Clustering Based Sampling for Learning from Unbalanced Seismic Data Set

IF 0.5 Q4 ENGINEERING, GEOLOGICAL

International Journal of Geotechnical Earthquake Engineering Pub Date : 2017-07-01 DOI:10.4018/IJGEE.2017070101

M. Rahmani, Abdelmalek Amine, R. M. Hamou

{"title":"Clustering Based Sampling for Learning from Unbalanced Seismic Data Set","authors":"M. Rahmani, Abdelmalek Amine, R. M. Hamou","doi":"10.4018/IJGEE.2017070101","DOIUrl":null,"url":null,"abstract":"Thisarticledescribeshowsomestratumcontainastressconcentrationzones,andwhilethestress increases andexceedsahighvalueor socalledcriticalvalue, it destroys rocks.This causes the emissionofseismictremorsofdifferentenergies.Seismologyconsistsofthestudyoftheeffectsof seismicwaves,andpredictingtheseismichazardstorocksandlongwallcoals.Thisisalongsidethe mainproblemoccurredinthisfield,theunbalanceddatathatlackscausewhenstudyingtheseismic hazards.Learningfromunbalanceddataisconsideredasoneofthemostdifficultissuestosolve nowadays,thisarticlepresentsaninformedsamplingmethodthatisbasedonaclusteringapproach forthepredictionofseismichazardsinPolishcoalmines.Theideaisbasedonthedividingofnonhazardousexampleswhichrepresentsmorethan90%ofthereal-lifecasesintosubsetsofexamplesin ordertobalancetheclasses.Thisactionfacilitatesthelearningfromtherecordeddata.Forevaluation, theauthorshaveevaluatedthesystembasedonthepredictionofseismichazardswherepositive resultshavebeenreviewedcomparedtotheclassificationofexampleswithoutbalancingthecases. KEywoRDS Clustering, Data Mining, Machine Learning, Seismic Hazards Detection, Supervised Classification, Unbalanced Data","PeriodicalId":42473,"journal":{"name":"International Journal of Geotechnical Earthquake Engineering","volume":"39 1","pages":"1-22"},"PeriodicalIF":0.5000,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Geotechnical Earthquake Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/IJGEE.2017070101","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Thisarticledescribeshowsomestratumcontainastressconcentrationzones,andwhilethestress increases andexceedsahighvalueor socalledcriticalvalue, it destroys rocks.This causes the emissionofseismictremorsofdifferentenergies.Seismologyconsistsofthestudyoftheeffectsof seismicwaves,andpredictingtheseismichazardstorocksandlongwallcoals.Thisisalongsidethe mainproblemoccurredinthisfield,theunbalanceddatathatlackscausewhenstudyingtheseismic hazards.Learningfromunbalanceddataisconsideredasoneofthemostdifficultissuestosolve nowadays,thisarticlepresentsaninformedsamplingmethodthatisbasedonaclusteringapproach forthepredictionofseismichazardsinPolishcoalmines.Theideaisbasedonthedividingofnonhazardousexampleswhichrepresentsmorethan90%ofthereal-lifecasesintosubsetsofexamplesin ordertobalancetheclasses.Thisactionfacilitatesthelearningfromtherecordeddata.Forevaluation, theauthorshaveevaluatedthesystembasedonthepredictionofseismichazardswherepositive resultshavebeenreviewedcomparedtotheclassificationofexampleswithoutbalancingthecases. KEywoRDS Clustering, Data Mining, Machine Learning, Seismic Hazards Detection, Supervised Classification, Unbalanced Data

查看原文本刊更多论文

基于聚类的非平衡地震数据学习方法

Thisarticledescribeshowsomestratumcontainastressconcentrationzones，andwhilethestress增加了andexceedsahighvalueor socalledcriticalvalue，它破坏了岩石。This导致了emissionofseismictremorsofdifferentenergies。Seismologyconsistsofthestudyoftheeffectsof seismicwaves，andpredictingtheseismichazardstorocksandlongwallcoals。Thisisalongsidethe mainproblemoccurredinthisfield，theunbalanceddatathatlackscausewhenstudyingtheseismic危险。Learningfromunbalanceddataisconsideredasoneofthemostdifficultissuestosolve现在是thisarticlepresentsaninformedsamplingmethodthatisbasedonaclusteringapproach forthepredictionofseismichazardsinPolishcoalmines。Theideaisbasedonthedividingofnonhazardousexampleswhichrepresentsmorethan90%ofthereal-lifecasesintosubsetsofexamplesin ordertobalancetheclasses.Thisactionfacilitatesthelearningfromtherecordeddata。Forevaluation, theauthorshaveevaluatedthesystembasedonthepredictionofseismichazardswherepositive resultshavebeenreviewedcomparedtotheclassificationofexampleswithoutbalancingthecases。关键词聚类，数据挖掘，机器学习，地震灾害检测，监督分类，不平衡数据

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Geotechnical Earthquake Engineering ENGINEERING, GEOLOGICAL-

CiteScore

1.90

自引率

25.00%

发文量