|本期目录/Table of Contents|

[1]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):79-85.[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(7):79-85.[doi:10.11731/j.issn.1673-193x.2018.07.012]
点击复制

3种典型机器学习方法在灾害敏感性评估中的对比
分享到：

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

卷:
14
期数:
2018年7期
页码:
79-85
栏目:
职业安全卫生管理与技术
出版日期:
2018-07-31

文章信息/Info

Title:
Comparison of three typical machine learning methods in susceptibility assess-ment of disasters
文章编号:
1673-193X(2018)-07-0079-07
作者:
张雪蕾1; 2; 汪明1; 2; 曹寅雪1; 2; 刘凯1; 2; 洪超裕1; 2
（1.环境演变与自然灾害教育部重点实验室，北京 100875;2.北京师范大学 地理科学学部减灾与应急管理研究院，北京 100875）
Author(s):
ZHANG Xuelei1; 2;  WANG Ming1; 2;  CAO Yinxue1; 2;  LIU Kai1; 2;  HONG Chaoyu1; 2
(1. Key Laboratory of Environmental Change and Natural Disaster, MOE, BNU, Beijing 100875, China;2. Academy of Disaster Reduction and Emergency Management, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China)
关键词:
机器学习; 敏感性评估; K近邻; 朴素贝叶斯; 随机森林
Keywords:
machine learning;  susceptibility assessment;  K-Nearest Neighbor;  Nave Bayes;  Random Forest
分类号:
X913.4
DOI:
10.11731/j.issn.1673-193x.2018.07.012
文献标志码:
A
摘要:
为了比较不同机器学习方法在灾害敏感性评估中的适用性，将K近邻、朴素贝叶斯和随机森林3种典型机器学习方法运用到灾害敏感性评估中，比较3种方法在预测准确率、混淆矩阵和敏感性图上的异同；并基于深圳市电动自行车出险数据以及孕灾环境数据，运用3种方法评估深圳市电动自行车出险的敏感性，进而绘制敏感性图，探讨3种方法对于不同性质数据的适用条件，为开展灾害敏感性评估工作时选取更为适宜的方法，提供参考建议。
Abstract:
In order to compare the applicability of different machine learning methods in the susceptibility assess-ment of disasters, three typical machine learning methods including K-Nearest Neighbor, Nave Bayes and Random Forest were applied in the susceptibility assessment of disasters, and the similarities and differences of three methods in the prediction accuracy, confusion matrix and susceptibility map were compared. Based on the accidents data and disaster-pregnant environment data of electric bicycles in Shenzhen, the susceptibility of electric bicycle accidents in Shenzhen were assessed by using three methods, then the susceptibility maps were drawn, and the applicable conditions of three methods for the data with different properties were discussed. The results provide the reference suggestions for selecting the more appropriate method when conducting the susceptibility assessment of disasters.

参考文献/References:

［1］SONG Y, GONG J, GAO S, et al. Susceptibility assessment of earthquake-induced landslides using bayesian network: a case study in Beichuan, China［J］. Computers & Geosciences, 2012, 42(5):189-199.
［2］DAS I,STEIN A,KERLE N, et al. Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models［J］. Geomorphology, 2012, 179(60):116-125.
［3］NEFESLIOGLU H A, GOKCEOGLU C, SONMEZ H. An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps［J］. Engineering Geology, 2008, 97(3):171-191.
［4］Gómez H, Kavzoglu T. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela［J］. Engineering Geology, 2005, 78(1-2):11-27.
［5］ERMINI L, CATANI F, CASAGLI N. Artificial neural networks applied to landslide susceptibility assessment［J］. Geomorphology, 2005, 66(1):327-343.
［6］YAO X, THAM L G, DAI F C. Landslide susceptibility mapping based on support vector machine: a case study on natural slopes of Hong Kong, China［J］. Geomorphology, 2008, 101(4):572-582.
［7］MICHELETTI N,KANEVSKI M，BAI S，et al.Intelligent analysis of landslide data using machine learning algorithms［M］.Berlin Heidelberg:Springer,2013:161-167.
［8］桑应宾. 基于K近邻的分类算法研究［D］. 重庆：重庆大学, 2009.
［9］BREIMAN L. Bagging predictors［J］. Machine Learning, 1996, 24(2):123-140.
［10］贺鸣, 孙建军, 成颖. 基于朴素贝叶斯的文本分类研究综述［J］. 情报科学, 2016, 34(7):147-154.HE Ming, SUN Jianjun,CHENG Ying.Text classification based on naive bayes：a review［J］. Information Science, 2016,34(7):147-154.
［11］阿曼.朴素贝叶斯分类算法的研究与应用［D］.大连:大连理工大学,2014.
［12］BREIMAN L. Random Forests［J］. Machine Learning, 2001, 45(1):5-32.
［13］HO T K. The random subspace method for constructing decision forests［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1998, 20(8):832-844.
［14］冯少荣. 决策树算法的研究与改进［J］. 厦门大学学报(自然版), 2007, 46(4):496-500.FENG Shaorong.Research and improvement of decision trees algorithm［J］. Journal of Xiamen University (Natural Science), 2007,46(4):496-500.
［15］伊卫国. 基于关联规则与决策树的预测方法研究及其应用［D］. 大连：大连海事大学, 2012.
［16］张宇.决策树分类及剪枝算法研究［D］.哈尔滨：哈尔滨理工大学, 2009.
［17］王黎明. 决策树学习及其剪枝算法研究［D］. 武汉：武汉理工大学, 2007.
［18］丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述［J］. 电子科技大学学报, 2011, 40(1):2-10.DING Shifei, QI Bingjuan,TAN Hongyan.An overview on theory and algorithm of support vector machines［J］. Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
［19］梁礼明, 钟震, 陈召阳. 支持向量机核函数选择研究与仿真［J］. 计算机工程与科学, 2015, 37(6):1135-1141.LIANG Liming, ZHONG Zhen, CHEN Zhaoyang.Research and simulation of kernel function selection for support vector machine［J］. Computer Engineering & Science, 2015,37(6):1135-1141.
［20］周志华.机器学习［M］.北京:清华大学出版社, 2016.
［21］刘敏, 郎荣玲, 曹永斌. 随机森林中树的数量［J］. 计算机工程与应用, 2015, 51(5):126-131.LIU Min, LANG Rongling,CAO Yongbin.Number of trees in random forest［J］. Computer Engineering and Applications. 2015, 51（5）：126-131.
［22］曹正凤.随机森林算法优化研究［D］.北京:首都经济贸易大学, 2014.
［23］马骊.随机森林算法的优化改进研究［D］.广州:暨南大学, 2016.
［24］李荣华. 深圳电动自行车暴增至400万辆［N］. 南方日报, 2015-07-21.
［25］中国青年网. 深圳交警局召开“禁摩限电”记者会：整治并非随意之举［EB/OL］.(2016-04-05)［2018-07-11］. http://news.youth.cn/gn/201604/t20160405_7821191.htm.
［26］CAO Y, WANG M, LIU K. Wildfire Susceptibility Assessment in Southern China:A Comparison of Multiple Methods［J］. International Journal of Disaster Risk Science, 2017, 8(2):1-18.
［27］孔英会, 景美丽. 基于混淆矩阵和集成学习的分类方法研究［J］. 计算机工程与科学, 2012, 34(6):111-117.KONG Yinghui, JING Meili.Research of the classification method based on confusion matrixes and ensemble learning［J］. Omputer Engineering & Science, 2012,34(6): 111-117.
［28］毕凯, 王晓丹, 姚旭,等. 一种基于Bagging和混淆矩阵的自适应选择性集成［J］. 电子学报, 2014, 42(4):711-716.BI Kai，WANG Xiaodan，YAO Xu，et al.Adaptively selective ensemble algorithm based on bagging and confusion matrix［J］. Acta Electronica Sinica, 2014,42(4): 711-716.

