Combining knowledge graph into metro passenger flow prediction: A split-attention relational graph convolutional network

Zeng, Jie; Tang, Jinjun

doi:10.1016/j.eswa.2022.118790

Cited by 31 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, there are other studies such as [2], [3], [6], [7], where it is clear that these techniques used can be applied in a very similar way to perform origin-destination forecasting. The overall focus is really on being able to collect these spatial and temporal dependencies together with the environmental conditions in order to be able to make a prediction.…”

Section: A Inflow/outflow Forecastingmentioning

confidence: 99%

Model Generation and Origin - Destination(OD) Matrix Forecasting for metro systems

Sobrino,

Andión,

Dueñas

et al. 2023

2023 7th International Young Engineers Forum (YEF-ECE)

View full text Add to dashboard Cite

The growth of data collection has led to a proliferation of studies and research, including the transport sector, especially in metro systems. There are few studies about the prediction of the Origin-Destination (OD) matrix, which is important to know the number of passengers on each vehicle and the routes with the most traffic. Knowing this information will allow for more efficient management of resources and adjusting timetables and services to meet demand. Moreover, most OD studies focus on short-term forecasting, however, longterm prediction models are necessary for public transport planning and design. Therefore, a model capable of generating samples and predicting them is proposed, achieving a long-term prediction of OD demand. It will start with a prior process of elimination and reconstruction of records. Subsequently, the spatial-temporal dependencies will be captured in the model of generation of origin samples to finally achieve the prediction of the destinations. For the prediction model, an innovative method for the selection of the target sample based on the probability of occurrence is proposed, which increases the accuracy of the model. Finally, the model is evaluated on a real dataset of Metro de Madrid to demonstrate its validity and universality.

show abstract

Section: A Inflow/outflow Forecastingmentioning

confidence: 99%

Model Generation and Origin - Destination(OD) Matrix Forecasting for metro systems

Sobrino,

Andión,

Dueñas

et al. 2023

2023 7th International Young Engineers Forum (YEF-ECE)

View full text Add to dashboard Cite

show abstract

“…Furthermore, hypergraph convolution and spatial-temporal blocks are proposed to extract spatial and temporal features to achieve node level prediction. The model in [36] integrates the Relational Graph Convolutional Network (R-GCN), split-attention mechanism, and Long Short-Term Memory (LSTM) to explore the spatial-temporal correlations and dependence between passenger inflow and outflow.…”

Section: Related Workmentioning

confidence: 99%

A Spatial-Temporal Graph Convolutional Recurrent Network for Transportation Flow Estimation

Drosouli,

Voulodimos,

Mastorocostas

et al. 2023

Sensors

View full text Add to dashboard Cite

Accurate estimation of transportation flow is a challenging task in Intelligent Transportation Systems (ITS). Transporting data with dynamic spatial-temporal dependencies elevates transportation flow forecasting to a significant issue for operational planning, managing passenger flow, and arranging for individual travel in a smart city. The task is challenging due to the composite spatial dependency on transportation networks and the non-linear temporal dynamics with mobility conditions changing over time. To address these challenges, we propose a Spatial-Temporal Graph Convolutional Recurrent Network (ST-GCRN) that learns from both the spatial stations network data and time series of historical mobility changes in order to estimate transportation flow at a future time. The model is based on Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) in order to further improve the accuracy of transportation flow estimation. Extensive experiments on two real-world datasets of transportation flow, New York bike-sharing system and Hangzhou metro system, prove the effectiveness of the proposed model. Compared to the current state-of-the-art baselines, it decreases the estimation error by 98% in the metro system and 63% in the bike-sharing system.

show abstract

“…The network was trained using historical metro flow data and meteorological data. Furthermore, there are advanced deep learning approaches like attention mechanism-based methods and semi-supervised deep learning methods [22][23][24]. Xie et al innovatively built a spatialtemporal dynamic graph relationship learning model [25], and Zhang et al introduced a spatial-temporal graph GAN for accurate short-term passenger flow forecasting [26].…”

Section: Introductionmentioning

confidence: 99%

A Novel Spatial–Temporal Deep Learning Method for Metro Flow Prediction Considering External Factors and Periodicity

Shi,

Wang,

Yan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Predicting metro traffic flow is crucial for efficient urban planning and transit management. It enables cities to optimize resource allocation, reduce congestion, and enhance the overall commuter experience in rapidly urbanizing environments. Nevertheless, metro flow prediction is challenging due to the intricate spatial–temporal relationships inherent in the data and the varying influence of external factors. To model spatial–temporal correlations considering external factors, a novel spatial–temporal deep learning framework is proposed in this study. Firstly, mutual information is utilized to select the highly corrected stations of the examined station. Compared with the traditional correlation calculation methods, mutual information is particularly advantageous for analyzing nonlinear metro flow data. Secondly, metro flow data reflecting the historical trends from different time granularities are incorporated. Additionally, the external factor data that influence the metro flow are also considered. Finally, these multiple sources and dimensions of data are combined and fed into the deep neural network to capture the complex correlations of multi-dimensional data. Sufficient experiments are designed and conducted on the real dataset collected from Xi’an subway to verify the effectiveness of the proposed model. Experimental results are comprehensively analyzed according to the POI information around the subway station.

show abstract

Combining knowledge graph into metro passenger flow prediction: A split-attention relational graph convolutional network

Cited by 31 publications

References 41 publications

Model Generation and Origin - Destination(OD) Matrix Forecasting for metro systems

Model Generation and Origin - Destination(OD) Matrix Forecasting for metro systems

A Spatial-Temporal Graph Convolutional Recurrent Network for Transportation Flow Estimation

A Novel Spatial–Temporal Deep Learning Method for Metro Flow Prediction Considering External Factors and Periodicity

Contact Info

Product

Resources

About