Metro OD Matrix Prediction Based on Multi-View Passenger Flow Evolution Trend Modeling

Furong, Zheng,; Zhao, Juanjuan; Ye, Jiexia; Gao, Xitong; Ye, Kejiang; Xu, Cheng‐Zhong

doi:10.1109/tbdata.2022.3229836

Cited by 4 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although certain studies utilize matrix decomposition or its variants for OD flow prediction, 29,37 these methods are inherently linear and may not be optimal for capturing the comprehensive nonlinear correlation among OD pairs. In recent years, advanced deep learning architectures tailored for metro scenarios, such as convolutional networks and GCN, 30,31 have been introduced to tackle the challenge of metro OD prediction.…”

Section: Afc Data-base Methodsmentioning

confidence: 99%

“…• MVPF 31 (multi-view passenger flow evolution trend based OD matrix prediction method): MVPF sufficiently captures the dynamic traffic evolution trend of each station, functioning as both an origin and a destination. It not only utilizes recent inflows and outflows but also takes into consideration the allocation information of destinations (origins) for recently completed trips starting (ending) at each origin (destination).…”

Section: Baseline Methodsmentioning

confidence: 99%

“…LSTM has been widely used and proved effective for traffic flow prediction in the transportation domain. 30,31 In the following sections, we primarily focus on introducing the GCN designed for modeling spatial correlation in metro systems.…”

Section: Spatial Componentmentioning

confidence: 99%

“…We extract the inflow (outflow) of each metro station during each past time slot

{T}_{k-i}

, 31 which refers to the total number of passengers who enter (exit) the metro system at the station during the target time slot. For a station

{s}_i

and a time slot

{T}_k

, the inflow

{O}_{i,k}

can be calculated by Equation ().…”

Section: Passenger State Transition Predictormentioning

confidence: 99%

“…Each block comprises a novel GCN (graph convolution network) designed to model spatial dependencies and a LSTM (long short‐term memory) network capturing sequential dependencies and arbitrary time lags in time series. LSTM has been widely used and proved effective for traffic flow prediction in the transportation domain 30,31 . In the following sections, we primarily focus on introducing the GCN designed for modeling spatial correlation in metro systems.…”

Section: Passenger State Transition Predictormentioning

confidence: 99%

See 4 more Smart Citations

STRmt: A state transition based model for real‐time crowd counting in a metro system

Sun,

Zhao,

Zhang

et al. 2024

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

SummaryReal‐time estimation of crowd counting in underground metro systems, constrained by limited space, is crucial for managing heightened pedestrian volumes and responding promptly to emergencies. To address this challenge, we propose a passenger state transition‐based model, called STRmt, designed for the seamless and continuous monitoring of real‐time crowd movement within service areas of stations and trains, leveraging auto fare collection systems (AFC) as a comprehensive sensor network. Our innovation lies in modeling the dynamic movement of passengers within a metro system over time as a state transition process aligned with the train schedule. To achieve this, we introduce a spatio‐temporal deep learning framework, denoted as STnet, designed to dynamically predict these state transitions. The performance of our method is rigorously assessed through extensive experiments conducted spanning 2 years in Shenzhen, China, utilizing AFC data, train schedule data, and weather data. The results demonstrate that the proposed method surpasses baseline methods, achieving an estimation precision of 0.92.

show abstract