入射(几何)
亲密度
学位(音乐)
数学
统计
计算机科学
几何学
声学
物理
数学分析
作者
Wenjie Dong,Sifeng Liu,Zhigeng Fang
出处
期刊:Grey systems
[Emerald (MCB UP)]
日期:2018-08-20
卷期号:8 (4): 448-461
被引量:16
标识
DOI:10.1108/gs-04-2018-0019
摘要
Purpose The purpose of this paper is to study the modelling mechanisms of several grey incidence analysis models with great influence, including Deng’s grey incidence model, absolute degree of grey incidence model, slope degree of incidence model, similitude degree of incidence model and closeness degree of incidence model; then analyse the problems to be solved in grey incidence analysis models; and clarify the applicable ranges of commonly used grey incidence models. Design/methodology/approach The paper comes to conclusions by means of comparable analysis. The authors compare several commonly used grey incidence analysis models, including Deng’s grey incidence model, absolute degree of grey incidence model, slope degree of incidence model, similitude degree of incidence model and closeness degree of incidence model and give several examples to clarify the reasons why quantitative analysis results of different models are not exactly the same. Findings As the intension of each kind of incidence model is clear and the extension is relatively obscure, grey incidence orders calculated by different incidence models are often different. When making actual decisions, incompatible results may appear. According to different characteristics of extraction, grey incidence analysis models can be divided into three types: incidence model based on closeness perspective, incidence model based on similarity perspective and incidence model based on comprehensive perspective. Practical implications The conclusions obtained in this paper can help people avoid some defects in the process of actual selection and choose the better incidence analysis model. Originality/value The conclusions can be used as a reference and basis for the selection of grey incidence analysis models, it can help to overcome the defects and shortcomings of models caused by themselves and screen out more excellent analytical models.
科研通智能强力驱动
Strongly Powered by AbleSci AI