A Multi-Stream Feature Fusion Approach for Traffic Prediction

Zhishuai Li · Gang Xiong · Yonglin Tian · Yisheng Lv · Yuanyuan Chen · Pan Hui +1 more

340 citations0/0 files storedIEEE Transactions on Intelligent Transportation Systems

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Traffic Prediction and Management Techniques Traffic control and management Advanced Graph Neural Networks

Abstract

Accurate and timely traffic flow prediction is crucial for intelligent transportation systems (ITS). Recent advances in graph-based neural networks have achieved promising prediction results. However, some challenges remain, especially regarding graph construction and the time complexity of models. In this paper, we propose a multi-stream feature fusion approach to extract and integrate rich features from traffic data and leverage a data-driven adjacent matrix instead of the distance-based matrix to construct graphs. We calculate the Spearman rank correlation coefficient between monitor stations to obtain the initial adjacent matrix and fine-tune it while training. As to the model, we construct a multi-stream feature fusion block (MFFB) module, which includes a three-channel network and the soft-attention mechanism. The three-channel networks are graph convolutional neural network (GCN), gated recurrent unit (GRU) and fully connected neural network (FNN), which are used to extract spatial, temporal and other features, respectively. The soft-attention mechanism is utilized to integrate the obtained features. The MFFB modules are stacked, and a fully connected layer and a convolutional layer are used to make predictions. We conduct experiments on two real-world traffic prediction tasks and verify that our proposed approach outperforms the state-of-the-art methods within an acceptable time complexity.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 340 citations exist upstream.

References

2018Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting 2017Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting 2019T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction 2014Traffic Flow Prediction With Big Data: A Deep Learning Approach 2016Using LSTM and GRU neural network methods for traffic flow prediction 2019Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting 2008Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions 1996Combining kohonen maps with arima time series models to forecast traffic flow

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.