Journal
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
Volume 22, Issue 12, Pages 7891-7903Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2021.3072743
Keywords
Predictive models; Public transportation; Convolution; Neural networks; Graph neural networks; Forecasting; Urban areas; Metro flow prediction; hypergraph; graph neural network
Categories
Funding
- National Natural Science Foundation of China [62072015, U19B2039, U1811463, 61632006, 61876012, 61902053]
- Natural Science Foundation of Beijing [4172003]
- China Scholarship Council [201806540008]
Ask authors/readers for more resources
This paper proposes a dynamic spatio-temporal hypergraph neural network to forecast metro passenger flow, utilizing hypergraph convolution and spatio-temporal blocks to extract spatial and temporal features for node-level prediction. Experiments on historical datasets from Beijing and Hangzhou validate the effectiveness and superior performance of the proposed method in prediction accuracy compared with the state-of-the-arts.
Metro passenger flow prediction is a strategically necessary demand in an intelligent transportation system to alleviate traffic pressure, coordinate operation schedules, and plan future constructions. Graph-based neural networks have been widely used in traffic flow prediction problems. Graph Convolutional Neural Networks (GCN) captures spatial features according to established connections but ignores the high-order relationships between stations and the travel patterns of passengers. In this paper, we utilize a novel representation to tackle this issue - hypergraph. A dynamic spatio-temporal hypergraph neural network to forecast passenger flow is proposed. In the prediction framework, the primary hypergraph is constructed from metro system topology and then extended with advanced hyperedges discovered from pedestrian travel patterns of multiple time spans. Furthermore, hypergraph convolution and spatio-temporal blocks are proposed to extract spatial and temporal features to achieve node-level prediction. Experiments on historical datasets of Beijing and Hangzhou validate the effectiveness of the proposed method, and superior performance of prediction accuracy is achieved compared with the state-of-the-arts.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available