Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study pres...Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.展开更多
Based on the tropical cyclone(TC) observations in the western North Pacific from 2000 to 2008, this paper adopts the particle swarm optimization(PSO) algorithm of evolutionary computation to optimize one comprehensive...Based on the tropical cyclone(TC) observations in the western North Pacific from 2000 to 2008, this paper adopts the particle swarm optimization(PSO) algorithm of evolutionary computation to optimize one comprehensive classification rule, and apply the optimized classification rule to the forecasting of TC intensity change. In the process of the optimization, the strategy of hierarchical pruning has been adopted in the PSO algorithm to narrow the search area,and thus to enhance the local search ability, i.e. hierarchical PSO algorithm. The TC intensity classification rule involves core attributes including 12-HMWS, MPI, and Rainrate which play vital roles in TC intensity change. The testing accuracy using the new mined rule by hierarchical PSO algorithm reaches 89.6%. The current study shows that the novel classification method for TC intensity change analysis based on hierarchic PSO algorithm is not only easy to explain the source of rule core attributes, but also has great potential to improve the forecasting of TC intensity change.展开更多
A number of clustering algorithms were used to analyze many databases in the field of image clustering. The main objective of this research work was to perform a comparative analysis of the two of the existing partiti...A number of clustering algorithms were used to analyze many databases in the field of image clustering. The main objective of this research work was to perform a comparative analysis of the two of the existing partitions based clustering algorithms and a hybrid clustering algorithm. The results verification done by using classification algorithms via its accuracy. The perfor-mance of clustering and classification algorithms were carried out in this work based on the tumor identification, cluster quality and other parameters like run time and volume complexity. Some of the well known classification algorithms were used to find the accuracy of produced results of the clustering algorithms. The performance of the clustering algorithms proved mean-ingful in many domains, particularly k-Means, FCM. In addition, the proposed multifarious clustering technique has revealed their efficiency in terms of performance in predicting tumor affected regions in mammogram images. The color images are converted in to gray scale images and then it is processed. Finally, it is identified the best method for the analysis of finding tumor in breast images. This research would be immensely useful to physicians and radiologist to identify cancer affected area in the breast.展开更多
Data mining is the process of extracting implicit but potentially useful information from incomplete, noisy, and fuzzy data. Data mining offers excellent nonlinear modeling and self-organized learning, and it can play...Data mining is the process of extracting implicit but potentially useful information from incomplete, noisy, and fuzzy data. Data mining offers excellent nonlinear modeling and self-organized learning, and it can play a vital role in the interpretation of well logging data of complex reservoirs. We used data mining to identify the lithologies in a complex reservoir. The reservoir lithologies served as the classification task target and were identified using feature extraction, feature selection, and modeling of data streams. We used independent component analysis to extract information from well curves. We then used the branch-and- bound algorithm to look for the optimal feature subsets and eliminate redundant information. Finally, we used the C5.0 decision-tree algorithm to set up disaggregated models of the well logging curves. The modeling and actual logging data were in good agreement, showing the usefulness of data mining methods in complex reservoirs.展开更多
Based on the discuss of the basic concept of data mining technology and the decision tree method,combining with the data samples of wind and hailstorm disasters in some counties of Mudanjiang region,the forecasting mo...Based on the discuss of the basic concept of data mining technology and the decision tree method,combining with the data samples of wind and hailstorm disasters in some counties of Mudanjiang region,the forecasting model of agro-meteorological disaster grade was established by adopting the C4.5 classification algorithm of decision tree,which can forecast the direct economic loss degree to provide rational data mining model and obtain effective analysis results.展开更多
针对SMOTE算法和随机森林可较好解决不平衡数据集的分类问题但对少数类样本分类效果还有待提高的问题,融合Canopy和K-means两种聚类算法,设计了C-K-SMOTE改进算法。先后利用Canopy算法进行快速近似聚类,再利用K-means算法进行精准聚类,...针对SMOTE算法和随机森林可较好解决不平衡数据集的分类问题但对少数类样本分类效果还有待提高的问题,融合Canopy和K-means两种聚类算法,设计了C-K-SMOTE改进算法。先后利用Canopy算法进行快速近似聚类,再利用K-means算法进行精准聚类,得到精准聚类簇,最后利用SMOTE算法增加少数类样本数量,使数据趋于平衡。选取公开数据集KEEL(knowledge extraction on evolutionary learning)数据库中的不平衡数据集,结合随机森林分类模型进行了实验验证,实验表明C-K-SMOTE算法可有效平衡不平衡数据集。展开更多
基金This research is funded by the National Natural Science Foundation of China(Grant Nos.41807285 and 51679117)Key Project of the State Key Laboratory of Geohazard Prevention and Geoenvironment Protection(SKLGP2019Z002)+3 种基金the National Science Foundation of Jiangxi Province,China(20192BAB216034)the China Postdoctoral Science Foundation(2019M652287 and 2020T130274)the Jiangxi Provincial Postdoctoral Science Foundation(2019KY08)Fundamental Research Funds for National Universities,China University of Geosciences(Wuhan)。
文摘Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.
