...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Artificial intelligence >Predicting citywide crowd flows using deep spatio-temporal residual networks
【24h】

Predicting citywide crowd flows using deep spatio-temporal residual networks

机译：使用深时空残留网络预测城市范围内的人群流量

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, including spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), and external conditions (e.g. weather and events). We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i.e. inflow and outflow) in each and every region of a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. We have developed a real-time system based on Microsoft Azure Cloud, called UrbanFlow, providing the crowd flow monitoring and forecasting in Guiyang City of China. In addition, we present an extensive experimental evaluation using two types of crowd flows in Beijing and New York City (NYC), where ST-ResNet outperforms nine well-known baselines. (C) 2018 Elsevier B.V. All rights reserved.
机译：预测人群流量对交通管理和公共安全至关重要，因为它受到许多复杂因素的影响，包括空间依赖性（临近和遥远），时间依赖性（接近性，时段，趋势）和外部条件，这非常具有挑战性（例如天气和事件）。我们提出一种称为ST-ResNet的基于深度学习的方法，以集体预测城市每个区域中两种类型的人群流量（即流入和流出）。我们基于时空数据的独特属性设计了ST-ResNet的端到端结构。更具体地说，我们采用残差神经网络框架对人群交通的时间接近度，时段和趋势属性进行建模。对于每个属性，我们设计一个残差卷积单位的分支，每个残差卷积单位都模拟人群交通的空间属性。 ST-ResNet学会根据数据动态聚合三个残差神经网络的输出，为不同的分支和区域分配不同的权重。该汇总进一步与外部因素（例如天气和一周中的一天）结合在一起，以预测每个区域中人群的最终流量。我们已经开发了一种基于Microsoft Azure云的实时系统，称为UrbanFlow，可在中国贵阳市提供人群流量的监视和预测。此外，我们在北京和纽约市（NYC）使用两种类型的人群流量进行了广泛的实验评估，其中ST-ResNet的表现优于9个知名基准。 （C）2018 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Artificial intelligence》 |2018年第6期|147-166|共20页
  • 作者

    Zhang Junbo; Zheng Yu; Qi Dekang; Li Ruiyuan; Yi Xiuwen; Li Tianrui;

  • 作者单位

    Microsoft Res, Urban Comp Grp, Beijing, Peoples R China;

    JD Finance, Urban Comp Business Unit, Beijing, Peoples R China;

    Southwest Jiaotong Univ, Sch Informat Sci & Technol, Chengdu 610031, Sichuan, Peoples R China;

    Xidian Univ, Sch Comp Sci & Technol, Xian, Shaanxi, Peoples R China;

    Southwest Jiaotong Univ, Sch Informat Sci & Technol, Chengdu 610031, Sichuan, Peoples R China;

    Southwest Jiaotong Univ, Sch Informat Sci & Technol, Chengdu 610031, Sichuan, Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Convolutional neural networks; Spatio-temporal data; Residual learning; Crowd flows; Cloud;

    机译：卷积神经网络;时空数据;残差学习;人群流动;云计算;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号