Smart City Gnosys
Smart city article details
| Title | Interpretable Local Flow Attention For Multi-Step Traffic Flow Prediction |
|---|---|
| ID_Doc | 33152 |
| Authors | Huang X.; Zhang B.; Feng S.; Ye Y.; Li X. |
| Year | 2023 |
| Published | Neural Networks, 161 |
| DOI | http://dx.doi.org/10.1016/j.neunet.2023.01.023 |
| Abstract | Traffic flow prediction (TFP) has attracted increasing attention with the development of smart city. In the past few years, neural network-based methods have shown impressive performance for TFP. However, most of previous studies fail to explicitly and effectively model the relationship between inflows and outflows. Consequently, these methods are usually uninterpretable and inaccurate. In this paper, we propose an interpretable local flow attention (LFA) mechanism for TFP, which yields three advantages. (1) LFA is flow-aware. Different from existing works, which blend inflows and outflows in the channel dimension, we explicitly exploit the correlations between flows with a novel attention mechanism. (2) LFA is interpretable. It is formulated by the truisms of traffic flow, and the learned attention weights can well explain the flow correlations. (3) LFA is efficient. Instead of using global spatial attention as in previous studies, LFA leverages the local mode. The attention query is only performed on the local related regions. This not only reduces computational cost but also avoids false attention. Based on LFA, we further develop a novel spatiotemporal cell, named LFA-ConvLSTM (LFA-based convolutional long short-term memory), to capture the complex dynamics in traffic data. Specifically, LFA-ConvLSTM consists of three parts. (1) A ConvLSTM module is utilized to learn flow-specific features. (2) An LFA module accounts for modeling the correlations between flows. (3) A feature aggregation module fuses the above two to obtain a comprehensive feature. Extensive experiments on two real-world datasets show that our method achieves a better prediction performance. We improve the RMSE metric by 3.2%–4.6%, and the MAPE metric by 6.2%–6.7%. Our LFA-ConvLSTM is also almost 32% faster than global self-attention ConvLSTM in terms of prediction time. Furthermore, we also present some visual results to analyze the learned flow correlations. © 2023 Elsevier Ltd |
| Author Keywords | Attention mechanism; Explainable artificial intelligence; Neural networks; Traffic flow prediction |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
4883  | 0.911 | Cao S.; Wu L.; Wu J.; Wu D.; Li Q. | A Spatio-Temporal Sequence-To-Sequence Network For Traffic Flow Prediction | Information Sciences, 610 (2022) |
| 35590 | 0.907 | Remmouche B.; Boukraa D.; Zakharova A.; Bouwmans T.; Taffar M. | Long-Term Spatio-Temporal Graph Attention Network For Traffic Forecasting | Expert Systems with Applications, 288 (2025) |
| 11043 | 0.903 | He Q.; Xia D.; Li J.; Yang J.; Hu Y.; Li Y.; Li H. | Attention-Based Spatiotemporal Adaptive Graph Diffusion Convolutional Network For Traffic Flow Prediction | Transportation Research Record (2025) |
| 58576 | 0.903 | Zheng L.; Pu Y.; Sun W. | Traffic Flow Prediction Algorithm Based On Attention Spatiotemporal Graph Convolution Mechanism | IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) (2024) |
| 53044 | 0.902 | Meng X.; Xie W.; Cui J. | Stmgfn: Spatio-Temporal Multi-Graph Fusion Network For Traffic Flow Prediction | Lecture Notes in Computer Science, 15291 LNCS (2025) |
| 58579 | 0.901 | Zhao J. | Traffic Flow Prediction Based On Adjacency Graph And Attention Mechanism | 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024 (2024) |
| 4890 | 0.899 | Zhang Y.; Zhang F. | A Spatiotemporal Neural Network Model For City Traffic Prediction | Proceedings of SPIE - The International Society for Optical Engineering, 12970 (2023) |
| 2156 | 0.895 | Yang S. | A Hybrid Deep Learning Model Combining Multi-Scale Self-Attention And Lstm For Accurate Traffic Flow Prediction | IET Conference Proceedings, 2025, 2 (2025) |
| 1348 | 0.895 | Hu J.; Li B. | A Deep Learning Framework Based On Spatio-Temporal Attention Mechanism For Traffic Prediction | Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 (2020) |
| 1395 | 0.894 | Tripathi A.N.; Sharma B. | A Deep Review: Techniques, Findings And Limitations Of Traffic Flow Prediction Using Machine Learning | Lecture Notes in Mechanical Engineering (2023) |