基金National Natural Science Foundation of China(41201045)Jiangsu Qing Lan Project(2016)Natural Science Foundation of Jiangsu Province(BK20151458)
文摘Based on the tropical cyclone(TC) observations in the western North Pacific from 2000 to 2008, this paper adopts the particle swarm optimization(PSO) algorithm of evolutionary computation to optimize one comprehensive classification rule, and apply the optimized classification rule to the forecasting of TC intensity change. In the process of the optimization, the strategy of hierarchical pruning has been adopted in the PSO algorithm to narrow the search area,and thus to enhance the local search ability, i.e. hierarchical PSO algorithm. The TC intensity classification rule involves core attributes including 12-HMWS, MPI, and Rainrate which play vital roles in TC intensity change. The testing accuracy using the new mined rule by hierarchical PSO algorithm reaches 89.6%. The current study shows that the novel classification method for TC intensity change analysis based on hierarchic PSO algorithm is not only easy to explain the source of rule core attributes, but also has great potential to improve the forecasting of TC intensity change.
文摘A number of clustering algorithms were used to analyze many databases in the field of image clustering. The main objective of this research work was to perform a comparative analysis of the two of the existing partitions based clustering algorithms and a hybrid clustering algorithm. The results verification done by using classification algorithms via its accuracy. The perfor-mance of clustering and classification algorithms were carried out in this work based on the tumor identification, cluster quality and other parameters like run time and volume complexity. Some of the well known classification algorithms were used to find the accuracy of produced results of the clustering algorithms. The performance of the clustering algorithms proved mean-ingful in many domains, particularly k-Means, FCM. In addition, the proposed multifarious clustering technique has revealed their efficiency in terms of performance in predicting tumor affected regions in mammogram images. The color images are converted in to gray scale images and then it is processed. Finally, it is identified the best method for the analysis of finding tumor in breast images. This research would be immensely useful to physicians and radiologist to identify cancer affected area in the breast.
基金sponsored by the National Science and Technology Major Project(No.2011ZX05023-005-006)
文摘Data mining is the process of extracting implicit but potentially useful information from incomplete, noisy, and fuzzy data. Data mining offers excellent nonlinear modeling and self-organized learning, and it can play a vital role in the interpretation of well logging data of complex reservoirs. We used data mining to identify the lithologies in a complex reservoir. The reservoir lithologies served as the classification task target and were identified using feature extraction, feature selection, and modeling of data streams. We used independent component analysis to extract information from well curves. We then used the branch-and- bound algorithm to look for the optimal feature subsets and eliminate redundant information. Finally, we used the C5.0 decision-tree algorithm to set up disaggregated models of the well logging curves. The modeling and actual logging data were in good agreement, showing the usefulness of data mining methods in complex reservoirs.
基金Supported by Science and Technology Plan of Mudanjiang City (G200920064)Teaching Reform Construction of Mudanjiang Normal University (10-xj11080)
文摘Based on the discuss of the basic concept of data mining technology and the decision tree method,combining with the data samples of wind and hailstorm disasters in some counties of Mudanjiang region,the forecasting model of agro-meteorological disaster grade was established by adopting the C4.5 classification algorithm of decision tree,which can forecast the direct economic loss degree to provide rational data mining model and obtain effective analysis results.
文摘针对SMOTE算法和随机森林可较好解决不平衡数据集的分类问题但对少数类样本分类效果还有待提高的问题,融合Canopy和K-means两种聚类算法,设计了C-K-SMOTE改进算法。先后利用Canopy算法进行快速近似聚类,再利用K-means算法进行精准聚类,得到精准聚类簇,最后利用SMOTE算法增加少数类样本数量,使数据趋于平衡。选取公开数据集KEEL(knowledge extraction on evolutionary learning)数据库中的不平衡数据集,结合随机森林分类模型进行了实验验证,实验表明C-K-SMOTE算法可有效平衡不平衡数据集。
