首页> 外文期刊>Grey systems: theory and application >Two-stage grey cloud clustering model for drought risk assessment
【24h】

Two-stage grey cloud clustering model for drought risk assessment

机译:干旱风险评估的两阶段灰云聚类模型

获取原文
获取原文并翻译 | 示例
       

摘要

Purpose - The purpose of this paper is to establish a two-stage grey cloud clustering model to assess the drought risk level of 18 prefecture-level cities in Henan Province. Design/methodology/approach - The clustering process is divided into two stages. In the first stage, grey cloud clustering coefficient vectors are obtained by grey cloud clustering. In the second stage, with the help of the weight kernel clustering function, the general representation of the weight vector group of kernel clustering is given. And a new coefficient vector of kernel clustering that integrates the support factors of the adjacent components was obtained in this stage. The entropy resolution coefficient of grey cloud clustering coefficient vector is set as the demarcation line of the two stages, and a two-stage grey cloud clustering model, which combines grey and randomness, is proposed. Findings - This paper demonstrates that 18 cities in Henan Province are divided into five categories, which are in accordance with five drought hazard levels. And the rationality and validity of this model is illustrated by comparing with other methods. Practical implications - This paper provides a practical and effective new method for drought risk assessment and, then, provides theoretical support for the government and production departments to master drought information and formulate disaster prevention and mitigation measures. Originality/value - The model in this paper not only solves the problem that the result and the rule of individual subjective judgment are always inconsistent owing to not fully considering the randomness of the possibility function, but also solves the problem that it's difficult to ascertain the attribution of decision objects, when several components of grey clustering coefficient vector tend to be balanced. It provides a new idea for the development of the grey clustering model. The rationality and validity of the model are illustrated by taking 18 cities in Henan Province as examples.
机译:目的-本文的目的是建立一个两阶段的灰色云聚类模型来评估河南省18个地级市的干旱风险水平。设计/方法/方法-聚类过程分为两个阶段。在第一阶段,通过灰云聚类获得灰云聚类系数矢量。在第二阶段,借助权重核聚类函数,给出了核聚类的权重向量组的一般表示。在此阶段,获得了一个新的核聚类系数向量,该向量融合了相邻成分的支持因子。将灰云聚类系数矢量的熵分辨率系数设置为两阶段的分界线,提出了一种将灰阶和随机性相结合的两阶段灰云聚类模型。调查结果-本文证明,河南省的18个城市根据五个干旱灾害等级分为五个类别。通过与其他方法的比较说明了该模型的合理性和有效性。实际意义-本文为干旱风险评估提供了一种实用有效的新方法,然后为政府和生产部门掌握干旱信息并制定防灾减灾措施提供了理论支持。独创性/价值-本文模型不仅解决了由于没有充分考虑可能性函数的随机性而导致主观判断的结果和规则始终不一致的问题,而且解决了难以确定概率的问题。当灰色聚类系数向量的几个分量趋于平衡时,决策对象的归属。它为灰色聚类模型的发展提供了新思路。以河南省18个城市为例,说明了该模型的合理性和有效性。

著录项

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