Modeling citywide crowd flows using attentive convolutional LSTM

Chi Harold Liu, Chengzhe Piao, Xiaoxin Ma, Ye Yuan, Jian Tang, Guoren Wang, Kin K. Leung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Understanding the movement patterns of humans and vehicles traveling in a city is important for many applications like emergency evacuation and rescue, as well as city planning and management. In this paper, we aim to predict citywide crowd flows within a period in the future to give aid to urban management, through modeling spatiotemporal patterns of recent crowd flows. We present a novel deep model for this task, called "AttConvLSTM", which leverages a convolutional LSTM (ConvLSTM), Convolutional Neural Networks (CNNs) along with an attention mechanism, where ConvLSTM keeps spatial information as intact as possible during sequential analysis, and the attention mechanism can focus important crowd flow variations which cannot be identified by the recurrent module. We conducted extensive experiments for performance evaluation using three large datasets, including Beijing Taxi dataset, Rome Taxi dataset, and Chengdu Didi chauffeuring trace. The experimental results show that AttConvLSTM significantly outperforms several widely-used baselines in terms of Root Mean Squared Error (RMSE), and Mean Average Percentage Error (MAPE), indicating that our approach can deal with crowd flows with different dynamics in both spatial and temporal domains, and make valid predictions several steps ahead.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE 37th International Conference on Data Engineering, ICDE 2021
PublisherIEEE Computer Society
Pages217-228
Number of pages12
ISBN (Electronic)9781728191843
DOIs
StatePublished - Apr 2021
Externally publishedYes
Event37th IEEE International Conference on Data Engineering, ICDE 2021 - Virtual, Chania, Greece
Duration: Apr 19 2021Apr 22 2021

Publication series

NameProceedings - International Conference on Data Engineering
Volume2021-April
ISSN (Print)1084-4627

Conference

Conference37th IEEE International Conference on Data Engineering, ICDE 2021
Country/TerritoryGreece
CityVirtual, Chania
Period4/19/214/22/21

Keywords

  • Attention Mechanism
  • Convolutional LSTM
  • Crowd flow prediction
  • User Mobility

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Information Systems

Fingerprint

Dive into the research topics of 'Modeling citywide crowd flows using attentive convolutional LSTM'. Together they form a unique fingerprint.

Cite this