Road traffic forecasting — A hybrid approach combining Artificial Neural Network with Singular Spectrum Analysis

Abstract

The paper presents a comparison of a hybrid methodology which combines Singular Spectrum Analysis (SSA) with Artificial Neural Networks (ANN) against conventional ANN, applied on time series analysis and forecasting of road traffic volume. The main research objective was to develop a short-term forecast of daily traffic volume at toll stations across the Greek National Highway Network. The proposed methodology was implemented and evaluated upon a custom developed integrated forecasting software, based on the Mathworks MatLab platform. Experimental outcomes on daily data, from specific toll stations, demonstrate a superior prediction accuracy of hybrid SSA–ANN forecasting methodology against conventional ANN, when compared to performances of statistical criteria such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Coefficient of Determination (R2). A comparison of results revealed that the SSA–ANN hybrid model could improve the forecasting accuracy of the conventional ANN model in the case of daily traffic volume forecasting. An Intelligent Transport System with embedded hybrid SSA–ANN forecasting algorithm could manage and analyze big data traffic volume time series in real time, providing an advanced decision support system for transportation system management and maintenance, while it would enable proactive decisions to mitigate the economic and environmental impacts of traffic congestion.