不确定近似骨架蚁群聚类算法在滑坡危险性预测中的研究与应用
|
摘要
受不确定因素降雨难以准确处理的制约以及蚁群聚类算法在搜索空间容易陷入局部最优解和搜索速度慢的特征影响,为了提高滑坡危险性预测的精度,提出一种不确定近似骨架蚁群聚类算法。首先采用Gauss点概率模型来描述不确定数据,对不确定数据进行相似性度量;其次引入信息素重分配和自适应动态变量实现蚁群聚类算法局部信息素和全局信息素更新,提高蚁群聚类算法搜索速度,加载遗传算法避免蚁群聚类算法过早陷入局部最优;最后结合近似骨架理论,构建不确定近似骨架蚁群聚类算法模型,缩减迭代次数,快速搜索出聚类结果。在UCI真实数据集和延安宝塔区滑坡实验数据集上的实验结果显示,不确定近似骨架蚁群聚类算法具有较高的聚类质量,预测精度达到93.3%,验证了算法在滑坡危险性预测中的可行性。
The uncertain factor rainfall is hard to accurately handle and the ant colony clustering algorithm is easy to get caught into sub-optimal solution and the searching speed is low in searching space.In order to improve the prediction accuracy of landslide hazard,we propose an uncertain ant colony clustering algorithm based on approximate backbone.Firstly,it utilizes the Gauss point probability model to describe the uncertain data and measure their similarity.Secondly,we introduce the pheromone redistribution and adaptive dynamic variables to update the local pheromone and global pheromone for improving the algorithm's searching speed,and load the genetic algorithm to prevent it from falling into local optimum early.Finally,combining the approximate backbone theory,we build an uncertain ant colony clustering algorithm model based on approximate backbone,which reduces the iteration times and obtains the clustering solution rapidly.Experiments on UCI true datasets and landslide experiment datasets of the Baota district of Yan'an show that the proposed method achieves a higher clustering quality and the prediction accuracy reaches 93.3%,which verifies its feasibility.
The uncertain factor rainfall is hard to accurately handle and the ant colony clustering algorithm is easy to get caught into sub-optimal solution and the searching speed is low in searching space.In order to improve the prediction accuracy of landslide hazard,we propose an uncertain ant colony clustering algorithm based on approximate backbone.Firstly,it utilizes the Gauss point probability model to describe the uncertain data and measure their similarity.Secondly,we introduce the pheromone redistribution and adaptive dynamic variables to update the local pheromone and global pheromone for improving the algorithm's searching speed,and load the genetic algorithm to prevent it from falling into local optimum early.Finally,combining the approximate backbone theory,we build an uncertain ant colony clustering algorithm model based on approximate backbone,which reduces the iteration times and obtains the clustering solution rapidly.Experiments on UCI true datasets and landslide experiment datasets of the Baota district of Yan'an show that the proposed method achieves a higher clustering quality and the prediction accuracy reaches 93.3%,which verifies its feasibility.
引文
[1] Feizizadeh B,Roodposhti M S,Blaschke T,et al.Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping[J].Arabian Journal of Geosciences,2017,10(5):122-134.
[2] Lee G,An H,Kim M.Comparing the performance of TRIGRS and TiVaSS in spatial and temporal prediction of rainfall-induced shallow landslides[J].Environmental Earth Sciences,2017,76(8):315-330.
[3] Ruan Yun-kai,Zhan Jie-wei,Chen Jian-ping,et al.Landslide sensitivity based on K-PSO clustering algorithm and entropy method[J].Journal of Northeastern University(Natural Science),2017,38(4):571-575.(in Chinese)
[4] Zhang Jun,Yin Kun-long,Wang Jia-jia,et al.Evaluation of landslide susceptibility for Wanzhou district of Three Gorges Reservoir[J].Chines Journal of Rock Mechanics&Engineering,2016,35(2):284-296.(in Chinese)
[5] Sang Yi-hui.The landslide-debris flow risk assessment of primary and middle campus in Chuxiong[D].Nanjing:Nanjing University of Information Science&Technology,2016.(in Chinese)
[6] Chen W,Panahi M,Pourghasemi H R.Performance evaluation of GIS-based new ensemble data mining techniques of adaptive neuro-fuzzy inference system(ANFIS)with genetic algorithm(GA),differential evolution(DE),and particle swarm optimization(PSO)for landslide spatial modelling[J].CATENA,2017,157(13):310-324.
