基于FastDTW案例检索的台风灾害应急方案生成

doi:10.16265/j.cnki.issn1003-3033.2022.04.025

中国安全科学学报 ›› 2022, Vol. 32 ›› Issue (4): 171-176.doi: 10.16265/j.cnki.issn1003-3033.2022.04.025

基于FastDTW案例检索的台风灾害应急方案生成

陈莉婷¹^,²(), 郑晶¹^,², 高建清¹^,², 梁娟³

¹ 福建江夏学院电子信息科学学院,福建福州 350108
² 福建江夏学院数据分析与智能决策研究所,福建福州 350108
³ 福建江夏学院工商管理学院,福建福州 350108

收稿日期:2022-01-11 修回日期:2022-03-12 出版日期:2022-04-28 发布日期:2022-10-28
作者简介:
陈莉婷 (1977—),女,福建泉州人,硕士,讲师,主要从事智能决策、应急决策、匹配理论等方面的研究。E-mail: jasminechan@qq.com。
郑晶, 教授。
高建清, 副教授。
梁娟, 教授。
基金资助:
国家自然科学基金青年项目资助(71902034); 教育部人文社会科学研究项目(20YJC630229); 福建省自然科学基金资助(2021J011223); 校级科研项目(JXZ2021006)

Generation of typhoon emergency response plan based on FastDTW case retrieval

CHEN Liting¹^,²(), ZHENG Jing¹^,², GAO Jianqing¹^,², LIANG Juan³

¹ College of Electronics and Information Science, Fujian Jiangxia University, Fuzhou Fujian 350108, China
² Research Institute for Data Analysis and Intelligent Decision, Fujian Jiangxia University, Fuzhou Fujian 350108, China
³ College of Business Administration, Fujian Jiangxia University, Fuzhou Fujian 350108, China

Received:2022-01-11 Revised:2022-03-12 Online:2022-04-28 Published:2022-10-28

摘要/Abstract

摘要：

为提高台风案例检索的效率,研究台风灾害时空性、案例属性的重要性差异和信息完整性。通过FastDTW算法测算台风灾害时空轨迹相似度,构建与目标台风路径相似的历史案例集;为凸显不同案例属性间的重要性差异,采用关联系数标准差(CCSD)方法的优化模型来确定案例属性权重,并集结案例属性相似度,得到案例相似度;综合考虑时空轨迹相似度和基于灾害信息的案例相似度,检索相似历史案例集,得到最相似历史台风灾害,进而生成目标台风的应急方案;再对该方法进行实例应用。结果表明:该方法通过对台风的时空轨迹相似度测算、属性权重确定和信息合成,可检索到最相似历史案例,生成的应急方案更加全面、精确,贴近目标台风。

关键词: FastDTW, 案例检索, 台风灾害, 应急方案, 时空轨迹相似度, 关联系数标准差(CCSD)

Abstract:

In order to improve efficiency of typhoon case retrieval method, spatio-temporal nature of typhoon hazards and importance differences regarding case attributes and information integrity were studied. Spatio-temporal trajectory similarities were measured using FastDTW algorithm, and a set of historical cases similar to target typhoon path was established. To highlight importance differences between case attributes, an optimized model of CCSD method was used to determine attribute weights. Subsequently, case similarity was obtained by aggregating that of attributes. Then, considering spatio-temporal trajectory similarities and case similarities based on disaster information, the most similar case was retrieved from the set of historical cases, and an emergency plan regarding target typhoon trajectory was generated. Finally, the method was applied to real examples. The results show that the proposed method retrieves the most similar historical case by measuring spatio-temporal trajectory similarities of typhoons, determining attribute weights and synthesizing resulting information to ensure that the generated emergency plan is comprehensive and accurate with respect to the target typhoon.

Key words: fast dynamic time warping(FastDTW), case retrieval, typhoon, emergency plan, spatio-temporal trajectory similarity, correlation coefficient and standard deviation (CCSD)

陈莉婷, 郑晶, 高建清, 梁娟. 基于FastDTW案例检索的台风灾害应急方案生成[J]. 中国安全科学学报, 2022, 32(4): 171-176.

