您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（理学版）》

《山东大学学报(理学版)》 ›› 2023, Vol. 58 ›› Issue (7): 67-79.doi: 10.6040/j.issn.1671-9352.4.2022.9768

•   • 上一篇    下一篇

可拓序贯三支决策模型及应用

王君宇1,2,3(),杨亚锋1,2,3,薛静轩1,李丽红1,2,3,*()   

  1. 1. 华北理工大学理学院, 河北 唐山 063210
    2. 河北省数据科学与应用重点实验室, 河北 唐山 063210
    3. 唐山市工程计算重点实验室, 河北 唐山 063210
  • 收稿日期:2022-08-09 出版日期:2023-07-20 发布日期:2023-07-05
  • 通讯作者: 李丽红 E-mail:1784557362@qq.com;22687426@qq.com
  • 作者简介:王君宇(1996—), 女, 硕士研究生, 研究方向为数据挖掘、三支决策等. E-mail: 1784557362@qq.com
  • 基金资助:
    河北省数据科学与应用重点实验室项目(10120201);唐山市数据科学重点实验室项目(10120301)

Extension sequential three-way decision model and its application

Junyu WANG1,2,3(),Yafeng YANG1,2,3,Jingxuan XUE1,Lihong LI1,2,3,*()   

  1. 1. College of Science, North China University of Science and Technology, Tangshan 063210, Hebei, China
    2. Hebei Province Key Laboratory of Data Science and Application, Tangshan 063210, Hebei, China
    3. Tangshan Key Laboratory of Engineering Computing, Tangshan 063210, Hebei, China
  • Received:2022-08-09 Online:2023-07-20 Published:2023-07-05
  • Contact: Lihong LI E-mail:1784557362@qq.com;22687426@qq.com

RichHTML

1

PDF (PC)

280

摘要：

将可拓评价基本方法与“三分而治”决策思想融合, 引入序贯思想, 构建可拓序贯三支决策模型, 实现动态决策与挖掘优化指标的目的。首先, 对数据进行标准化处理, 计算属性的权重; 其次, 将可拓评价方法作为三支决策的评价准则, 定义新的决策规则, 阐释划分3个域的合理性; 然后, 根据属性权重得到多个粒度的序贯评价属性, 进行多阶段三支决策, 给出决策结果; 最后, 根据决策结果对引起样本划分变化的指标进行分析, 并提出优化建议。将模型应用于水资源承载力分析领域, 与熵权物元可拓决策模型进行对比。结果表明, 运用可拓序贯三支决策模型与熵权物元可拓决策模型所得的评价结果基本一致, 准确率达84.55%, 验证了模型的有效性和实用性。

关键词: 序贯三支决策, 可拓评价, 粒化, 水资源承载力

Abstract:

The basic method of extension evaluation and the "rule by three divisions" decision-making idea are integrated, and the sequential idea is introduced to construct an extension sequential three-way decision model and realize the purpose of dynamic decision-making and mining optimization indicators. Firstly, the data is standardized and the weight of attributes is calculated. The extension evaluation method is used as the evaluation criterion of the three-way decisions, new decision rules are defined, and the rationality of dividing the three domains is explained. Then, according to the attribute weight, the sequential evaluation attributes of multiple granularity are obtained, the multi-stage three-way decision is made, and the decision results are given. Finally, according to the decision-making results, the indicators that cause changes in sample division are analyzed, and optimization suggestions are put forward. The model was applied to the analysis of water resources carrying capacity, and compared with the entropy weight matter-element extension decision-making model. The results show that the evaluation results obtained by using the extension sequential three-way decision model and the entropy weight matter-element extension decision-making model are basically consistent, the accuracy rate reaches 84.55%, which verifies the validity and practicability of the model.