[7] Zhang Lei,Cao Qi-xin,Li Jie.A new self-adaptive clustering algorithm based on ant swarm[J].Journal of Shanghai Jiaotong University,2009,43(6):906-909.(in Chinese)
[8] Li Hong-ze,Guo Sen,Wang Bao.Evaluation on power customer value based on ants colony clustering algorithm optimized by genetic algorithm[J].Power System Technology,2012,36(12):256-261.(in Chinese)
[9] Li Zhen,Jia Rui-yu.An improved K-means ant colony clustering algorithm[J].Computer Technology&Development,2015,25(12):28-31.(in Chinese)
[10] Lu Ze-hua,Jin Hai,Yuan Ping-peng,et al.A fuzzy clustering algorithm for interval-valued data based on Gauss distribution functions[J].Acta Electronica Sinica,2010,38(2):295-300.(in Chinese)
[11] Hou J V,Li L V,He J.Detection of grapevine leafroll disease based on 11-index imagery and ant colony clustering algorithm[J].Precision Agriculture,2016,17(4):488-505.
[12] Yuan Ya-bo,Liu Yi,Wu Bin.Solving shortest path problem with modified ant colony algorithm[J].Computer Engineering&Applications,2016,52(6):8-12.(in Chinese)
[13] Zong Y,Xu G D,Jin P,et al.HC_AB:A new heuristic clustering algorithm based on approximate backbone[J].Information Processing Letters,2011,111(17):857-863.
[14] Qu Shi-chao.Approximate backbone guided heuristic clustering algorithm for uncertain data[D].Dalian:Dalian University of Technology,2013.(in Chinese)
[15] Jia Rui-yu,Li Zhen.The level of K-means clustering algorithm based on the minimum spanning tree[J].Microelectronics&Computer,2016,33(3):86-88.(in Chinese)
[16] Orazi V,Bechthold P,Jasen P V,et al.DFT study of methanol adsorption on PtCo(111)[J].Applied Surface Science,2017,420(32):383-389.
[17] Jin Ping,Zong Yu,Qu Shi-chao,et al.Approximate backbone guided heuristic clustering algorithm for uncertain data[J].Journal of Najing University(Natural Sciences),2015,51(1):197-205.(in Chinese)
[18] Chen F Z,Lu C H,Wu H,et al.A semantic similarity measure integrating multiple conceptual relationships for web service discovery[J].Expert Systems with Applications,2017,67(C):19-31.
[19] Mao Yi-min,Peng Zhe,Chen Zhi-gang,et al.Landslide hazard assessment based on uncertain decision tree classification method[J].Application Research of Computers,2014,31(12):3646-3650.(in Chinese)
[20] Lin Shun-fu,Tian Er-wei,Fu Yang,et al.Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J].Proceedings of The Chinese Society for Electrical Engineering,2017,37(8):2242-2252.(in Chinese)
[21] Yeon Y K,Han J,Ryu K H.Landslide susceptibility mapping in Injae,Korea,using a decision tree[J].Engineering Geology,2010,116(3-4):274-283.
[22] Pinto R,Gaiardelli P.Setting forecasting model parameters using unconstrained direct search methods:An empirical evaluation[J].Expert Systems with Applications,2013,40(13):5331-5340.
[23] Sezer E A,Nefeslioglu H A,Osna T.An expert-based landslide susceptibility mapping(LSM)module developed for Netcad Architect Software[J].Computers&Geosciences,2017,98(C):26-37.
[24] Fachrurrozi M.Segmentation and classification models validation area mapping of peat lands as initial value of Fuzzy Kohonen Clustering Network[C]∥Proc of IAES International Conference on Electrical Engineering,Computer Science&Informatics,2017:12-19.
[25] Diniz R C,Fontenele A M M,Do Carmo L H A,et al.Quantitative methods in electroencephalography to access therapeutic response[J].Biomedicine&Pharmacotherapy,2016,81(5):182-191.
[26]Montechiesi L,Cocconcelli M,Rubini R.Artificial immune system via euclidean distance minimization for anomaly detection in bearings[J].Mechanical Systems&Signal Processing,2015,76(7):380-393.
[3]阮云凯,占洁伟,陈剑平,等.基于K-PSO聚类算法和熵值法的滑坡敏感性[J].东北大学学报(自然科学版),2017,38(4):571-575.
[4]张俊,殷坤龙,王佳佳,等.三峡库区万州区滑坡灾害易发性评价研究[J].岩石力学与工程学报,2016,35(2):284-296.
[5]桑议惠.楚雄州中小学校园滑坡泥石流灾害风险评估[D].南京:南京信息工程大学,2016.
