|本期目录/Table of Contents|

[1]张贺丹,丁元春,刘祖文.基于随机森林的人群疏散预测及影响因素分析*[J].中国安全生产科学技术,2024,20(3):157-162.[doi:10.11731/j.issn.1673-193x.2024.03.022]
　ZHANG Hedan,DING Yuanchun,LIU Zuwen.Crowd evacuation prediction and influencing factors analysis based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(3):157-162.[doi:10.11731/j.issn.1673-193x.2024.03.022]
点击复制

基于随机森林的人群疏散预测及影响因素分析*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年3期
页码:
157-162
栏目:
职业安全卫生管理与技术
出版日期:
2024-03-31

文章信息/Info

Title:
Crowd evacuation prediction and influencing factors analysis based on random forest
文章编号:
1673-193X(2024)-03-0157-06
作者:
张贺丹; 丁元春; 刘祖文
（1.江西理工大学 赣州市工业安全与应急技术重点实验室，江西 赣州 341000；
2.江西理工大学 应急管理与安全工程学院，江西 赣州 341000；
3.南昌工程学院 鄱阳湖流域水工程安全与资源高效利用国家地方联合工程实验室，江西 南昌 330099）
Author(s):
ZHANG Hedan;  DING Yuanchun;  LIU Zuwen
（1.Ganzhou Key Laboratory of Industrial Safety and Emergency Technology,Jiangxi University of Science and Technology，Ganzhou Jiangxi 341000，China；
2.School of Emergency Management and Safety Engineering,Jiangxi University of Science and Technology,Ganzhou Jiangxi 341000,China;
3.National-local Joint Engineering Laboratory of Water Engineering Safety and Efficient Utilization of Resources in Poyang Lake Watershed,Nanchang Institute of Technology,Nanchang Jiangxi 330099,China)
关键词:
人群疏散; 随机森林; 影响因素; 重要性分析
Keywords:
crowd evacuation;  random forest;  influencing factor;  importance analysis
分类号:
X913.4
DOI:
10.11731/j.issn.1673-193x.2024.03.022
文献标志码:
A
摘要:
为对人群疏散预期目标快速预测，分析预期目标与多重影响因素之间的关系，提出基于疏散仿真模拟和随机森林相结合的预测模型。首先，构建人群疏散三维模型；其次，分析影响疏散的关键因素；最后，基于随机森林构建预测模型，开展预测变量的重要性分析。研究结果表明：该方法能对预期目标进行快速预测，预测准确度达到94%；基于变量重要性分析发现，人员数量对疏散的影响显著，且小群体的存在对疏散也有重要影响。研究结果可为人群安全疏散评估提供一定参考。
Abstract:
In order to quickly predict the expected goals of crowd evacuation and analyze the relationship between the expected goals and various influencing factors,a prediction model based on the combination of evacuation simulation and random forest was proposed.Firstly,a three-dimensional model of crowd evacuation was constructed.Secondly,the key factors affecting evacuation were analyzed.Finally,a prediction model based on random forest was constructed,and the importance analysis of the prediction variables was carried out.The results show that this method can quickly predict the expected goals with a prediction accuracy of 94%.Based on the importance analysis of variables,it is found that the number of personnel has a significant impact on evacuation,and the presence of small groups also has significant influence on evacuation.The research results can provide some reference for the safety evacuation assessment of crowd.

参考文献/References:

［1］WENG W G,WANG J Y,SHEN L C,et al.Review of analyses on crowd-gathering risk and its evaluation methods［J］.Journal of Safety Science and Resilience,2023,4(1): 93-107.
［2］JIN C J,JIANG R,WONG S C,et al.Observational characteristics of pedestrian flows under high-density conditions based on controlled experiments［J］.Transportation Research Part C:Emerging Technologies,2019,109:137-154.
［3］SUN Q,TURKAN Y.A BIM-based simulation framework for fire safety management and investigation of the critical factors affecting human evacuation performance［J］.Advanced Engineering Informatics,2020,44:101093.
［4］HAN Y B,LIU H,MOORE P.Extended route choice model based on available evacuation route set and its application in crowd evacuation simulation［J］.Simulation Modelling Practice and Theory,2017,75:1-16.
［5］ZHANG Z,JIA L M.Optimal guidance strategy for crowd evacuation with multiple exits:a hybrid multiscale modeling approach［J］.Applied Mathematical Modelling,2021,90:488-504.
［6］FU Z J,JIA Q H,CHEN J,et al.A fine discrete field cellular automaton for pedestrian dynamics integrating pedestrian heterogeneity,anisotropy,and time-dependent characteristics［J］.Transportation Research Part C:Emerging Technologies,2018,91:37-61.
［7］GUO K,ZHANG L M.Simulation-based passenger evacuation optimization in metro stations considering multi-objectives［J］.Automation in Construction,2022,133:104010.
［8］ZHAO X L,LOVREGLIO R,NILSSON D.Modelling and interpreting pre-evacuation decision-making using machine learning［J］.Automation in Construction,2020,113:103140.
［9］GHOSH A,DEY P.Flood Severity assessment of the coastal tract situated between muriganga and saptamukhi estuaries of sundarban delta of india using frequency ratio (FR),fuzzy logic (FL),logistic regression (LR) and random forest (RF) models［J］.Regional Studies in Marine Science,2021,42:101624.
［10］张大伟.考虑人员差异性的客船疏散模型研究［D］.哈尔滨：哈尔滨工程大学,2019.
［11］LU L L,CHAN C,Y WANG J,et al.A study of pedestrian group behaviors in crowd evacuation based on an extended floor field cellular automaton model［J］.Transportation Research Part C:Emerging Technologies,2017,81:317-329.
［12］LANCEL S,CHAPURLAT V,DRAY G,et al.Emergency evacuation in a supermarket during a terrorist attack:towards a possible modelling of the influence of affordances on the evacuation behavior of agents in a complex virtual environment［J］.Journal of Safety Science and Resilience,2023,4(2):139-150.
［13］MANDAL T,RAMACHANDRA R K,TIWARI G.Evacuation of metro stations:a review［J］.Tunnelling and Underground Space Technology Incorporating Trenchless Technology Research,2023,140(10):105304.
［14］LIU Z A,HOU J W,ZHANG L L,et al.Research on energy-saving factors adaptability of exterior envelopes of university teaching-office buildings under different climates (China) based on orthogonal design and energy plus［J］.Heliyon,2022,8(8):e10056.
［15］任博,岳珠峰,司勇,等.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.REN Bo,YUE Zhufeng,SI Yong,et al.A new method for causal prediction of aviation safety based on random forest ［J］.Systems Engineering and Electronic Technology,2023,45(3):762-768.