CHEN Liting, ZHENG Jing, GAO Jianqing, LIANG Juan. Generation of typhoon emergency response plan based on FastDTW case retrieval[J]. China Safety Science Journal, 2022, 32(4): 171-176.

图/表 9

图1

表1

表2

案例相似度和综合相似度

案例	$s i m (C 0, C l)$	U_l
C₁	0.579 5	0.260 0
C₂	0.604 2	0.256 4
C₃	0.791 5	0.349 1
C₄	0.611 3	0.268 0
C₅	0.602 1	0.279 7
C₆	0.717 7	0.272 1
C₇	0.673 5	0.283 7
C₈	0.717 2	0.294 5
C₉	0.586 5	0.215 8
C₁₀	0.699 3	0.271 6

表2

图2

图3

图4

表3

图5

表4

参考文献 14

[1]	央视财经. 2018年全国自然灾害基本情况:以洪涝、台风灾害为主[EB/OL]. [2021-07-27]. https://www.sohu.com/a/287573800_114960.
[2]	FAN Zhiping, LI Yonghai, WANG Xiaohuan, et al. Hybrid similarity measure for case retrieval in CBR and its application to emergency response towards gas explosion[J]. Expert Systems with Applications, 2014, 41(5): 2526-2534. doi: 10.1016/j.eswa.2013.09.051
[3]	ZHENG Jing, WANG Yingming, ZHANG Kai, et al. A dynamic emergency decision-making method based on group decision making with uncertainty information[J]. International Journal of Disaster Risk Science, 2020, 11(5): 667-679. doi: 10.1007/s13753-020-00308-4
[4]	郑晶, 王应明. 不完备信息条件下的应急案例检索方法[J]. 中国安全科学学报, 2018, 28(8): 186-191. doi: 10.16265/j.cnki.issn1003-3033.2018.08.031
	ZHENG Jing, WANG Yingming. Method for retrieving emergency cases under incomplete information condition[J]. China Safety Science Journal, 2018, 28(8):186-191. doi: 10.16265/j.cnki.issn1003-3033.2018.08.031
[5]	YU Xiaobing, LI Chenliang, ZHAO Wenxuan, et al. A novel case adaptation method based on differential evolution algorithm for disaster emergency[J]. Applied Soft Computing, 2020, 92: 1-12.
[6]	任斌, 朱昌锋, 钟校. 基于前景理论的应急物资需求动态调整模型[J]. 中国安全科学学报, 2018, 28(3): 179-184. doi: 10.16265/j.cnki.issn1003-3033.2018.03.031
	REN Bin, ZHU Changfeng, ZHONG Xiao. A PT based model for dynamic adjusting emergency material demand[J]. China Safety Science Journal, 2018, 28(3): 179-184. doi: 10.16265/j.cnki.issn1003-3033.2018.03.031
[7]	李永海, 樊治平, 李铭洋. 解决广义不确定型决策问题的案例决策方法[J]. 系统工程学报, 2014, 29(1): 21-29.
	LI Yonghai, FAN Zhiping, LI Mingyang. Case-based decision analysis method for general uncertain decision making problem[J]. Journal of Systems Engineering, 2014, 29(1): 21-29.
[8]	李永海, 樊治平, 袁媛. 考虑应急方案实施效果的突发事件应急方案生成方法[J]. 控制与决策, 2014, 29(2): 275-280.
	LI Yonghai, FAN Zhiping, YUAN Yuan. Method for generating emergency alternative with considering implementation effects of emergency alternatives[J]. Control and Decision, 2014, 29(2): 275-280.
[9]	宋英华, 吴昊, 刘丹, 等. 基于D-S证据理论的地震应急救援群决策[J]. 中国安全科学学报, 2020, 30(5): 163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
	SONG Yinghua, WU Hao, LIU Dan, et al. Group decision-making for earthquake emergency rescue plan based on D-S evidence theory[J]. China Safety Science Journal, 2020, 30(5): 163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
[10]	YAN Aijun, SHAO Hongshan, GUO Zhen. Weight optimization for case-based reasoning using membrane computing[J]. Information Sciences, 2014, 287(12) : 109-120. doi: 10.1016/j.ins.2014.07.043
[11]	WU Dengsheng, LI Jianping, BAO Chunbing. Case-based reasoning with optimized weight derived by particle swarm optimization for software effort estimation[J]. Soft Computing, 2018, 22(16) : 5299-5310. doi: 10.1007/s00500-017-2985-9
[12]	徐高扬, 郑海涛, 黄国庆, 等. 基于门控单元循环神经网络的台风路径预测[J]. 计算机应用与软件, 2019, 36(5): 125-131.
	XU Gaoyang, ZHENG Haitao, HUANG Guoqing, et al. Typhoon track prediction based on gated recurrent unit neural network[J]. Computer Applications and Software, 2019, 36(5): 125-131.
[13]	姬文江, 左元, 黑新宏, 等. 基于FastDTW的道岔故障智能诊断方法[J]. 模式识别与人工智能, 2020, 33(11): 1013-1022. doi: 10.16451/j.cnki.issn1003-6059.202011006
	JI Wenjiang, ZUO Yuan, HEI Xinhong, et al. An intelligent fault diagnosis method based on FastDTW for railway turnout[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(11): 1013-1022. doi: 10.16451/j.cnki.issn1003-6059.202011006
[14]	LU Xiaoqin, YU Hui, YING Ming, et al. Western north pacific tropical cyclone database created by the China meteorological administration[J]. Advances in Atmospheric Sciences, 2021, 38(4): 690-699. doi: 10.1007/s00376-020-0211-7

