LSTM network: a deep learning approach for short‐term traffic forecast
Top Cited Papers
Open Access
- 24 February 2017
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 11 (2), 68-75
- https://doi.org/10.1049/iet-its.2016.0208
Abstract
Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal–spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.Keywords
Funding Information
- National Natural Science Foundation of China (61573048, 61620106012)
- Natural Science Foundation of Beijing Municipality (3152018)
This publication has 36 references indexed in Scilit:
- Traffic forecasting using least squares support vector machinesTransportmetrica, 2009
- Self-adapting traffic flow status forecasts using clusteringIET Intelligent Transport Systems, 2009
- Short-Term Traffic Flow Forecasting Using Fuzzy Logic System MethodsJournal of Intelligent Transportation Systems, 2008
- A Wavelet Network Model for Short-Term Traffic Volume ForecastingJournal of Intelligent Transportation Systems, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- A Bayesian Network Approach to Traffic Flow ForecastingIEEE Transactions on Intelligent Transportation Systems, 2006
- Predicting Urban Arterial Travel Time with State-Space Neural Networks and Kalman FiltersTransportation Research Record: Journal of the Transportation Research Board, 2006
- Evaluation Framework for Dynamic Vehicle Routing Strategies Under Real-Time InformationTransportation Research Record: Journal of the Transportation Research Board, 2001
- Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX ModelingTransportation Research Record: Journal of the Transportation Research Board, 2001
- A cellular automaton model for freeway trafficJournal de Physique I, 1992