways; I23: Properties of Road Surfaces

TRIS, TRB, ATRI

Nov 17 1998 12:00AM

• "OFF-THE-WALL" PAVEMENT DISTRESS VARIABILITY STUDY
• A COMPARATIVE STUDY OF RIDE QUALITY MEASURING DEVICES
• ALGORITHM DEVELOPMENT FOR DERIVATION OF SECTION-RELATED MEASURES OF TRAFFIC SYSTEM PERFORMANCE USING INDUCTIVE LOOP DETECTORS
• ANALYSIS OF PAVEMENT MANAGEMENT ACTIVITIES PROGRAMMING BY GENETIC ALGORITHMS
• ASSESSMENT OF LONG-TERM PAVEMENT PERFORMANCE PLAN WALL PROJECTION-BASED DISTRESS DATA VARIABILITY
• CONTRACTING FOR PAVEMENT DISTRESS DATA COLLECTION
• DEVELOPMENT OF DISTRESS PROGRESSION MODELS USING PANEL DATA SETS OF IN-SERVICE PAVEMENTS
• DEVELOPMENT OF KNOWLEDGE-BASED FORMULA TO PRIORITIZE PAVEMENT REHABILITATION PROJECTS
• ELECTRONIC PERMITTING ISSUANCE SYSTEM FOR OVERSIZE/OVERWEIGHT VEHICLES
• ENGINEERING APPLICATION OF WASHINGTON STATE'S PAVEMENT MANAGEMENT SYSTEM
• FIELD TEST OF NONINTRUSIVE TRAFFIC DETECTION TECHNOLOGIES
• INTERNATIONAL STANDARDS ORGANIZATION-COMPATIBLE INDEX FOR PAVEMENT ROUGHNESS
• MINIMUM PAVEMENT TEMPERATURE MODELING AND MAPPING FOR ALASKAN CONDITIONS
• PAVEMENT DETERIORATION, RATE OF DYNAMIC FORCE, AND RIDE QUALITY
• PAVEMENT PRESERVATION STRATEGY
• PROJECT SCOPING USING FALLING WEIGHT DEFLECTOMETER TESTING: NEW JERSEY EXPERIENCE
• SWITCHING TO INTERNATIONAL ROUGHNESS INDEX
• TRUCK TRAFFIC CROSSING TEXAS-MEXICO BORDER
• TRUCK WEIGHT ENFORCEMENT MEASURES OF EFFECTIVENESS: DEVELOPMENT AND SOFTWARE APPLICATION
• UPDATE OF LONG-TERM PAVEMENT PERFORMANCE MANUAL DISTRESS DATA VARIABILITY: BIAS AND PRECISION
• VEHICLE RE-IDENTIFICATION AND TRAVEL TIME MEASUREMENT IN REAL-TIME ON FREEWAYS USING EXISTING LOOP DETECTOR INFRASTRUCTURE