cff-version: 1.2.0
message: If you use ASTIR in your work, please cite it using the following metadata
title: "ASTIR: Spatio-Temporal Data Mining for Crowd Flow Prediction"
abstract: The citywide crowd flow prediction is crucial for a city to ensure productivity, safety and management of its citizen. However, the crowd flow may be affected by many factors, such as weather, working times, events, seasons, and so on. In this paper, we proposed Attentive Spatio-Temporal Inception ResNet (ASTIR), which aims to address the difficulty of crowd flow prediction. The ASTIR is based on the Inception-ResNet structure combined with Convolution-LSTM layers and attention module to better capture pattern movement changes. We build our deep neural network framework consisting of four distinct parts, by which we can capture the short-term, long-term and period properties, as well as external factors that can affect crowd flow behaviors. To show the performance of the proposed method, we use the widely applied benchmarks for crowd flow prediction (Taxi Beijing and Bike New York), and obtain notable improvements over the state-of-the-art approaches.
authors:
  - family-names: Lablack
    given-names: Mourad
    orcid: https://orcid.org/0000-0001-5997-7199
    affiliation: Dalian University Of Technology, Dalian, China
  - name: "ASTIR: Spatio-Temporal Data Mining for Crowd Flow Prediction"
keywords:
  - Traffic flow Prediction
  - ConvLSTM
  - Spatio-Temporal Neural Network
version: 1.0.0
doi: 10.1109/ACCESS.2019.2950956
date-released: 2019
license: MIT License
repository-code: https://github.com/Mouradost/ASTIR
references:
  - type: article
    title: "ASTIR: Spatio-Temporal Data Mining for Crowd Flow Prediction"
    authors:
      - family-names: Lablack
        given-names: Mourad
        orcid: https://orcid.org/0000-0001-5997-7199
      - family-names: Qi
        given-names: Heng
        orcid: https://orcid.org/0000-0002-8770-3934
      - family-names: Shen
        given-names: Yanming
        orcid: https://orcid.org/0000-0003-4108-0230
      - family-names: Yin
        given-names: Baocai
    identifiers:
      - type: doi
        value: 10.1109/ACCESS.2019.2950956
    keywords:
      - Traffic flow Prediction
      - ConvLSTM
      - Spatio-Temporal Neural Network
    abstract: The citywide crowd flow prediction is crucial for a city to ensure productivity, safety and management of its citizen. However, the crowd flow may be affected by many factors, such as weather, working times, events, seasons, and so on. In this paper, we proposed Attentive Spatio-Temporal Inception ResNet (ASTIR), which aims to address the difficulty of crowd flow prediction. The ASTIR is based on the Inception-ResNet structure combined with Convolution-LSTM layers and attention module to better capture pattern movement changes. We build our deep neural network framework consisting of four distinct parts, by which we can capture the short-term, long-term and period properties, as well as external factors that can affect crowd flow behaviors. To show the performance of the proposed method, we use the widely applied benchmarks for crowd flow prediction (Taxi Beijing and Bike New York), and obtain notable improvements over the state-of-the-art approaches.
    date-released: 2019
    license: IEEE Access