基于改进随机森林算法的评估指标精简方法研究

doi:10.12305/j.issn.1001-506X.2023.07.21

系统工程与电子技术 ›› 2023, Vol. 45 ›› Issue (7): 2108-2113.doi: 10.12305/j.issn.1001-506X.2023.07.21

基于改进随机森林算法的评估指标精简方法研究

程绍驰¹^,²^,*, 游光荣¹

1. 军事科学院战略评估咨询中心, 北京 100091
2. 军事科学院战争研究院, 北京 100091

收稿日期:2022-04-12 出版日期:2023-06-30 发布日期:2023-07-11
通讯作者: 程绍驰
作者简介:程绍驰 (1985—), 男, 副研究员, 博士研究生, 主要研究方向为军事评估、机器学习
游光荣 (1963—), 男, 研究员, 博士, 主要研究方向为军事评估、军事运筹
基金资助:
国家自然科学基金面上项目(71874200);国家社会科学基金重大项目(20ZDA091)

Research on the method of simplifying evaluation index based on improved random forest algorithm

Shaochi CHENG¹^,²^,*, Guangrong YOU¹

1. Strategic Evaluation and Consulting Center, Academy of Military Sciences, Beijing 100091, China
2. Institute of War, Academy of Military Sciences, Beijing 100091, China

Received:2022-04-12 Online:2023-06-30 Published:2023-07-11
Contact: Shaochi CHENG

摘要/Abstract

摘要：

为快速、准确获得武器装备系统效能评估结果, 提出一种能够精简武器装备系统效能评估指标的方法。以随机森林(random forest, RF)算法度量的评估指标重要性为基础, 通过改进RF算法中决策树划分属性选择、叶结点取值确定、决策树输出值计算方法, 实现在指标值有缺失的情况下, 对评估指标进行重要性的排序, 进而精简出指定数量的重要评估指标。以防空系统效能评估指标精简为应用场景, 基于指标值有缺失的模拟数据集, 验证了提出的改进RF算法比传统RF算法具有更高的准确性。

关键词: 指标值缺失, 评估指标, 精简方法, 随机森林

Abstract:

To obtain the effectiveness evaluation results of weapon equipment system quickly and accurately, a method is proposed that can simplify the effectiveness evaluation index of weapon equipment systems. Based on the importance of evaluation index measured by random forest (RF) algorithm, the importance of evaluation index can be sorted in the case of missing index value, and then the specified number of important evaluation index can be refined by improving the decision tree partition attribute selection, leaf node value determination, and decision tree output value calculation methods in RF algorithm. Based on the simulation data set with missing index value, it is verified that the improved RF algorithm is more accurate than the traditional RF algorithm in the application scenario of air defense system effectiveness evaluation index simplification.

Key words: missing index value, evaluation index, simplifying method, random forest (RF)

中图分类号:

TP181

程绍驰, 游光荣. 基于改进随机森林算法的评估指标精简方法研究[J]. 系统工程与电子技术, 2023, 45(7): 2108-2113.

Shaochi CHENG, Guangrong YOU. Research on the method of simplifying evaluation index based on improved random forest algorithm[J]. Systems Engineering and Electronics, 2023, 45(7): 2108-2113.

