Construction and application of management system of urban emergency shelters

doi:10.16265/j.cnki.issn 1003-3033.2021.12.020

Abstract

Abstract: In order to develop a more scientific management system of urban emergency shelters, ArcGIS was used to collect quantitative data of 36 shelters in Chengdu according to 7 indicators such as effective area. Then, ward method was applied to cluster them systematically, and 3 types of them were showed to be suitable according to results. Finally, characteristics and differences of these 3 types were analyzed, and dimensions of indexes were reduced by using principal component method so as to draw a characteristic scatter plot of these shelters. The results show that these 3 types of emergency shelters play a role of hub, core and supplement in urban earthquake disaster reduction, and they constitute an olive-shaped urban emergency shelter system.In order to apply this system, nonlinear classification model is obtained by BP neural network algorithm. The training set loss function converges after about 800 iterations, and classification accuracy of both training set and test set can reach as high as 100%.

Key words: emergency shelters, Ward method, BP neural network, classification, principal component

CLC Number:

X928.04

WANG Haibiao, CHEN Haichao, LI Rui, YU He, ZHAO Tianyi. Construction and application of management system of urban emergency shelters[J]. China Safety Science Journal, 2021, 31(12): 153-159.

References

[1] 李霞.今年我市将再增42个应急避难场所[EB/OL].(2016-07-25).https://www.163.com/news/article/BSPO2JR500014AED.html.
[2] 刘朝峰,杜金泽,张嘉鑫,等.基于RAGA-PP模型的城市应急避难场所适宜性分析[J].灾害学,2020,35(2):80-84.
LIU Chaofeng, DU Jinze, ZHANG Jiaxin, et al. Analysis of the suitability of urban emergency shelter based on RAGA-PP model [J]. Journal of Catastrophology, 2020,35(2):80-84.
[3] CHU Jianyu, SU Youpo. The application of TOPSIS method in selecting fixed seismic shelter for evacuation in cities [J]. Systems Engineering Procedia, 2012,3:391-397.
[4] 张宣峰,于善初,张晓飞.多目标约束下的固定避难场所选址优化[J].城市发展研究,2020,27(8):59-66.
ZHANG Xuanfeng, YU Shanchu, ZHANG Xiaofei. Optimized location model of resident emergency congregate shelter based on multi-objective constraints [J]. Urban Development Studies,2020,27(8):59-66.
[5] 国务院.国务院关于进一步加强防震减灾工作的意见[Z].2010-06-09.
[6] 李亦纲,吴建春,王忠国,等.地震安全示范社区建设标准研究[J].震灾防御技术,2015,10(3):621-628.
LI Yigang, WU Jianchun, WANG Zhongguo, et al. Standard of building demonstration earthquake safety community [J]. Technology for Earthquake Disaster Prevention,2015,10(3):621-628.
[7] 蒋蓉.城乡统筹背景下成都市地震应急避难场所规划研究[D].成都:西南交通大学,2012.
JIANG Rong. Research on the emergency shelter plam of Chendu uner the background of urban-rural intergration [D]. Chengdu:Southwest Jiaotong University,2012.
[8] 徐相友,鞠晓峰,张悦,等.辉河自然保护区草地群落类型聚类分析[J].黑龙江畜牧兽医,2016(5):53-57.
XU Xiangyou, JU Xiaofeng, ZHANG Yue, et al. Clustering analysis of the grassland community types in Huihe nature reserve [J]. Heilongjiang Animal Science and Veterinary Medicine,2016(5):53-57.
[9] 赵秀红.基于主成分分析的特征提取的研究[D].西安:西安电子科技大学,2016.
ZHAO Xiuhong. Research on feature extraction based on principal component analysis [D]. Xi'an:Xidian University,2016.
[10] 戴健非,杨鹏,诸利一,等.集成PCA和LSTM神经网络的浸润线预测方法[J].中国安全科学学报,2020,30(3):94-101.
DAI Jianfei, YANG Peng, ZHU Liyi, et al. A PCA-LSTM neuralnetwork-integrated method for phreatic line prediction [J]. China Safety Science Journal,2020,30(3):94-101.
[11] 林海明.如何用SPSS软件一步算出主成分得分值[J].统计与信息论坛,2007(5):15-17.
LIN Haiming. How to use SPSS software calculate the value of the principal component scores in one step [J]. Statistics & Information Forum,2007(5):15-17.
[12] LOW C, PARK J, TEOH A. Stacking-based deep neural network: deep analytic network for pattern classification[J]. IEEE Transactionson Cybernetics, 2019,50(12):5 021-5 034.
[13] 林海飞,高帆,严敏,等.煤层瓦斯含量PSO-BP神经网络预测模型及其应用[J].中国安全科学学报,2020,30(9):80-87.
LIN Haifei, GAO Fan, YANG Min,et al. Studyon PSO-BP neural network prediction method of coal seam gas conten tand its application[J]. China Safety Science Journal,2020,30(9):80-87.
[14] IMRAN K, AMELIA R, SYED Q. Adam optimization algorithm for wide and deep neural network[J]. Knowledge Engineering and Data Science,2019,2(1):41-46.
[15] 胡瑾秋,张尚尚,曾然,等.基于深度学习的页岩气压裂砂堵事故预警方法[J].中国安全科学学报,2020,30(9):108-114.
HU Jinqiu, ZHANG Shangshang, ZENG Ran, et al. Early warning method for sand plugging accidents in shale gas fracturing based on deep learning [J]. China Safety Science Journal,2020,30(9):108-114.
[16] 章敏敏,徐和平,王晓洁,等.谷歌TensorFlow机器学习框架及应用[J].微型机与应用,2017,36(10):58-60.
ZHANG Minmin, XU Heping, WANG Xiaojie. Application of Google TensorFlow machine learning framework [J]. Microcomputer & Its Applications,2017,36(10):58-60.