- 1、本文档共16页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
聚类分析文献英文翻译
电气信息工程学院
英文名称:Datamining-clustering译文名称:数据挖掘—聚类分析专业:
自动化姓名:****班级学号:****指导教师:******译文出处:Data
mining:IanH.Witten,Eibe
Frank著
Clustering
5.1INTRODUCTION
Clusteringissimilartoclassificationinthatdataaregrouped.
However,unlikeclassification,thegroupsarenotpredefined.Instead,
thegroupingisaccomplishedbyfindingsimilaritiesbetweendata
accordingtocharacteristicsfoundintheactualdata.Thegroupsare
calledclusters.Someauthorsviewclusteringasaspecialtypeof
classification.Inthistext,however,wefollowamoreconventional
viewinthatthetwoaredifferent.Manydefinitionsforclustershave
beenproposed:
,Setoflikeelements.Elementsfromdifferentclustersarenot
alike.
,Thedistancebetweenpointsinaclusterislessthanthedistance
between
apointintheclusterandanypointoutsideit.
Atermsimilartoclusteringisdatabasesegmentation,wherelike
tuple(record)inadatabasearegroupedtogether.Thisisdoneto
partitionorsegmentthedatabaseintocomponentsthatthengivethe
useramoregeneralviewofthedata.Inthiscasetext,wedonot
differentiatebetweensegmentationandclustering.Asimpleexampleof
clusteringisfoundinExample5.1.Thisexampleillustratesthefact
thatthatdetermininghowtodotheclusteringisnotstraightforward.
AsillustratedinFigure5.1,agivensetofdatamaybeclustered
ondifferentattributes.Hereagroupofhomesinageographicareais
shown.Thefirstfloortypeofclusteringisbasedonthelocationof
thehome.Homesthataregeographicallyclosetoeachotherare
clusteredtogether.Inthesecondclustering,homesaregroupedbasedon
thesizeofthehouse.
Clusteringhasbeenusedinmanyapplicationdomains,including
biology,medicine,anthropology,marketing,andeconomics.Clustering
applica
文档评论(0)