Key words: sequential three-way decision, extension evaluation, granulation, carrying capacity of water resource

中图分类号: 

  • TP181

图1

三支决策框架图"

表1

长江经济带水资源承载力评价等级及标准"

评价指标 性质 评价等级及标准值
Ⅰ Ⅱ Ⅲ Ⅳ Ⅴ
人均水资源量/m3 正 80~500 500~1 000 1 000~2 000 2 000~3 000 3 000~5 500
农业用水占比/% 负 60~100 55~60 50~55 30~50 0~30
生活用水占比/% 正 0~4 4~5 5~7 7~10 10~100
人均库容量/m3 正 0~200 200~400 400~600 600~800 800~2 200
生态环境用水占比/% 正 0~1 1~2 2~3 3~5 5~10
污水处理率/% 正 0~40 40~50 50~80 80~95 95~100
万元GDP化学需氧量排放量/kg 负 3~7 2~3 1~2 0.5~1 0~0.5
建成区绿化覆盖率/% 正 0~20 20~30 30~35 35~40 40~50
森林覆盖率/% 正 0~10 10~20 20~40 40~50 50~100
湿地总面积占国土面积比重/% 正 0~2 2~4 4~6 6~8 8~74
造林面积/hm2 正 0~60 000 60 000~170 000 170 000~280 000 280 000~480 000 480 000~720 000
第一产业占GDP比值/% 负 20~15 13~15 10~13 5~10 0~5
第二产业占GDP比值/% 负 52~56 48~52 44~48 40~44 0~40
农业灌溉亩均用水量/m3 负 800~1 000 600~800 400~600 200~400 0~200

表2

各指标权重"

符号指标权重
c1 湿地总面积占国土面积比重/% 0.099 0
c2 森林覆盖率/% 0.093 7
c3 造林面积/hm2 0.092 4
c4 生活用水占比/% 0.087 6
c5 农业用水占比/% 0.087 1
c6 人均库容量/m3 0.083 7
c7 第一产业占GDP比值/% 0.082 2
c8 万元GDP化学需氧量排放量/kg 0.075 5
c9 人均水资源量/m3 0.072 9
c10 第二产业占GDP比值/% 0.064 8
c11 生态环境用水占比/% 0.057 5
c12 农业灌溉亩均用水量/m3 0.052 9
c13 污水处理率/% 0.026 4
c14 建成区绿化覆盖率/% 0.024 3

表3

2018年长江经济带水资源承载力指标与等级的关联度"

省级行政区 评价指标 关联度
K1(x0) K2(x0) K3(x0) K4(x0) K5(x0)
上海 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.223 5 0.404 0 -0.298 0 -0.649 0 -0.719 2
江苏 c1 -0.481 1 -0.460 8 -0.438 8 -0.414 9 0.295 6
c2 -0.254 9 0.480 0 -0.240 0 -0.620 0 -0.696 0
浙江 c1 -0.449 5 -0.387 8 -0.310 4 -0.210 6 0.044 1
c2 -0.549 2 -0.492 9 -0.323 8 -0.188 6 0.188 6
安徽 c1 -0.422 6 -0.316 8 -0.163 7 0.270 0 -0.067 5
c2 -0.394 3 -0.231 9 0.432 5 -0.283 8 -0.427 0
江西 c1 -0.387 6 -0.210 1 0.275 0 -0.091 7 -0.318 8
c2 -0.568 4 -0.514 5 -0.352 7 -0.223 2 0.223 2
湖北 c1 -0.426 1 -0.326 7 -0.185 5 0.115 0 -0.028 8
c2 -0.427 8 -0.331 1 0.019 5 -0.009 8 -0.207 8
湖南 c1 -0.368 8 -0.144 1 0.405 0 -0.198 3 -0.398 8
c2 -0.444 1 -0.374 0 -0.163 2 0.031 0 -0.006 2
重庆 c1 -0.168 9 0.255 0 -0.372 5 -0.581 7 -0.686 3
c2 -0.434 4 -0.349 0 -0.067 3 0.311 0 -0.137 8
四川 c1 -0.308 4 0.195 0 -0.097 5 -0.398 3 -0.548 8
c2 -0.424 3 -0.321 6 0.098 5 -0.049 3 -0.239 4
贵州 c1 0.405 0 -0.405 0 -0.702 5 -0.801 7 -0.851 3
c2 -0.435 5 -0.351 9 -0.079 3 0.377 0 -0.124 6
云南 c1 0.285 0 -0.285 0 -0.642 5 -0.761 7 -0.821 3
c2 -0.500 4 -0.438 0 -0.250 7 -0.100 8 0.100 8