相似文献/References:

[1]刘梦婷,蒋美英.考虑人群拥堵的疏散出口选择行为研究及建模[J].中国安全生产科学技术,2016,12(9):157.[doi:10.11731/j.issn.1673-193x.2016.09.028]
　LIU Mengting,JIANG Meiying.Study on exit choice behavior in evacuation considering crowd congestion and its modeling[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(3):157.[doi:10.11731/j.issn.1673-193x.2016.09.028]
[2]徐绪堪,王京.基于随机森林的突发事件分级模型研究[J].中国安全生产科学技术,2018,14(2):77.[doi:10.11731/j.issn.1673-193x.2018.02.012]
　XU Xukan,WANG Jing.Research on classification model of emergencies based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(3):77.[doi:10.11731/j.issn.1673-193x.2018.02.012]
[3]张雪蕾,汪明,曹寅雪,等.3种典型机器学习方法在灾害敏感性评估中的对比[J].中国安全生产科学技术,2018,14(7):79.[doi:10.11731/j.issn.1673-193x.2018.07.012]
　ZHANG Xuelei,WANG Ming,CAO Yinxue,et al.Comparison of three typical machine learning methods in susceptibility assess-ment of disasters[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(3):79.[doi:10.11731/j.issn.1673-193x.2018.07.012]
[4]陈长坤,童蕴贺.基于元胞自动机恐慌状态下人群疏散模型研究[J].中国安全生产科学技术,2019,15(6):12.[doi:10.11731/j.issn.1673-193x.2019.06.002]
　CHEN Changkun,TONG Yunhe.Study on crowd evacuation model under panic state based on cellular automata[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(3):12.[doi:10.11731/j.issn.1673-193x.2019.06.002]
[5]吕惠,刘向元,王英龙,等.人群疏散出口障碍物对疏散效率的影响规律研究[J].中国安全生产科学技术,2020,16(1):141.[doi:10.11731/j.issn.1673-193x.2020.01.023]
　LYU Hui,LIU Xiangyuan,WANG Yinglong,et al.Study on influence laws of obstacle in evacuation exit on evacuation efficiency[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(3):141.[doi:10.11731/j.issn.1673-193x.2020.01.023]
[6]邱凌峰,韩昕格,胡啸峰.基于机器学习的恐怖袭击事件后果预测方法研究[J].中国安全生产科学技术,2020,16(1):175.[doi:10.11731/j.issn.1673-193x.2020.01.029]
　QIU Lingfeng,HAN Xinge,HU Xiaofeng.Study on method of consequence prediction for terrorist attacks based on machine learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(3):175.[doi:10.11731/j.issn.1673-193x.2020.01.029]
[7]孙瑞山,李重锋.基于随机森林的飞机长着陆预警方法[J].中国安全生产科学技术,2021,17(5):182.[doi:10.11731/j.issn.1673-193x.2021.05.028]
　SUN Ruishan,LI Chongfeng.Early-warning method of aircraft long landing based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(3):182.[doi:10.11731/j.issn.1673-193x.2021.05.028]
[8]刘以雪,毛占利,廖明煜.考虑从众阈值和主体特征的人群疏散元胞自动机模型*[J].中国安全生产科学技术,2021,17(12):156.[doi:10.11731/j.issn.1673-193x.2021.12.025]
　LIU Yixue,MAO Zhanli,LIAO Mingyu.Cellular automata model for crowd evacuation considering herding threshold and agent characteristics[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(3):156.[doi:10.11731/j.issn.1673-193x.2021.12.025]
[9]倪景峰,李振,乐晓瑞,等.基于随机森林的阻变型通风网络故障诊断方法*[J].中国安全生产科学技术,2022,18(4):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]
　NI Jingfeng,LI Zhen,LE Xiaorui,et al.Resistance variant fault diagnosis method of ventilation network based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]
[10]乔建刚,王傑,岳凌峰.基于随机森林的高速公路运营隧道风险判别法则研究*[J].中国安全生产科学技术,2022,18(9):195.[doi:10.11731/j.issn.1673-193x.2022.09.028]
　QIAO Jiangang,WANG Jie,YUE Lingfeng.Research on risk discrimination rule of expressway operating tunnel based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):195.[doi:10.11731/j.issn.1673-193x.2022.09.028]

备注/Memo

备注/Memo:
收稿日期： 2023-10-17
* 基金项目： 国家自然科学基金项目(72164016)
作者简介： 张贺丹，硕士研究生，主要研究方向为人员安全疏散。
通信作者： 丁元春，博士，副教授，主要研究方向为人员疏散建模与实验。
更新日期/Last Update: 2024-04-07