Implications of Spatiotemporal Data Aggregation on Short-Term Traffic Prediction Using Machine Learning Algorithms

• Published in: Journal of advanced transportation Vol. 2020; no. 2020; pp. 1 - 21
• Main Authors: Weerasekera, Rivindu, Ranjitkar, Prakash, Sridharan, Mohan
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 2020; Hindawi; John Wiley & Sons, Inc; Hindawi Limited; Hindawi-Wiley
• Subjects: Accuracy; Agglomeration; Algorithms; Artificial neural networks; Autoregressive models; Data management; Data mining; Data smoothing; Historical account; Identification methods; Intelligent transportation systems; Learning algorithms; Machine learning; Neural networks; Predictions; Regression models; Roads; Short term; Spatiotemporal data; Statistical analysis; Studies; Support vector machines; Traffic congestion; Traffic flow; Traffic models; Transportation; Transportation networks; United Kingdom
• ISSN: 0197-6729; 2042-3195
• DOI: 10.1155/2020/7057519

Short-term traffic prediction is a key component of Intelligent Transportation Systems. It uses historical data to construct models for reliably predicting traffic state at specific locations in road networks in the near future. Despite being a mature field, short-term traffic prediction still poses some open problems related to the choice of optimal data resolution, prediction of nonrecurring congestion, and the modelling of relevant spatiotemporal dependencies. As a step towards addressing these problems, this paper investigates the ability of Artificial Neural Networks, Random Forests, and Support Vector Regression algorithms to reliably model traffic flow at different data resolutions and respond to unexpected traffic incidents. We also explore different feature selection methods to identify and better understand the spatiotemporal attributes that most influence the reliability of these models. Experimental results indicate that data aggregation does not necessarily achieve good performance for multivariate spatiotemporal machine learning models. The models learned using high-resolution 30-second input data outperformed the corresponding baseline ARIMA models by 8%. Furthermore, feature selection based on Recursive Feature Elimination resulted in models that outperformed those based on linear correlation-based feature selection.