Spatial-Temporal Feature Extraction and Evaluation Network for Citywide Traffic Condition Prediction

TL;DR

This paper introduces DL-STFEE, a novel neural network model that extracts and evaluates spatial-temporal features from traffic data to improve citywide traffic condition prediction accuracy.

Contribution

The paper proposes a double-layer model combining multi-graph convolution and self-attention mechanisms for feature extraction and evaluation in traffic prediction.

Findings

DL-STFEE effectively captures complex spatial-temporal dependencies.

The model accurately evaluates the importance of different feature combinations.

Experiments show improved traffic prediction performance on real datasets.

Abstract

Traffic prediction plays an important role in the realization of traffic control and scheduling tasks in intelligent transportation systems. With the diversification of data sources, reasonably using rich traffic data to model the complex spatial-temporal dependence and nonlinear characteristics in traffic flow are the key challenge for intelligent transportation system. In addition, clearly evaluating the importance of spatial-temporal features extracted from different data becomes a challenge. A Double Layer - Spatial Temporal Feature Extraction and Evaluation (DL-STFEE) model is proposed. The lower layer of DL-STFEE is spatial-temporal feature extraction layer. The spatial and temporal features in traffic data are extracted by multi-graph graph convolution and attention mechanism, and different combinations of spatial and temporal features are generated. The upper layer of DL-STFEE is the spatial-temporal feature evaluation layer. Through the attention score matrix generated by the high-dimensional self-attention mechanism, the spatial-temporal features combinations are fused and evaluated, so as to get the impact of different combinations on prediction effect. Three sets of experiments are performed on actual traffic datasets to show that DL-STFEE can effectively capture the spatial-temporal features and evaluate the importance of different spatial-temporal feature combinations.