Predicting Transport Mode in the Rabat Region: A Machine Learning Approach

The continuous increase in population density and the increase in average travel of people by different modes of transportation, whether public or private, play a crucial part in how the city's urban area develops.The latter contribute significantly to the emergence of many problems, including road congestion, loss of time, and pollution in urban areas, noise, and other issues.Machine Learning has extensively beneficial aspects of proposing models in this context.Therefore, we proposed four algorithms of the machine learning techniques that have been implemented to analyze and classify the displacement of an individual's database to support urban decisions, K-Nearest Neighbors (KNN), Artificial Neural Network-multilayer perceptron Neural (net-RBF), Bayesian Belief Network (BNN) and Support Vector Machine (SVM).We will compare their learning metrics using train/test and cross-validation.The obtained results show that net-RBF offers the best accuracy (92.77%),SVM classifier (89.87%),BBN classifier (87.33%), and KNN classifier (86.53%).