Trip Attraction Model Using Radial Basis Function Neural Networks

Trip Attraction model with seven independent variables, i.e., population size, number of schools, number of students, number of teachers, areas of school buildings, number of offices, and number of houses applying Radial Basis Function Neural Networks (RBFNN) is presented in this paper. The data used in this study were derived from the origin destination survey in Palembang and the model was developed using 85 sets of land use - trip attraction data. A comparison was made between RBF model and regression model. The results show that RBF model performs better than regression model in predicting trip attraction and important variables are number of students, number of teachers, total areas of school buildings and number of offices.