Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.

Accurate traffic forecasting is important to enable intelligent transportation systems in a smart city. This problem is challenging due to the complicated spatial, short-term temporal and long-term periodical dependencies. Existing approaches have considered these factors in modeling. Most solutions apply CNN, or its extension Graph Convolution Networks (GCN) to model the spatial correlation. However, the convolution operator may not adequately model the non-Euclidean pair-wise correlations. In this paper, we propose a novel Attention-based Periodic-Temporal neural Network (APTN), an end-to-end solution for traffic foresting that captures spatial, short-term, and long-term periodical dependencies. APTN first uses an encoder attention mechanism to model both the spatial and periodical dependencies. Our model can capture these dependencies more easily because every node attends to all other nodes in the network, which brings regularization effect to the model and avoids overfitting between nodes. Then, a temporal attention is applied to select relevant encoder hidden states across all time steps. We evaluate our proposed model using real world traffic datasets and observe consistent improvements over state-of-the-art baselines.

The citywide crowd flow prediction is crucial for a city to ensure productivity, safety and management of its citizen. However, the crowd flow may be affected by many factors, such as weather, working times, events, seasons, and so on. In this paper, we proposed Attentive Spatio-Temporal Inception ResNet (ASTIR), which aims to address the difficulty of crowd flow prediction. The ASTIR is based on the Inception-ResNet structure combined with Convolution-LSTM layers and attention module to better capture pattern movement changes. We build our deep neural network framework consisting of four distinct parts, by which we can capture the short-term, long-term and period properties, as well as external factors that can affect crowd flow behaviors. To show the performance of the proposed method, we use the famous benchmarks for crowd flow prediction (Taxi Beijing and Bike New York), and obtain notable improvements over the state-of-the-art approaches.

Next Point-of-Interest (POI) recommendation has been proven effective at utilizing sparse, intricate spatial-temporal trajectory data to recommend subsequent POIs to users. While existing methods commonly alleviate the problem of data sparsity by integrating spatial-temporal context information, POI category features, and social relationships, they largely overlook the fact that the trajectory sequences collected in the datasets are often incomplete. This oversight limits the model’s potential to fully leverage historical context. In light of this background, we propose Trajectory Data Augmentation with Uncertainty (TAU) for Next POI Recommendation. TAU is a general graph-based trajectory data augmentation method designed to complete user mobility patterns by marrying uncertainty estimation into the next POI recommendation task. More precisely, TAU taps into the global transition pattern graph to identify sets of intermediate nodes located between every pair of locations, effectively leveraging edge weights as transition probabilities. During trajectory sequence construction, TAU selectively prompts intermediate nodes, chosen based on their likelihood of occurrence as pseudo-labels, to establish comprehensive trajectory sequences. Furthermore, to gauge the certainty and impact of pseudo-labels on the target location, we introduce a novel confidence-aware calibration strategy using evidence deep learning (EDL) for improved performance and reliability. The experimental results clearly indicate that our TAU method achieves consistent performance improvements over existing techniques across two real-world datasets, verifying its effectiveness as the state-of-the-art approach to the task.