首页|Studies from Zhejiang University in the Area of Machine Learning Reported (A Comparative Evaluation of Clustering Methods and Data Sampling Techniques In the Prediction of Reservoir Landslide Deformation State)
Studies from Zhejiang University in the Area of Machine Learning Reported (A Comparative Evaluation of Clustering Methods and Data Sampling Techniques In the Prediction of Reservoir Landslide Deformation State)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ma chine Learning. According to news reporting outof Hangzhou, People’s Republic o f China, by NewsRx editors, research stated, “Landslides exhibiting stepwisede formation characteristics are extensively dispersed throughout the Three Gorges Reservoir (TGR) region of China. Predicting the deformation state of landslides in TGR holds paramount significance inlandslide early warning and risk manageme nt.”Financial supporters for this research include Natural Science Foundation of Jia ngsu Province, NationalField Observation and Research Station of Landslides in the TGR Area of the Yangtze River.Our news journalists obtained a quote from the research from Zhejiang University , “Machine learningbasedlandslide deformation state prediction is a combinatio n of clustering and imbalanced classification.This paper compares the efficacy of three prevalent clustering methods, namely K-means, Density-BasedSpatial Clu stering of Applications with Noise (DBSCAN), and Gaussian Mixture Model (GMM), i n theclustering analysis process. Furthermore, the paper evaluates the performa nce of three widely-used datasampling technologies, namely Synthetic Minority O versampling Technique (SMOTE), SMOTE-EditedNearest Neighbors (SMOTE-ENN), and A DAptive SYNthetic Sampling (ADASYN), in the imbalancedclassification process. T he Baijiabao and Bazimen landslides in the TGR region, which exhibit step-wised eformation characteristics, are used as case studies. DBSCAN and GMM exhibit sig nificant advantagesin the clustering process. Meanwhile, the mixture models tha t integrate oversampling technologies andclassification algorithms perform exce ptionally well in imbalanced classification. The aforementionedalgorithms are r ecommended for predicting the deformation states of step-wise landslides in the TGRregion.”
HangzhouPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningTechnologyZhejiang Unive rsity
NETL
NSTL
