Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning

TLDR

Accurate short‑term traffic flow forecasting facilitates active traffic control and trip planning, yet most existing models fail to fully exploit temporal and spatial features. This study proposes a short‑term traffic flow prediction model based on a convolutional neural network deep‑learning framework. The framework first uses a spatio‑temporal feature selection algorithm to determine optimal input lags and spatial data amounts, extracts selected features into a 2‑D matrix, and trains a CNN to build a predictive model, which is then evaluated against actual traffic data and benchmarked against other existing models. The proposed method outperforms baseline models in accuracy.

Abstract

Accurate short-term traffic flow forecasting facilitates active traffic control and trip planning. Most existing traffic flow models fail to make full use of the temporal and spatial features of traffic data. This study proposes a short-term traffic flow prediction model based on a convolution neural network (CNN) deep learning framework. In the proposed framework, the optimal input data time lags and amounts of spatial data are determined by a spatio-temporal feature selection algorithm (STFSA), and selected spatio-temporal traffic flow features are extracted from actual data and converted into a two-dimensional matrix. The CNN then learns these features to construct a predictive model. The effectiveness of the proposed method is evaluated by comparing the forecast results with actual traffic data. Other existing models are also evaluated for comparison. The proposed method outperforms baseline models in terms of accuracy.