图/表 4

参考文献 31

1	BI W H , GAO F , ZHANG A . A novel weapon system effectiveness assessment method based on the interval-valued evidential reasoning algorithm and the analytical hierarchy process[J]. IEEE Access, 2021, 9, 53480- 53490. doi: 10.1109/ACCESS.2021.3071419
2	CHEN H, WANG R H, WANG J J, et al. Weapon system of systems evaluation method based on capability perspective[C]//Proc. of the 2nd International Conference on Applied Machine Learning, 2020: 200-203.
3	QI Z Y , ZHANG Y Y , FANG L Q , et al. Research on effectiveness evaluation method of weapon system based on cloud model[J]. Journal of Physics Conference Series, 2021, 1965 (1): 012005. doi: 10.1088/1742-6596/1965/1/012005
4	CHEN Z W, YANG L, WEI J X, et al. Weapon system effectiveness assessment methodology study[C]//Proc. of the 2nd International Conference on Machine Learning and Computer Application, 2021.
5	SU B , LIU H P , ZHANG G C . Anti-UAV group effectiveness evaluation based on fuzzy analytic hierarchy process[J]. Journal of Physics: Conference Series, 2021, 1802 (2): 022098. doi: 10.1088/1742-6596/1802/2/022098
6	WU H, GAO L, LI M Y. Effectiveness evaluation of army equipment support force in the new situation[C]//Proc. of the 2nd International Conference on Computing and Data Science, 2021.
7	FANG Z , SHUANG W U , ZHANG X , et al. ADC-GERT network parameter estimation model for mission effectiveness of joint operation system[J]. Journal of Systems Engineering and Electronics, 2021, 32 (6): 1394- 1460. doi: 10.23919/JSEE.2021.000119
8	TAN X P , ZHANG Q . Review of system contribution rate eva-luation[J]. Scientific Journal of Intelligent Systems Research, 2022, 4 (5): 310- 317.
9	JIANG J Y, LI J C, XIA B Y, et al. Modeling and resilience analysis of combat systems-of-systems based on kill web[C]//Proc. of the 17th Annual System of Systems Engineering Conference, 2022: 28-35.
10	LIU P , LI J C , XIA B Y , et al. Weapons equipment portfolios selection based on equipment system contribution rates[J]. Journal of Systems Engineering and Electronics, 2021, 32 (3): 584- 595. doi: 10.23919/JSEE.2021.000050
11	HAN Y M , LIU T L , LI Y , et al. Construction of intelligent weapon system effectiveness evaluation index system based on Delphi method[J]. Journal of Physics: Conference Series, 2020, 1570 (1): 012049. doi: 10.1088/1742-6596/1570/1/012049
12	HUANG Q , ZHANG Y S , ZHANG B Z , et al. Emerging SEM equipment system combat capability assessment method[J]. Procedia Computer Science, 2021, 183 (5): 545- 550.
13	LI Q Y , CHEN G M , LI Z Q , et al. Evaluation of missile electromagnetic launch system based on effectiveness[J]. Journal of Intelligent & Fuzzy Systems, 2021, 41 (6): 6517- 6526.
14	乔蓉, 周峰. 基于PCA-BP神经网络地空导弹武器系统作战效能评估[J]. 军事运筹与系统工程, 2020, 34 (4): 38- 43.
	QIAO R , ZHOU F . Operational effectiveness evaluation of surface-to air missile weapon system based on PCA-BP neural network[J]. Military Operations Research and Systems Engineering, 2020, 34 (4): 38- 43.
15	姬正一, 陈阳, 沈培志, 等. 决策树集成方法在反舰导弹效能评估中的应用[J]. 现代防御技术, 2021, 49 (4): 15- 23.
	JI Z Y , CHEN Y , SHEN P Z , et al. Decision tree integration method application in effectiveness evaluation of anti-ship missile weapon system[J]. Modern Defence Technology, 2021, 49 (4): 15- 23.
16	HE Y L, HU F Y, LV L L, et al. Research on effectiveness evaluation of equipment maintenance support based on simulation[C]//Proc. of the International Conference on Intelligent Computing, Automation and Systems, 2019: 339-343.
17	ZHANG X W , LI Y X , ZHAO J F , et al. Review on effectiveness evaluation of missile weapon system[J]. International Journal of Frontiers in Engineering Technology, 2021, 3 (9): 30- 35.
18	DING J F , SI G Y , LI B Q , et al. Construction of composite indicator system based on simulation data mining[J]. Journal of Systems Engineering and Electronics, 2017, 28 (1): 81- 87. doi: 10.21629/JSEE.2017.01.10
19	LI X L, LU J Y, GAO Z B, et al. Effectiveness evaluation of kill chain based on PCA, AHP and entropy weight method[C]// Proc. of the 3rd International Conference on Modelling, Simulation and Applied Mathematics, 2018: 192-196.
20	HE Z X , ZHAO L J , GE L , et al. Comprehensive evaluation of weapon equipment systems operational effectiveness based on state space concept[J]. Journal of Physics: Conference Series, 2005, (1): 012099.
21	牛得清, 伍友利, 徐洋, 等. 红外空空导弹抗干扰效能评估建模[J]. 北京航空航天大学学报, 2021, 47 (9): 1874- 1883.
	NIU D Q , WU Y L , XU Y , et al. Modeling of anti jamming effectiveness evaluation of infrared air-to-air missile[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (9): 1874- 1883.
22	BREIMAN L . Random forest[J]. Machine Learning, 2001, 45 (1): 5- 32. doi: 10.1023/A:1010933404324
23	GOLDSTEIN B A , POLLEY E C , BRIGGS F B . Random fo-rests for genetic association studies[J]. Statistical Applications in Genetics and Molecular Biology, 2011, 10 (1): 2- 32.
24	FRIEDMAN J H . Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2000, 29 (5): 1189- 1232.
25	CALLE M L , URREA V . Letter to the editor: stability of random forest importance measures[J]. Briefings in Bioinformatics, 2011, 12 (1): 86- 89. doi: 10.1093/bib/bbq011
26	STROL C , BOULESTEIX A L , ZEILEIS A , et al. Bias in random forest variable importance measures: illustrations, sources and a solution[J]. BMC Bioinformatics, 2007, 8, 25. doi: 10.1186/1471-2105-8-25
27	KRISTIN K , NICODEMU S . Letter to the editor: on the stability and ranking of predictors from random forest variable importance measures[J]. Briefings in Bioinformatics, 2001, 12 (4): 369- 373.
28	QUINLAN J R . Induction of decision trees[J]. Machine Learning, 1986, 1 (1): 81- 106.
29	QUINLAN J R . C4.5: programs for machine learning[M]. San Mateo: Morgan Kaufmann Publishers, 1992.
30	BREIMAN L , FRIEDMAN J H , STONE C J , et al. Classification and regression trees (CART)[M]. Boca Raton: Chapman and Hall/CRC, 1984.
31	杨冬波. 地空导弹武器系统效能评估[D]. 南京: 南京理工大学, 2013.
	YANG D B. Effectiveness evaluation of surface-to-air missile weapon system[D]. Nanjing: Nanjing University of Science and Technology, 2013.

