Open Access Conference Proceedings

The bus arrival time is one of the key elements in public transport information systems. The amount of Automated Vehicle Location (AVL) systems is growing, therefore in this paper we aim to provide a cloud-based machine learning solution of this problem. Using bus location data, we created models in Microsoft Azure Machine Learning Studio using different machine learning methods: Artificial Neural Network (ANN), Support Vector Machine (SVM) and Linear Regression (LR). We validated the methods using historical data and compared the results to naïve predictions that use either historical data with a delay or a vehicle speed.

Keywords: public transport network, bus arrival time prediction, machine learning, artificial neural network, support vector machine, linear regression

© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.