Regional Landslide Susceptibility Zonation(LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statis...Regional Landslide Susceptibility Zonation(LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression(LR), Artificial Neural Networks(ANN) and Support Vector Machine(SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis(LDA), receiver operating characteristic(ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadilyincreasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes. Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.展开更多
This article deals with implementation of the classification and regression trees into the DMAIC phases of Six Sigma methodology. Six Sigma methodology seeks to improve the quality of manufacturing process by identify...This article deals with implementation of the classification and regression trees into the DMAIC phases of Six Sigma methodology. Six Sigma methodology seeks to improve the quality of manufacturing process by identifying and minimizing variability of this process. Using the classification, regression and segmentation trees as a part of the Data Mining methods could improve results of DMAIC phases. This improvement has a direct impact on the Sigma performance level of processes. The author introduces research results of implementation Data Mining algorithms into retail sales promotion. The author implements classification and regression techniques in our research. As a software tool has been selected SPSS PASW Modeler. The author deals with more data mining algorithms ad their implementation in the DMAIC phases. The article is divided into several parts. The first part is the introduction to Six Sigma methodology, the second deals with classification and regression trees. The third part describes tree research focused on the implementation of data mining algorithms and the fourth section summarizes the research results.展开更多
基金supported by the open fund of Key Laboratory of Geoscience Spatial Information Technology, Ministry of Land and Resource of the China (Grant No. KLGSIT2013-15)The GIS-studio (www.gis-studio.nl) of the Institute for Biodiversity and Ecosystem Dynamics (IBED) is acknowledged for computational support
文摘Regional Landslide Susceptibility Zonation(LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression(LR), Artificial Neural Networks(ANN) and Support Vector Machine(SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis(LDA), receiver operating characteristic(ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadilyincreasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes. Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.
文摘This article deals with implementation of the classification and regression trees into the DMAIC phases of Six Sigma methodology. Six Sigma methodology seeks to improve the quality of manufacturing process by identifying and minimizing variability of this process. Using the classification, regression and segmentation trees as a part of the Data Mining methods could improve results of DMAIC phases. This improvement has a direct impact on the Sigma performance level of processes. The author introduces research results of implementation Data Mining algorithms into retail sales promotion. The author implements classification and regression techniques in our research. As a software tool has been selected SPSS PASW Modeler. The author deals with more data mining algorithms ad their implementation in the DMAIC phases. The article is divided into several parts. The first part is the introduction to Six Sigma methodology, the second deals with classification and regression trees. The third part describes tree research focused on the implementation of data mining algorithms and the fourth section summarizes the research results.
