Skip to Main Content
Annually, the Philippine government'sDepartment of Public Works and Highways (DPWH) gathers visual road condition data for use in the rehabilitation of the Philippine national road network. Alongside the condition data of the road, inventory and traffic data are also gathered simultaneously. In literature, Visual Condition Index (VCI) is used to determine the condition of a road. The data gathering that will result for the VCI is a lengthy and tedious process, subject to various validations by DPWH, before being considered for budget preparation analysis. This study applies Support Vector Machines (SVM) and Artificial Neural Network (ANN) as methods for determining the visual condition of roads on an inventory and traffic data set with 16continuous-valued and 2 nominal-valued dimensions. These methods were applied on predetermined subsets of the dimensions using 10-fold cross-validation on each subset. The results show that ANN generally performs better classification compared to SVM, the difference within the 95% confidence interval. The best known results reported by ANN accurately predict the road condition by 42%. The results show that the inclusion of a large number of dimensions not directly involve din the computation of the VCI in building the classifier contributed to the low accuracy rating.