[7]张蕾,曹其新,李杰.一种新型的自适应蚁群聚类算法[J].上海交通大学学报,2009,43(6):906-909.
[8]李泓泽,郭森,王宝.基于遗传改进蚁群聚类算法的电力客户价值评价[J].电网技术,2012,36(12):256-261.
[9]李振,贾瑞玉.一种改进的K-means蚁群聚类算法[J].计算机技术与发展,2015,25(12):28-31.
[10]吕泽华,金海,袁平鹏,等.基于Gauss分布函数的区间值数据的模糊聚类算法[J].电子学报,2010,38(2):295-300.
[12]袁亚博,刘羿,吴斌.改进蚁群算法求解最短路径问题[J].计算机工程与应用,2016,52(6):8-12.
[14]屈世超.面向不确定数据的近似骨架启发式聚类算法[D].大连:大连理工大学,2013.
[15]贾瑞玉,李振.基于最小生成树的层次K-means聚类算法[J].微电子学与计算机,2016,33(3):86-88.
[17]金萍,宗瑜,屈世超,等.面向不确定数据的近似骨架启发式聚类算法[J].南京大学学报(自然科学),2015,51(1):197-205.
[19]毛伊敏,彭喆,陈志刚,等.基于不确定决策树分类算法在滑坡危险性预测的应用[J].计算机应用研究,2014,31(12):3646-3650.
[20]林顺富,田二伟,符杨,等.基于信息熵分段聚合近似和谱聚类的负荷分类方法[J].中国电机工程学报,2017,37(8):2242-2252.
[2] Lee G,An H,Kim M.Comparing the performance of TRIGRS and TiVaSS in spatial and temporal prediction of rainfall-induced shallow landslides[J].Environmental Earth Sciences,2017,76(8):315-330.
[3] Ruan Yun-kai,Zhan Jie-wei,Chen Jian-ping,et al.Landslide sensitivity based on K-PSO clustering algorithm and entropy method[J].Journal of Northeastern University(Natural Science),2017,38(4):571-575.(in Chinese)
[4] Zhang Jun,Yin Kun-long,Wang Jia-jia,et al.Evaluation of landslide susceptibility for Wanzhou district of Three Gorges Reservoir[J].Chines Journal of Rock Mechanics&Engineering,2016,35(2):284-296.(in Chinese)
[5] Sang Yi-hui.The landslide-debris flow risk assessment of primary and middle campus in Chuxiong[D].Nanjing:Nanjing University of Information Science&Technology,2016.(in Chinese)
[6] Chen W,Panahi M,Pourghasemi H R.Performance evaluation of GIS-based new ensemble data mining techniques of adaptive neuro-fuzzy inference system(ANFIS)with genetic algorithm(GA),differential evolution(DE),and particle swarm optimization(PSO)for landslide spatial modelling[J].CATENA,2017,157(13):310-324.
[7] Zhang Lei,Cao Qi-xin,Li Jie.A new self-adaptive clustering algorithm based on ant swarm[J].Journal of Shanghai Jiaotong University,2009,43(6):906-909.(in Chinese)
[8] Li Hong-ze,Guo Sen,Wang Bao.Evaluation on power customer value based on ants colony clustering algorithm optimized by genetic algorithm[J].Power System Technology,2012,36(12):256-261.(in Chinese)
[9] Li Zhen,Jia Rui-yu.An improved K-means ant colony clustering algorithm[J].Computer Technology&Development,2015,25(12):28-31.(in Chinese)
[10] Lu Ze-hua,Jin Hai,Yuan Ping-peng,et al.A fuzzy clustering algorithm for interval-valued data based on Gauss distribution functions[J].Acta Electronica Sinica,2010,38(2):295-300.(in Chinese)
[11] Hou J V,Li L V,He J.Detection of grapevine leafroll disease based on 11-index imagery and ant colony clustering algorithm[J].Precision Agriculture,2016,17(4):488-505.
[12] Yuan Ya-bo,Liu Yi,Wu Bin.Solving shortest path problem with modified ant colony algorithm[J].Computer Engineering&Applications,2016,52(6):8-12.(in Chinese)
[13] Zong Y,Xu G D,Jin P,et al.HC_AB:A new heuristic clustering algorithm based on approximate backbone[J].Information Processing Letters,2011,111(17):857-863.
