ENHANCEMENT OF DECISION-MAKING PROCESS IN PMS THROUGH APPLICATION OF DATA MINING TECHNOLOGY

The process of collecting pavement data has been growing with advances in technology, consequently generating huge amounts of data to be stored in pavement management systems (PMS) databases. The rapid size increases of these databases presents a challenge for highway agencies to understand and take advantage of the data to increase the effectiveness of the decision-making process. The Knowledge Discovery in Databases (KDD) process and data mining are being applied to large pavement datasets with the objective of extracting usefulinformation and knowledge. One of the major, if not the sole, source of actual field data measured under actual varied site conditions is Long-Term Pavement Performance (LTPP), which is carried out through a 20-year program to study the performance of the in-service pavements. In this paper, a brief background on data mining and available commercially tools are introduced. Further applications of data mining to transportation engineering problems are reviewed. The application of data mining for typical example of Prediction of Remaining Life (RL) of Pavements is demonstrated. Furthermore, a Decision Support Model (DSM) was developed to predict the RL of pavements based on the extracted pattern knowledge. The prediction and validation process was performed. The results demonstrated that data mining could be an effective tool in predicting RL of pavements. The paper highlights the potential of data mining tool application in PMS to enhance decision-making process.