表4

2009—2018年上海水资源承载力指标与等级的关联度"

年份 评价指标 关联度
K1(x0) K2(x0) K3(x0) K4(x0) K5(x0)
2009 c1 -0.717 8 -0.709 7 -0.701 2 -0.692 1 0.307 9
c2 0.059 0 -0.059 0 -0.529 5 -0.764 8 -0.811 8
2010 c1 -0.717 8 -0.709 7 -0.701 2 -0.692 1 0.307 9
c2 0.059 0 -0.059 0 -0.529 5 -0.764 8 -0.811 8
2011 c1 -0.717 8 -0.709 7 -0.701 2 -0.692 1 0.307 9
c2 0.059 0 -0.059 0 -0.529 5 -0.764 8 -0.811 8
2012 c1 -0.717 8 -0.709 7 -0.701 2 -0.692 1 0.307 9
c2 0.059 0 -0.059 0 -0.529 5 -0.764 8 -0.811 8
2013 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.064 5 0.074 0 -0.463 0 -0.731 5 -0.785 2
2014 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.064 5 0.074 0 -0.463 0 -0.731 5 -0.785 2
2015 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.064 5 0.074 0 -0.463 0 -0.731 5 -0.785 2
2016 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.064 5 0.074 0 -0.463 0 -0.731 5 -0.785 2
2017 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.064 5 0.074 0 -0.463 0 -0.731 5 -0.785 2
2018 c1 -0.989 9 -0.989 6 -0.989 3 -0.988 9 0.011 1
c2 -0.223 5 0.404 0 -0.298 0 -0.649 0 -0.719 2

表5

2018年长江经济带水资源承载力评价值"

省级行政区 综合关联度 等级
K1(xi) K2(xi) K3(xi) K4(xi) K5(xi)
上海 -0.617 2 -0.312 0 -0.653 2 -0.823 7 -0.344 0 Ⅱ
江苏 -0.371 1 -0.003 4 -0.342 1 -0.514 6 -0.186 5 Ⅱ
浙江 -0.498 0 -0.438 9 -0.316 9 -0.199 9 0.114 4 Ⅴ
安徽 -0.408 8 -0.275 5 0.126 2 0.000 8 -0.242 3 Ⅲ
江西 -0.475 6 -0.358 1 -0.030 2 -0.155 6 -0.055 2 Ⅲ
湖北 -0.426 9 -0.328 9 -0.085 8 0.054 3 -0.115 8 Ⅳ
湖南 -0.405 4 -0.255 9 0.128 7 -0.086 8 -0.207 9 Ⅲ
重庆 -0.298 0 -0.038 7 -0.224 1 -0.147 6 -0.419 6 Ⅱ
四川 -0.364 8 -0.056 2 -0.002 2 -0.228 6 -0.398 3 Ⅲ
贵州 -0.003 7 -0.379 2 -0.399 5 -0.228 6 -0.497 9 Ⅰ
云南 -0.096 9 -0.359 4 -0.452 0 -0.440 3 -0.372 9 Ⅰ

表6

2009—2018年上海水资源承载力评价值"