[14] Qu Shi-chao.Approximate backbone guided heuristic clustering algorithm for uncertain data[D].Dalian:Dalian University of Technology,2013.(in Chinese)
[15] Jia Rui-yu,Li Zhen.The level of K-means clustering algorithm based on the minimum spanning tree[J].Microelectronics&Computer,2016,33(3):86-88.(in Chinese)
[16] Orazi V,Bechthold P,Jasen P V,et al.DFT study of methanol adsorption on PtCo(111)[J].Applied Surface Science,2017,420(32):383-389.
[17] Jin Ping,Zong Yu,Qu Shi-chao,et al.Approximate backbone guided heuristic clustering algorithm for uncertain data[J].Journal of Najing University(Natural Sciences),2015,51(1):197-205.(in Chinese)
[18] Chen F Z,Lu C H,Wu H,et al.A semantic similarity measure integrating multiple conceptual relationships for web service discovery[J].Expert Systems with Applications,2017,67(C):19-31.
[19] Mao Yi-min,Peng Zhe,Chen Zhi-gang,et al.Landslide hazard assessment based on uncertain decision tree classification method[J].Application Research of Computers,2014,31(12):3646-3650.(in Chinese)
[20] Lin Shun-fu,Tian Er-wei,Fu Yang,et al.Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J].Proceedings of The Chinese Society for Electrical Engineering,2017,37(8):2242-2252.(in Chinese)
[21] Yeon Y K,Han J,Ryu K H.Landslide susceptibility mapping in Injae,Korea,using a decision tree[J].Engineering Geology,2010,116(3-4):274-283.
[22] Pinto R,Gaiardelli P.Setting forecasting model parameters using unconstrained direct search methods:An empirical evaluation[J].Expert Systems with Applications,2013,40(13):5331-5340.
[23] Sezer E A,Nefeslioglu H A,Osna T.An expert-based landslide susceptibility mapping(LSM)module developed for Netcad Architect Software[J].Computers&Geosciences,2017,98(C):26-37.
[24] Fachrurrozi M.Segmentation and classification models validation area mapping of peat lands as initial value of Fuzzy Kohonen Clustering Network[C]∥Proc of IAES International Conference on Electrical Engineering,Computer Science&Informatics,2017:12-19.
[25] Diniz R C,Fontenele A M M,Do Carmo L H A,et al.Quantitative methods in electroencephalography to access therapeutic response[J].Biomedicine&Pharmacotherapy,2016,81(5):182-191.
[26]Montechiesi L,Cocconcelli M,Rubini R.Artificial immune system via euclidean distance minimization for anomaly detection in bearings[J].Mechanical Systems&Signal Processing,2015,76(7):380-393.
[3]阮云凯,占洁伟,陈剑平,等.基于K-PSO聚类算法和熵值法的滑坡敏感性[J].东北大学学报(自然科学版),2017,38(4):571-575.
[4]张俊,殷坤龙,王佳佳,等.三峡库区万州区滑坡灾害易发性评价研究[J].岩石力学与工程学报,2016,35(2):284-296.
[5]桑议惠.楚雄州中小学校园滑坡泥石流灾害风险评估[D].南京:南京信息工程大学,2016.
[7]张蕾,曹其新,李杰.一种新型的自适应蚁群聚类算法[J].上海交通大学学报,2009,43(6):906-909.
[8]李泓泽,郭森,王宝.基于遗传改进蚁群聚类算法的电力客户价值评价[J].电网技术,2012,36(12):256-261.
[9]李振,贾瑞玉.一种改进的K-means蚁群聚类算法[J].计算机技术与发展,2015,25(12):28-31.
[10]吕泽华,金海,袁平鹏,等.基于Gauss分布函数的区间值数据的模糊聚类算法[J].电子学报,2010,38(2):295-300.
[12]袁亚博,刘羿,吴斌.改进蚁群算法求解最短路径问题[J].计算机工程与应用,2016,52(6):8-12.
[14]屈世超.面向不确定数据的近似骨架启发式聚类算法[D].大连:大连理工大学,2013.
[15]贾瑞玉,李振.基于最小生成树的层次K-means聚类算法[J].微电子学与计算机,2016,33(3):86-88.
[17]金萍,宗瑜,屈世超,等.面向不确定数据的近似骨架启发式聚类算法[J].南京大学学报(自然科学),2015,51(1):197-205.
[19]毛伊敏,彭喆,陈志刚,等.基于不确定决策树分类算法在滑坡危险性预测的应用[J].计算机应用研究,2014,31(12):3646-3650.
[20]林顺富,田二伟,符杨,等.基于信息熵分段聚合近似和谱聚类的负荷分类方法[J].中国电机工程学报,2017,37(8):2242-2252.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |