Co-location decision tree for enhancing decision-making of pavement maintenance and rehabilitation

Guoqing Zhou, Linbing Wang
2012 Transportation Research Part C: Emerging Technologies  
A pavement management system (PMS) is a valuable tool and one of the critical elements of the highway transportation infrastructure. Since a vast amount of pavement data is frequently and continuously being collected, updated, and exchanged due to rapidly deteriorating road conditions, increased traffic loads, and shrinking funds, resulting in the rapid accumulation of a large pavement database, knowledge-based expert systems (KBESs) have therefore been developed to solve various transportation
more » ... problems. This dissertation presents the development of theory and algorithm for a new decision tree induction method, called co-location-based decision tree (CL-DT.) This method will enhance the decision-making abilities of pavement maintenance personnel and their rehabilitation strategies. This idea stems from shortcomings in traditional decision tree induction algorithms, when applied in the pavement treatment strategies. The proposed algorithm utilizes the co-location (co-occurrence) characteristics of spatial attribute data in the pavement database. With the proposed algorithm, one distinct event occurrence can associate with two or multiple attribute values that occur simultaneously in spatial and temporal domains. This research dissertation describes the details of the proposed CL-DT algorithms and steps of realizing the proposed algorithm. First, the dissertation research describes the detailed colocation mining algorithm, including spatial attribute data selection in pavement databases, the determination of candidate co-locations, the determination of table instances of candidate colocations, pruning the non-prevalent co-locations, and induction of co-location rules. In this step, a hybrid constraint, i.e., spatial geometric distance constraint condition and a distinct event-type constraint condition, is developed. The spatial geometric distance constraint condition is a neighborhood relationship-based spatial joins of table instances for many prevalent co-locations with one prevalent co-location; and the distance event-type constraint condition is a Euclidean distance between a set of attributes and its corresponding clusters center of attributes. The ~ iv ~ This dissertation research has demonstrated the advantages of the proposed method on the basis of the experimental results and several comparison analyses including the induced decision tree parameters, the misclassified percentage, the computational time taken, support, confidence and capture for rule induction, and the quantity and location of each treatment strategy. It has been concluded that (1) the proposed CL-DT algorithm can make better decisions for pavement treatment strategies when compared to the traditional DT method; (2) the proposed CL-DT method misclassified from 61.2% to 9.7%, which implies that the training data can contribute to decision tree induction; (3) the proposed CL-DT algorithm saves the 20% computational time taken in tree growing, tree drawing, and rule generation; (4) the percentage of support, confidence and capture of the FDP treatment strategy for the proposal CL-DT algorithm increases from 71.6%, 55.6%, and 66.2% to 83.2%, 84.4% and 77.7%, respectively; (5) the quantity of each treatment strategy discovered by CL-DT is very close to those proposed by the ITRE(Institute for Transportation Research and Education (ITRE); and (6) the location of each treatment strategy proposed by CL-DT is also very close to those proposed by the ITRE.
doi:10.1016/j.trc.2011.10.007 fatcat:t4uahzgyfbdtxmmpr67ylwq3pq