年份 综合关联度 等级
K1(xi) K2(xi) K3(xi) K4(xi) K5(xi)
2009 -0.340 1 -0.393 3 -0.617 7 -0.727 4 -0.236 5 Ⅴ
2010 -0.340 1 -0.393 3 -0.617 7 -0.727 4 -0.236 5 Ⅴ
2011 -0.340 1 -0.393 3 -0.617 7 -0.727 4 -0.236 5 Ⅴ
2012 -0.340 1 -0.393 3 -0.617 7 -0.727 4 -0.236 5 Ⅴ
2013 -0.539 9 -0.472 4 -0.733 4 -0.863 8 -0.376 1 Ⅴ
2014 -0.539 9 -0.472 4 -0.733 4 -0.863 8 -0.376 1 Ⅴ
2015 -0.539 9 -0.472 4 -0.733 4 -0.863 8 -0.376 1 Ⅴ
2016 -0.539 9 -0.472 4 -0.733 4 -0.863 8 -0.376 1 Ⅴ
2017 -0.539 9 -0.472 4 -0.733 4 -0.863 8 -0.376 1 Ⅴ
2018 -0.617 2 -0.312 0 -0.653 2 -0.823 7 -0.344 0 Ⅱ

图2

第一次水资源承载力决策结果"

图3

第二次水资源承载力决策结果"

图4

第三次水资源承载力决策结果"

图5

第四次水资源承载力决策结果"

图6

第五次水资源承载力决策结果"

图7

第六次水资源承载力决策结果"

图8

第七次水资源承载力决策结果"

图9

决策结果对比"