序号	指标							评估结果
序号	1	2	3	4	5	…	18	评估结果
1	7	3	7	3	1	…	7	4
2	2	5	9	4	5	…	9	3
3	8	6	9	5	6	…	3	4
4	6	2	1	6	4	…	5	4
5	6	3	3	2	1	…	8	3

指标值缺失百分比/%	算法	重要性高指标错误个数	重要性中指标错误个数	重要性低指标错误个数	总数
10	传统算法	0	1	1	2
10	改进算法	0	0	0	0
30	传统算法	2	3	1	6
30	改进算法	1	1	0	2
50	传统算法	3	4	1	8
50	改进算法	1	1	0	2

[1]	任博, 岳珠峰, 司勇, 崔利杰, 曾航. 基于随机森林的航空安全因果预测新方法[J]. 系统工程与电子技术, 2023, 45(3): 762-768.
[2]	方坤, 李晓辉, 樊韬. 基于随机森林权重补偿的无人机高精度定位算法[J]. 系统工程与电子技术, 2023, 45(1): 202-209.
[3]	王哲, 李建华, 康东. 网络信息体系双层异质相依网络模型鲁棒性[J]. 系统工程与电子技术, 2021, 43(4): 961-969.
[4]	姚智海, 刘建平, 王建平, 李伟, 任勃. 地面测控资源调度效能评估指标体系[J]. 系统工程与电子技术, 2020, 42(8): 1751-1758.
[5]	李波, 赵洁, 郭晋. 设备故障评估新指标及基于ARMA的预测系统[J]. Journal of Systems Engineering and Electronics, 2011, 33(1): 98-0101.

基于改进随机森林算法的评估指标精简方法研究

Research on the method of simplifying evaluation index based on improved random forest algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 31

相关文章 5

编辑推荐

Metrics

本文评价