Multi-attribute decision making for deep learning-based typhoon disaster assessment

被引:1
|
作者
Li, Dongmei [1 ]
Yang, Lehua [2 ,3 ]
Liu, Shaojun [4 ]
Tan, Ruipu [2 ,3 ]
机构
[1] Fujian Jiangxia Univ, Coll Foreign Languages, Fuzhou, Fujian, Peoples R China
[2] Fujian Jiangxia Univ, Coll Elect & Informat Sci, Fuzhou, Fujian, Peoples R China
[3] Res Inst Data Anal & Intelligent Decis Making, Fuzhou, Fujian, Peoples R China
[4] China Inst Sci & Technol Informat, Fuzhou, Fujian, Peoples R China
关键词
Deep learning; interval-valued neutrosophic numbers; multi-attribute decision making; typhoon disaster; MADM; SET;
D O I
10.3233/JIFS-235315
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Emergency rescue decisions in case of a typhoon disaster can be considered multi-attribute decision-making problems. Considering the need for the timeliness and authenticity of decision-making information sources after such a disaster, this study proposed using learning methods to process real-time online data and interval-valued neutrosophic numbers (NNs) to express the classification results. Using Typhoon Hagupit as an example, a trained text classification model was used to classify real-time data (online comments), following which the classification results were used as weights to convert these data into interval-valued NNs. Finally, the technique for order of preference by similarity to ideal solution (TOPSIS) method was adopted to rank the extent of damage caused by the typhoon in each region; the sorting results were consistent with the official statistical data, proving the effectiveness of the proposed method. A detailed sensitivity analysis was conducted to determine the optimal parameter settings of the classification model. Furthermore, the proposed method was compared with existing methods in terms of data conversion and deep learning efficiency; the results confirmed the superior capabilities of the proposed method. Notably, the proposed method can provide support to disaster management professionals in their post-disaster emergency relief work.
引用
收藏
页码:6657 / 6677
页数:21
相关论文
共 50 条
  • [41] A method of dynamic multi-attribute decision making based on variable weight
    Zhu, C.-X. (chuanxizhu@126.com), 1600, Northeast University (29):
  • [42] An algorithm for multi-attribute decision making based on soft rough sets
    Yu, Guangji
    JOURNAL OF COMPUTATIONAL ANALYSIS AND APPLICATIONS, 2016, 20 (07) : 1248 - 1258
  • [43] Multi-attribute fuzzy pattern decision making based on information systems
    Sun, Zhenduo
    Kong, Xiangzhi
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [44] Multi-attribute decision-making method based on design axioms
    College of Mechanical and Electrical Eng., Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
    不详
    Xinan Jiaotong Daxue Xuebao, 2008, 3 (392-397):
  • [45] Multi-attribute group decision making based on set pair analysis
    Yue, Rui
    Wang, Zhongbin
    Peng, Anhua
    International Journal of Advancements in Computing Technology, 2012, 4 (10) : 205 - 213
  • [46] Multi-Attribute Decision Making Method Based on Aggregated Neutrosophic Set
    Jiang, Wen
    Zhang, Zihan
    Deng, Xinyang
    SYMMETRY-BASEL, 2019, 11 (02):
  • [47] Hybrid multi-attribute decision making based on shadowed fuzzy numbers
    El-Hawy, Mohamed A. H.
    Wassif, Khaled T.
    Hefny, Hesham A.
    Hassan, Hesham A.
    2015 IEEE SEVENTH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND INFORMATION SYSTEMS (ICICIS), 2015, : 514 - 521
  • [48] Multi-attribute Group Decision Making Method Based on Evidence Theory
    Li, Yan-Ling
    Yan, Qi-Fei
    Wu, Jian-Wei
    2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2017, : 3043 - 3047
  • [49] Adaptive Exploration Strategy With Multi-Attribute Decision-Making for Reinforcement Learning
    Hu, Chunyang
    Xu, Meng
    IEEE ACCESS, 2020, 8 : 32353 - 32364
  • [50] A Group Decision Making Method Based on Mixed Multi-attribute and VIKOR
    Zhang Qi
    Cheng Pei-yuan
    2017 INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS, ELECTRONICS AND CONTROL (ICCSEC), 2017, : 1425 - 1429