1 刘盾, 李天瑞, 杨新, 等. 三支决策-基于粗糙集与粒计算研究视角[J]. 智能系统学报, 2019, 14 (6): 1111- 1120.
LIU Dun , LI Tianrui , YANG Xin , et al. Three-way decisions: research perspectives for rough sets and granular computing[J]. CAAI Transactions on Intelligent Systems, 2019, 14 (6): 1111- 1120.
2 杨新, 李天瑞, 刘盾, 等. 基于决策粗糙集的广义序贯三支决策方法[J]. 计算机科学, 2018, 45 (10): 1- 5.
doi: 10.11896/j.issn.1002-137X.2018.10.001
YANG Xin , LI Tianrui , LIU Dun , et al. Generalized sequential three-way decisions approach based on decision-theoretic rough sets[J]. Computer Science, 2018, 45 (10): 1- 5.
doi: 10.11896/j.issn.1002-137X.2018.10.001
3 CHEN Wenbin , ZHANG Qinghua , DAI Yongyang . Sequential multi-class three-way decisions based on cost-sensitive learning[J]. International Journal of Approximate Reasoning, 2022, 146, 47- 61.
doi: 10.1016/j.ijar.2022.03.009
4 邢颖, 李德玉, 王素格. 代价敏感的序贯三支决策方法[J]. 计算机科学, 2018, 45 (10): 6- 10.
XING Ying , LI Deyu , WANG Suge . Cost-sensitive sequential three-way decision making method[J]. Computer Science, 2018, 45 (10): 6- 10.
5 JU Hengrong , PEDRYCZ W , LI Huaxiong , et al. Sequential three-way classifier with justifiable granularity[J]. Knowledge-Based Systems, 2019, 163, 103- 119.
doi: 10.1016/j.knosys.2018.08.022
6 ZHANG Qinghua , PANG Guohong , WANG Guoyin . A novel sequential three-way decisions model based on penalty function[J]. Knowledge-Based Systems, 2020, 192, 105350.
doi: 10.1016/j.knosys.2019.105350
7 钱进, 汤大伟, 洪承鑫. 多粒度层次序贯三支决策模型研究[J]. 山东大学学报(理学版), 2022, 57 (9): 33- 45.
QIAN Jin , TANG Dawei , HONG Chengxin . Research on multi-granularity hierarchical sequential three-way decision model[J]. Journal of Shandong University (Natural Science), 2022, 57 (9): 33- 45.
8 QIAN Jin , DANG Chuangyin , YUE Xiaodong , et al. Attribute reduction for sequential three-way decisions under dynamic granulation[J]. International Journal of Approximate Reasoning, 2017, 85, 196- 216.
doi: 10.1016/j.ijar.2017.03.009
9 张清华, 庞国弘, 李新太, 等. 基于代价敏感的序贯三支决策最优粒度选择方法[J]. 电子与信息学报, 2021, 43 (10): 3001- 3009.
doi: 10.11999/JEIT200821
ZHANG Qinghu , PANG Guohong , LI Xintai , et al. Optimal granularity selection method based on cost-sensitive sequential three-way decisions[J]. Journal of Electronics and Information Technology, 2021, 43 (10): 3001- 3009.
doi: 10.11999/JEIT200821
10 SAVCHENKO A V . Sequential three-way decisions in multi-category image recognition with deep features based on distance factor[J]. Information Sciences, 2019, 489, 18- 36.
doi: 10.1016/j.ins.2019.03.030
11 蔡文. 可拓集合和不相容问题[J]. 科学探索学报, 1983, (1): 83- 97.
CAI Wen . Extension set and non-compatible problems[J]. Science Exploration, 1983, (1): 83- 97.
12 杨春燕, 蔡文, 涂序彦. 可拓学的研究、应用与发展[J]. 系统科学与数学, 2016, 36 (9): 1507- 1512.
YANG Chunyan , CAI Wen , TU Xuyan . Research, application and development on extenics[J]. Journal of Systems Science and Mathematical Sciences, 2016, 36 (9): 1507- 1512.
13 LIU Shiliang , LI Wenping . Indicators sensitivity analysis for environmental engineering geological patterns caused by underground coal mining with integrating variable weight theory and improved matter-element extension model[J]. The Science of the Total Environment, 2019, 686, 606- 618.
doi: 10.1016/j.scitotenv.2019.04.393
14 SHAN Chengju , DONG Zengchuan , LU Debao , et al. Study on river health assessment based on a fuzzy matter-element extension model[J]. Ecological Indicators, 2021, 127 (10): 107742.
15 付光辉, 刘万山. 基于物元可拓模型的城市生态化水平评价——以江浙两省城市群为例[J]. 生态经济, 2021, 37 (11): 86- 91.
FU Guanghui , LIU Wanshan . Evaluation of urban ecological level based on the object meta-topological model: taking city clusters in Jiangsu and Zhejiang Provinces as an example[J]. Ecological Economy, 2021, 37 (11): 86- 91.