相似文献/References:

[1]邱凌峰,胡啸峰,周睿,等.基于机器学习的典型社会安全事件发生规律研究及对雄安新区的启示[J].中国安全生产科学技术,2018,14(10):11.[doi:10.11731/j.issn.1673-193x.2018.10.002]
　QIU Lingfeng,HU Xiaofeng,ZHOU Rui,et al.Research on the occurrence regularity of typical social security incidents based on machine learning and implications for Xiongan New Area[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(7):11.[doi:10.11731/j.issn.1673-193x.2018.10.002]
[2]杨莉琼,蔡利强,古松.基于机器学习方法的安全帽佩戴行为检测[J].中国安全生产科学技术,2019,15(10):152.[doi:10.11731/j.issn.1673-193x.2019.10.024]
　YANG Liqiong,CAI Liqiang,GU Song.Detection on wearing behavior of safety helmet based on machine learning method[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(7):152.[doi:10.11731/j.issn.1673-193x.2019.10.024]
[3]卢子涵,胡啸峰,邱凌峰.基于机器学习的侵财类案件危害程度分析[J].中国安全生产科学技术,2019,15(12):29.[doi:10.11731/j.issn.1673-193x.2019.12.005]
　LU Zihan,HU Xiaofeng,QIU Lingfeng.Analysis on hazard degree of cases of encroaching on property based on machine learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(7):29.[doi:10.11731/j.issn.1673-193x.2019.12.005]
[4]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(7):175.[doi:10.11731/j.issn.1673-193x.2020.01.029]
[5]徐鲁帅,凌晓,马娟娟,等.基于DE-BPNN模型的含腐蚀缺陷管道失效压力预测*[J].中国安全生产科学技术,2021,17(3):91.[doi:10.11731/j.issn.1673-193x.2021.03.014]
　XU Lushuai,LING Xiao,MA Juanjuan,et al.Prediction on failure pressure of pipeline containing corrosion defects based on DE-BPNN[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(7):91.[doi:10.11731/j.issn.1673-193x.2021.03.014]
[6]孙宝财,朱蔡文,凌晓.基于SVR的含缺陷管道剩余强度研究*[J].中国安全生产科学技术,2022,18(2):172.[doi:10.11731/j.issn.1673-193x.2022.02.026]
　SUN Baocai,ZHU Caiwen,LING Xiao.Research on residual strength of pipeline with defects based on SVR[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(7):172.[doi:10.11731/j.issn.1673-193x.2022.02.026]
[7]段在鹏,李帆,邱少辉,等.地铁沿线老旧房屋结构安全预警模型*[J].中国安全生产科学技术,2022,18(3):162.[doi:10.11731/j.issn.1673-193x.2022.03.025]
　DUAN Zaipeng,LI Fan,QIU Shaohui,et al.Early warning model for structural safety of old buildings along metro lines[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(7):162.[doi:10.11731/j.issn.1673-193x.2022.03.025]
[8]陈利成,陈建宏.基于数据填补-机器学习的煤与瓦斯突出预测效果研究*[J].中国安全生产科学技术,2022,18(9):69.[doi:10.11731/j.issn.1673-193x.2022.09.010]
　CHEN Licheng,CHEN Jianhong.Study on prediction effect of coal and gas outburst based on data imputation and machine learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(7):69.[doi:10.11731/j.issn.1673-193x.2022.09.010]
[9]马云路,郑坚钦,梁永图.基于特征提取的输油管道泄漏系数预测*[J].中国安全生产科学技术,2022,18(10):130.[doi:10.11731/j.issn.1673-193x.2022.10.019]
　MA Yunlu,ZHENG Jianqin,LIANG Yongtu.Prediction on leakage coefficient of oil pipeline based on feature extraction[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(7):130.[doi:10.11731/j.issn.1673-193x.2022.10.019]
[10]曹占华,袁海平,李恒喆.基于PCA-PNN的采空区多源指标危险性辨识*[J].中国安全生产科学技术,2022,18(12):104.[doi:10.11731/j.issn.1673-193x.2022.12.014]
　CAO Zhanhua,YUAN Haiping,LI Hengzhe.Multi-source indexes risk identification of goaf based on PCA-PN[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(7):104.[doi:10.11731/j.issn.1673-193x.2022.12.014]

备注/Memo

备注/Memo:
国家自然科学基金项目（41671503）
更新日期/Last Update: 2018-08-09