Computer Engineering and Applications ›› 2017, Vol. 53 ›› Issue (13): 60-65.DOI: 10.3778/j.issn.1002-8331.1702-0027

Previous Articles     Next Articles

Sensitivity analysis on multiple attribute weight of geomagnetic map suitability evaluation based on WPM method

ZHU Zhanlong1,2, LI Jing3   

  1. 1.School of Information Engineering, Heibei GEO University, Shijiazhuang 050031, China
    2.Hebei Key Laboratory of Optoelectronic Information and Geo-Detection Technology, Heibei GEO University, Shijiazhuang 050031, China
    3.School of instrumentation Science and Opto-Electronics Engineering, Beihang University, Beijing 100191, China
  • Online:2017-07-01 Published:2017-07-12


朱占龙1,2,李  晶3   

  1. 1.河北地质大学 信息工程学院,石家庄 050031
    2.河北地质大学 河北省光电信息与地球探测技术重点实验室,石家庄 050031
    3.北京航空航天大学 仪器科学与光电工程学院,北京 100191

Abstract: The weight sensitivity of each index about geomagnetic map suitability is studied. Firstly, the indexes of geomagnetic map are presented such as standard deviation, roughness, correlation coefficient, entropy and cumulative gradient, subsequently the data processing strategy about positive indexes and negative indexes are discussed combined with Weighted Product Model(WPM), and then the change scope of weights is researched when maintains the order result unchanged and the smallest variation range of the weight of each index is deduced and further gets the weight sensitivity from the perspective of quantitative derivation. Lastly, a specific example is presented to solve the change scope of weights and the smallest variation range and sensitivity about the weight of each index, which provides a reference for decision makers.

Key words: sensitivity analysis, multiple attribute decision making, Weighted Product Model(WPM), geomagnetic suitability

摘要: 研究地磁图适配性分析中各指标权重灵敏度问题。给出常见的地磁图属性以及用于方案排序的WPM方法,讨论了在该方法下正向指标和负向指标的数据处理策略,在此基础上研究排序结果不变时属性权重的变化范围,并对使得两方案排序翻转的各指标权重最小变化区间进行定量推导,进而得到各指标权重灵敏度。最后,通过具体实例得到了属性权重变化范围和各指标权重最小变化区间及灵敏度,发现了对于两两方案排序翻转最敏感的指标,这为决策者在设定指标权重时提供一定参考和依据。

关键词: 灵敏度分析, 多属性决策, 加权模型(WPM), 地磁图适配性