Practical approach to evacuation planning via network flow and deep learning

Akira Tanaka, Nozomi Hata, Nariaki Tateiwa, Katsuki Fujisawa

    研究成果: Chapter in Book/Report/Conference proceedingConference contribution

    4 被引用数 (Scopus)

    抄録

    In this paper, we propose a practical approach to evacuation planning by utilizing network flow and deep learning algorithms. In recent years, large amounts of data are rapidly being stored in the cloud system, and effective data utilization for solving real-world problems is required more than ever. Hierarchical Data Analysis and Optimization System (HDAOS) enables us to select appropriate algorithms according to the degree of difficulty in solving problems and a given time for the decision-making process, and such selection helps address real-world problems. In the field of emergency evacuation planning, however, the Lexicographically Quickest Flow (LQF) algorithm has an extremely long computation time on a large-scale network, and is therefore not a practical solution. For Osaka city, which is the second-largest city in Japan, we must solve the maximum flow problems on a large-scale network with over 8.3M nodes and 32.8M arcs for obtaining an optimal plan. Consequently, we can feed back nothing to make an evacuation plan. To solve the problem, we utilize the optimal solution as training data of a deep Convolutional Neural Network (CNN). We train a CNN by using the results of the LQF algorithm in normal time, and in emergencies predict the evacuation completion time (ECT) immediately by the well-learned CNN. Our approach provides almost precise ECT, achieving an average regression error of about 2%. We provide several techniques for combining LQF with CNN and addressing numerous movements as CNN's input, which has rarely been considered in previous studies. Hodge decomposition also demonstrates that LQF is efficient from the standpoint of the total distance traveled by all evacuees, which reinforces the validity of the method of utilizing the LQF algorithm for deep learning.

    本文言語英語
    ホスト出版物のタイトルProceedings - 2017 IEEE International Conference on Big Data, Big Data 2017
    編集者Jian-Yun Nie, Zoran Obradovic, Toyotaro Suzumura, Rumi Ghosh, Raghunath Nambiar, Chonggang Wang, Hui Zang, Ricardo Baeza-Yates, Ricardo Baeza-Yates, Xiaohua Hu, Jeremy Kepner, Alfredo Cuzzocrea, Jian Tang, Masashi Toyoda
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ3368-3377
    ページ数10
    ISBN(電子版)9781538627143
    DOI
    出版ステータス出版済み - 7 1 2017
    イベント5th IEEE International Conference on Big Data, Big Data 2017 - Boston, 米国
    継続期間: 12 11 201712 14 2017

    出版物シリーズ

    名前Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017
    2018-January

    その他

    その他5th IEEE International Conference on Big Data, Big Data 2017
    国/地域米国
    CityBoston
    Period12/11/1712/14/17

    All Science Journal Classification (ASJC) codes

    • コンピュータ ネットワークおよび通信
    • ハードウェアとアーキテクチャ
    • 情報システム
    • 情報システムおよび情報管理
    • 制御と最適化

    フィンガープリント

    「Practical approach to evacuation planning via network flow and deep learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル