Real-time public transportation prediction with machine learning algorithms

Dancho Panovski (1, 2, 3) , Titus Zaharia (1, 2, 3)

1 ARMEDIA-SAMOVAR - ARMEDIA
2 IP Paris - Institut Polytechnique de Paris
3 TSP - ARTEMIS - Département Advanced Research And Techniques For Multidimensional Imaging Systems

As part of Intelligent Transportation Systems (ITS) public transportation plays a critical and essential role for the mobility in every modern city. In this paper, we introduce a novel method for the real-time prediction of bus arrival times in the various bus stops over a given itinerary. The proposed approach exploits machine and deep learning algorithms, including optimal least square (OLS) linear regression, support vector regression (SVR) and fully-connected neural networks (FNN). The experimental results obtained show that the FNN approach outperforms, in terms of mean absolute prediction error, both SVR (by 7,62 %) and OLS (for 15,74 %).

Domaines: Traitement du signal et de l'image [eess.SP]

Dancho Panovski, Titus Zaharia. Real-time public transportation prediction with machine learning algorithms. ICCE 2020: IEEE International Conference on Consumer Electronics, Jan 2020, Las Vegas, United States. pp.1-4, ⟨10.1109/ICCE46568.2020.9043077⟩. ⟨hal-03126809⟩