An Ensemble Model for Short-Term Traffic Prediction in Smart City Transportation System

Smart city visions aim to offer citizens with intelligent services in various aspects of life. The services envisioned have been significantly enhanced with the proliferation of Internet-of-Things (IoT) technology offering real-time and ubiquitous monitoring capability. In this paper, we focus on the short-term traffic flow prediction problem based on real-world traffic data as one critical component of a smart city. In contrast to long-term traffic prediction, accurate prediction of short-term traffic flow facilitates timely traffic management and rapid response. We develop and study a novel ensemble model (EM) based on long short term memory (LSTM), deep autoencoder (DAE) and convolutional neural network (CNN) models. Our approach takes into account both temporal and spatial characteristics of the traffic conditions. We evaluate our proposal against well-known existing prediction models. We use two real traffic data (California and London roadways) with different characteristics to train and test the models. Our results indicate that our proposed ensemble model achieves the most accurate predictions (approx. 97.50% and approx. % accuracy) and is robust against high variance traffic flow.