16 李东印, 孙凯旋, 王伸, 等. 基于熵权-可拓理论的智能化综采工作面安全评价[J]. 河南理工大学学报(自然科学版), 2022, 41 (3): 1- 9.
LI Dongyin , SUN Kaixuan , WANG Shen , et al. Study on safety evaluation of intelligence working face based on extension theory with entropy weight approach[J]. Journal of Henan Polytechnic University (Natural Science Edition), 2022, 41 (3): 1- 9.
17 YANG X , LI T R , FUJITA H , et al. A unified model of sequential three-way decisions and multilevel incremental processing[J]. Knowledge-Based Systems, 2017, 134, 172- 188.
18 王伟, 刘丹娜, 彭第. 基于熵值法的砂卵石地层深基坑开挖安全可拓评价[J]. 西南交通大学学报, 2021, 56 (4): 785- 791.
WANG Wei , LIU Danna , PENG Di . Extension evaluation on excavation safety of deep foundation pit in sandy cobble stratum based on entropy method[J]. Journal of Southwest Jiaotong University, 2021, 56 (4): 785- 791.
19 蔡文. 物元模型及其应用[M]. 北京: 科学技术文献出版社, 1994: 21- 25.
CAI Wen . Matter element model and its application[M]. Beijing: Scientific and Technical Documentation Press, 1994: 21- 25.
20 李敏, 杨亚锋, 雷宇, 等. 基于可拓域变化代价最小的最优粒度选择[J]. 山东大学学报(理学版), 2021, 56 (2): 17- 27.
LI Min , YANG Yafeng , LEI Yu , et al. Optimal granularity selection based on minimum cost of extension domain change[J]. Journal of Shandong University (Natural Science), 2021, 56 (2): 17- 27.
21 CUI Yi , FENG Ping , JIN Juliang , et al. Water resources carrying capacity evaluation and diagnosis based on set pair analysis and improved the entropy weight method[J]. Entropy, 2018, 20 (5): 359.
22 何刚, 夏业领, 秦勇, 等. 长江经济带水资源承载力评价及时空动态变化[J]. 水土保持研究, 2019, 26 (1): 287- 292.
HE Gang , XIA Yeling , QIN Yong , et al. Evaluation and spatial-temporal dynamic change of water resources carrying capacity in the Yangtze River Economic Belt[J]. Research of Soil and Water Conservation, 2019, 26 (1): 287- 292.
23 杨亚锋, 王红瑞, 巩书鑫, 等. 可变勾股模糊VIKOR水资源系统韧性评价调控模型及应用[J]. 水利学报, 2021, 52 (6): 633- 646.
YANG Yafeng , WANG Hongrui , GONG Shuxin , et al. Variable pythagorean fuzzy VIKOR evaluation regulation model of water resources system resilience and its application[J]. Journal of Hydraulic Engineering, 2021, 52 (6): 633- 646.
24 郭嘉伟, 张军, 陈彦. 基于熵权可拓物元模型的会宁县水土资源承载力评价[J]. 甘肃农业大学学报, 2018, 53 (6): 195- 203.
GUO Jiawei , ZHANG Jun , CHEN Yan . Water and soil resources matching patterns and carrying capacity in Huining County[J]. Journal of Gansu Agricultural University, 2018, 53 (6): 195- 203.
[1] 杨洁,罗天,李阳军. 基于TOPSIS的无标签序贯三支决策模型[J]. 《山东大学学报(理学版)》, 2022, 57(3): 41-48.
[2] 李敏,杨亚锋,雷宇,李丽红. 基于可拓域变化代价最小的最优粒度选择[J]. 《山东大学学报(理学版)》, 2021, 56(2): 17-27.
[3] 李善评,肖乃东,赵玉晓 . 硝酸铈对污泥胞外多聚物及污泥颗粒化的影响[J]. J4, 2008, 43(1): 24-27 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 唐风琴1,白建明2. 一类带有广义负上限相依索赔额的风险过程大偏差[J]. J4, 2013, 48(1): 100 -106 .
[2] 程智1,2,孙翠芳2,王宁1,杜先能1. 关于Zn的拉回及其性质[J]. J4, 2013, 48(2): 15 -19 .
[3] 汤晓宏1，胡文效2*，魏彦锋2，蒋锡龙2，张晶莹2，. 葡萄酒野生酿酒酵母的筛选及其生物特性的研究[J]. 山东大学学报（理学版）, 2014, 49(03): 12 -17 .
[4] 杨伦，徐正刚，王慧*，陈其美，陈伟，胡艳霞，石元，祝洪磊，曾勇庆*. RNA干扰沉默PID1基因在C2C12细胞中表达的研究[J]. J4, 2013, 48(1): 36 -42 .
[5] 刘婷婷,陈志勇,李晓琴*,杨文志. 随机变量序列的Berry-Esseen界[J]. 山东大学学报（理学版）, 2014, 49(03): 101 -106 .
[6] 刘艳萍,吴群英. 优化权重下高斯序列最大值几乎处处中心极限定理[J]. 山东大学学报（理学版）, 2014, 49(05): 50 -53 .
[7] 廖明哲. 哥德巴赫的两个猜想[J]. J4, 2013, 48(2): 1 -14 .
[8] 赵同欣1,刘林德1*,张莉1,潘成臣2,贾兴军1. 紫藤传粉昆虫与花粉多型性研究[J]. 山东大学学报（理学版）, 2014, 49(03): 1 -5 .
[9] 王开荣,高佩婷. 建立在DY法上的两类混合共轭梯度法[J]. 山东大学学报（理学版）, 2016, 51(6): 16 -23 .
[10] 杨军. 金属基纳米材料表征和纳米结构调控[J]. 山东大学学报（理学版）, 2013, 48(1): 1 -22 .
版权所有 © 2018 《山东大学学报(理学版)》编辑部　
地址: 山东省济南市山大南路27号山东大学中心校区（250100）　电话: +86-0531-88366917　E-mail: xblxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发