Traffic Flow Prediction using Long Short-Term Memory Network and Optimized Spatial Temporal Dependencies
Authors:
- 15 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1550-1557
Abstract
Accurate traffic flow prediction is required in traffic management and optimal route selection. Traffic data patterns are influenced by factors such as road characteristics, time of the day, day of the week, weather conditions, and special events. The accuracy of traffic flow prediction depends on the spatial and temporal extent and diversity of the available data, along with the prediction algorithm. This paper presents a long short-term memory (LSTM) network for traffic prediction which is boosted by optimizing the spatial and temporal extent of the features that are used as input. A grid search method is employed to choose the spatial and temporal window sizes that result in the highest generalization accuracy. The optimal temporal window size is the number of time steps for input features and the spatial window size refers to the size of the geographical neighborhood, where features are used as input. Our experiments with traffic prediction in the State of California showed that optimizing the spatial and temporal window sizes in an LSTM network could improve the RMSE and R 2 by up to 40.02% and 25.21%.Keywords
This publication has 25 references indexed in Scilit:
- Short-Term Traffic Flow Intensity Prediction Based on CHS-LSTMArabian Journal for Science and Engineering, 2020
- PSO-ELM: A Hybrid Learning Model for Short-Term Traffic Flow ForecastingIEEE Access, 2020
- LSTM-based traffic flow prediction with missing dataNeurocomputing, 2018
- A testbed for evaluating network construction algorithms from GPS tracesComputers, Environment and Urban Systems, 2017
- Intelligent GPS trace management for human mobility pattern detectionCogent Engineering, 2017
- Daily ETC Traffic Flow Time Series Prediction Based on k-NN and BP Neural Network2016
- A Comparative Study of Three Multivariate Short-Term Freeway Traffic Flow Forecasting Methods With Missing DataJournal of Intelligent Transportation Systems, 2015
- Short-term traffic flow prediction using seasonal ARIMA model with limited input dataEuropean Transport Research Review, 2015
- A novel hybridization of artificial neural networks and ARIMA models for time series forecastingApplied Soft Computing, 2011
- RENAISSANCE – A unified macroscopic model-based approach to real-time freeway network traffic surveillanceTransportation Research Part C: Emerging Technologies, 2006