PAVEMENT MAINTENANCE AND REHABILITATION DECISIONS DERIVED BY ROUGH SET THEORY

Rough Set Theory (RST) is an induction based decision-making technique, which can extract useful information from attribute-value (decision) table. This study introduces RST into pavement management system (PMS) for maintenance and rehabilitation (M&R) strategy induction. An empirical study is conducted by using the pavement distress survey data collected by experienced pavement engineers of Taiwan Highway Bureau (THB) in 1999. Eighteen distress types and their corresponding M&R treatments were surveyed and recorded from seven county roads to establish the analytical database. The database consists of 2,348 records (2,115 records for rule induction, and 233 records for rule verification). On the basis of the verification results, total accuracy for the induced rules is as high as 93.6%, which illustrates that RST certainly can assist pavement engineers to easily remove redundant records, reduce attributes, discover association, and induce the most appropriate M&R strategy when they deal with the enormous pavement distress data.