Daily long-term traffic flow forecasting based on a deep neural network

• Published in: Expert systems with applications Vol. 121; pp. 304 - 312
• Main Authors: Qu, Licheng, Li, Wei, Li, Wenjing, Ma, Dongfang, Wang, Yinhai
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 01.05.2019; Elsevier BV
• Subjects: Algorithms; Artificial neural networks; Batch training; Contextual factor; Daily long-term traffic flow; Deep neural network; Forecasting; Machine learning; Multilayers; Neural networks; Traffic flow; Traffic management; Training; Daily long-term traffic flow; Deep neural network; Contextual factor; Forecasting; Batch training
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.12.031

•A new deep learning algorithm to predict daily long-term traffic flow data using contextual factors.•Deep neutral network to mine the relationship between traffic flow data and contextual factors.•Advanced batch training can effectively improve convergence of the training process. Daily traffic flow forecasting is critical in advanced traffic management and can improve the efficiency of fixed-time signal control. This paper presents a traffic prediction method for one whole day using a deep neural network based on historical traffic flow data and contextual factor data. The main idea is that traffic flow within a short time period is strongly correlated with the starting and ending time points of the period together with a number of other contextual factors, such as day of week, weather, and season. Therefore, the relationship between the traffic flow values within a given time interval and a combination of contextual factors can be mined from historical data. First, a predictor was trained using a multi-layer supervised learning algorithm to mine the potential relationship between traffic flow data and a combination of key contextual factors. To reduce training times, a batch training method was proposed. Finally, a Seattle-based case study shows that, overall, the proposed method outperforms the conventional traffic prediction method in terms of prediction accuracy.