案例	台风编号	人生安全			经济损失		损害面积/hm²	天气情况		路径相似度
案例	台风编号	失踪人口	死亡人口	受伤人口	房屋损坏/万间	直接经济损失/亿元	损害面积/hm²	最大风力/级	最大风速/ (m·s^-1)	路径相似度
C₁	1213	0	0	213.7	0.3	25.6	24.9	13	38	663
C₂	1319	1	30	981	1.1	235.5	25	14	45	709
C₃	1208	0	11	96.6	0.1	18.7	6.4	14	45	677
C₄	1714	0	0	7.8	0	0.5	0.2	11	30	682
C₅	1823	0	0	6.3	0	0.5	0.6	10	25	634
C₆	809	0	3	194.5	0.8	6.04	6.17	10	25	802
C₇	1604	0	0	49.6	0.04	5.9	4.1	11	30	715
C₈	906	0	0	104.63	0.04	4.65	4.24	13	38	736
C₉	714	2.86	0	19.79	1	0.35	0.03	8	20	827
C₁₀	915	6	13	167.82	0.45	23.93	10.35	12	35	782
C₀	1713	0	13	142.4	0.1	273.6	6.4	14	48	—

方法	人生安全	经济损失	损害面积	天气情况
文中	0.244 8	0.299 3	0.300 4	0.155 4
结果	C₃> C₈> C₇> C₅> C₆> C₁₀> C₄> C₁> C₂> C₉
平均	0.250 0	0.250 0	0.250 0	0.250 0
结果	C₃> C₈> C₇> C₅> C₁> C₁₀> C₄> C₂> C₆> C₉
熵权	0.051 8	0.702 9	0.114 6	0.130 6
结果	C₂> C₃> C₁> C₈> C₅> C₇> C₄> C₁₀> C₆> C₉

方案	1713	714	1208
受灾地点	广东、香港、澳门	香港、澳门、海南	广东、香港、澳门
应急响应级别	Ⅲ	Ⅳ	Ⅲ
防御措施	组织渔船返港、渔民上岸避风、发布台风预警信息等	组织渔船返港、渔民上岸避风、发布台风预警信息等	组织渔船返港、渔民上岸避风、发布台风预警信息等

基于FastDTW案例检索的台风灾害应急方案生成

Generation of typhoon emergency response plan based on FastDTW case retrieval

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 14

相关文章 2

编辑推荐

Metrics

本文评价

[1]	尹念红，王增强，蒲云. 面向公共工程突发事件的语言信息应急决策方法[J]. 中国安全科学学报, 2013, 23(5): 161-.
[2]	尹念红，王增强，蒲云. 面向突发事件衰退期的应急方案决策方法[J]. 中国安全科学学报, 2013, 23(12): 153-.