|本期目录/Table of Contents|

[1]林永良,夏克文,王志恒,等.基于SOCP-MKRVM的区域滑坡敏感性分析研究[J].中国安全生产科学技术,2016,12(12):64-68.[doi:10.11731/j.issn.1673-193x.2016.12.011]
　LIN Yongliang,XIA Kewen,WANG Zhiheng,et al.Study on regional landslide susceptibility based on SOCP-MKRVM[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(12):64-68.[doi:10.11731/j.issn.1673-193x.2016.12.011]
点击复制

基于SOCP-MKRVM的区域滑坡敏感性分析研究
分享到：

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

卷:
12
期数:
2016年12期
页码:
64-68
栏目:
现代职业安全卫生管理与技术
出版日期:
2016-12-30

文章信息/Info

Title:
Study on regional landslide susceptibility based on SOCP-MKRVM
文章编号:
1673-193X(2016)-12-0064-05
作者:
林永良1; 2; 夏克文1; 王志恒2; 姜晓庆1
（1.河北工业大学 电子信息工程学院，天津300401；2. 天津城建大学 计算中心，天津 300384）
Author(s):
LIN Yongliang1; 2;  XIA Kewen1;  WANG Zhiheng2;  JIANG Xiaoqing1
(1. School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China; 2. Computing Center, Tianjin Chengjian University, Tianjin 300384, China)
关键词:
相关向量机; 二阶锥规划; 滑坡敏感性; ROC; 滑坡点密度
Keywords:
relevance vector machine;  second-order cone programming;  landslide susceptibility;  ROC;  landslide dot density
分类号:
X935
DOI:
10.11731/j.issn.1673-193x.2016.12.011
文献标志码:
A
摘要:
为了提高相关向量机（RVM）在区域滑坡敏感性评价中的预测能力，提出了基于二阶锥规划的多核相关向量机 (SOCP-MKRVM)预测模型。以四川省低山丘陵区为例，选取了8个滑坡孕灾因子训练RVM预测模型，并分别运用受试者工作特征曲线（ROC）和滑坡点密度2种方法对预测结果进行验证。通过与单核RVM模型的对比分析，结果表明：SOCP-MKRVM模型提高了对区域滑坡敏感性的评价能力，预测精度提高到71.33%，ROC曲线下面积达到0.741，滑坡点密度分布更加合理，两低敏感区之和为0.89个/100 km2，两高敏感区之和为6.54个/100 km2。
Abstract:
In order to improve the prediction ability of relevance vector machine (RVM) for the regional landslide susceptibility assessment, a prediction model of multiple-kernel RVM based on second-order cone programming (SOCP-MKRVM) was proposed. Taking the low hilly area of Sichuan Province as example, eight landslide-predisposing factors were selected to train the RVM prediction model, and two methods which include the receiver-operating characteristic curve (ROC) and the landslides dot density were used to verify the prediction results of the model. Through the contrastive analysis with the single kernel RVM model, the results showed that the SOCP-MKRVM model improved the assessment ability of the regional landslide susceptibility. The prediction accuracy increased to 71.33%, the area under the ROC curve reached 0.741, and the distribution of landslide dot density was more reasonable, with the sum of two low susceptibility areas as 0.89/100 km2 and the sum of two high susceptibility area as 6.54/100 km2.

参考文献/References:

［1］郁淑华.四川盆地泥石流、滑坡的时空分布特征及其气象成因分析［J］.高原气象，2003，22（z1）：83-89. YU Shuhua. Analyses on spatial-temporal characteristics of mud-rock flow and landslide in Sichuan basin and its meteorological cause ［J］. Plateau Meteorology, 2003, 22(z1): 83-89.
[2]WU X-l, REN F, NIU R. Q.landslide susceptibility assessment using object mapping units,decision tree,and support vector machine models in the three gorges of China［J］. Environmental Earth Sciences, 2014, 71(11): 4725-4738.
[3]YILMAZ I. Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey: conditional probability, logistic regression, artificial neural networks, and support vector machine［J］. Environmental Earth Sciences, 2010, 61(4): 821-836.
[4]陈建宏，郑荣凯，陈浩.基于 PCA 和 BP 神经网络边坡稳定性分析［J］.中国安全生产科学技术，2014，10（5）：142-147. CHEN Jianhong, ZHENG Rongkai, CHEN Hao. Analysis on slope stability based on combination of PCA and BP neural network ［J］. Journal of Safety Science and Technology, 2014, 10(5):142-147.
[5]陈祖云，张桂珍，邬长福，等.基于支持向量机的边坡稳定性预测研究［J］.中国安全生产科学技术，2009，5（4）：101-105. CHEN Zuyun, ZHANG Guizhen, WU Changfu, et al. Study of prediction of slope stability based on support vector machines ［J］. Journal of Safety Science and Technology, 2009, 5(4):101-105.
[6]LIN Yongliang, WANG Zhi-heng, et al. Regional landslide susceptibility assessment based on relevance vector machine［J］. Journal of Information and Computational Science, 2015, 12(18): 6893-6903.
[7]TIPPING M E. Sparse bayesian learning and the relevance vector machine［J］. Journal of Machine Learning Research, 2001, 1(3): 211-244.
[8]LIU Zaobao, SHAO Jianfu, XU Weiya, et al. Comparison on landslide nonlinear displacement analysis and prediction with computational intelligence approaches［J］. Landslides, 2014, 11(5): 889-896.
[9]WANG Hongqiao, SUN Fuchun, CAI Yanning, et al. On multiple kernel learning methods［J］. Acta automatic Sinica, 2010, 36(8): 1037-1050.
[10]GONEN M, ALPAYDIN E. Multiple kernel learning algorithms［J］. Journal of Machine Learning Research, 2011(12): 2211-2268.
[11]ZHU Changjian, XIA Kewen, ZU Baokai, et al. Multiple-kernel relevance vector machine based on SOCP［J］. Journal of Computational Information Systems, 2014, 10(24): 10831-10838.
[12]王志恒，胡卓玮，刘长青，等.基于变维分形理论的四川省低山丘陵区滑坡孕灾环境因素敏感性分析［J］.地球与环境，2013，41（6）：680-687. WANG Zhiheng, HU Zhuowei, LIU Changqing, et al. Susceptibility analysis of disaster-pregnant environmental factors of landslide in the hilly area in Sichuan based on variable dimension fractal theory ［J］. Earth Environ, 2013, 41(6):680-687.
[13]Kandola J, Shawe-Taylor J,Cristianini N. Optimizing kernel aligment over combinations of kernel ［J］. Optimizing kernel alignment over combinations of kernel, 2002.
[14]LE C V, NGUYEN-XUAN H, NGUYEN-DANG H. Upper and lower bound limit analysis of plates using FEM and second-order cone programming［J］. Computers & Structures, 2010, 88(1/2): 65-73.
[15]李志辉，罗平.PASW/SPSS Statistics中文版统计分析教程3版［M］.北京：电子工业出版社，2010.

相似文献/References:

[1]甘旭升,端木京顺,高建国.基于相关向量机的飞行安全评价方法[J].中国安全生产科学技术,2012,8(12):143.
　GAN Xu sheng,DUANMU Jing shun,GAO Jian guo.Flight safety evaluation method based on relevance vector machine[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(12):143.

备注/Memo

备注/Memo:
河北省自然科学基金(E2016202341)；河北省高等学校科学技术研究项目(BJ2014013)
更新日期/Last Update: 2017-01-13