Short-Term Prediction of the Traffic Status in Urban Places Using Neural Network Models
The last decades the phenomenon of urbanisation has led to crowded and jammed areas, which makes life in cities more stressful. Thus, there is a high interest in the field of Intelligent Transportation Systems in order to prevent the traffic congestion. The most common way to prevent this phenomenon is with the use of short-term forecasting of traffic parameters, such as traffic flow and speed. Nowadays, the accuracy of the estimations has increased significantly due to the use of the latest technological advances, such as probe data in combination with machine learning techniques. Probe data is a type of crowd-sourced data collected from individuals, including vehicles, passengers, travellers or pedestrians. This paper focuses on the data processing component with the use of neural networks, for predicting traffic status in urban areas based on the relation between traffic flows and speed. As a case study is used the traffic status in the city of Thessaloniki, Greece. In this case, data is aggregated after the collection phase, which gives a better representation of the mobility patterns in the city. Two types of test were performed. The first one shows the results of the prediction of eight sequentially quarters of the time, while the second test provides the prediction four steps forward of the date time. The results of both tests provide accurate predictions.
KeywordsNeural network Traffic prediction
This work presented herein is part of the BigDataEurope project (Integrating Big Data, Software & Communities for Addressing Europe’s Societal Challenges). For more information please visit https://www.big-data-europe.eu/.
- 3.Salanova, J.M., Maciejewski, M., Bischoff, J., Estrada, M., Tzenos, P., Stamos, I.: Use of probe data generated by taxis. In: Schintler, L.A., Chen, Z. (eds.) Big Data for Regional Science. Routledge Advances in Regional Economics, Science and Policy. Taylor & Francis Group, Abingdon (2017)Google Scholar
- 11.Salanova, J.M., Toumbalidis, J., Chaniotakis, E., Karanikolaos, N., Aifadopoulou, G.: Correlation between digital and physical world, case study in Thessaloniki. J. Locat. Based Serv. 13, 1–15 (2018)Google Scholar