Xian-fei Yang, Jian-pei Zhang, Yang Jing, Li Xiang
{"title":"A burst change detection algorithm for data streams","authors":"Xian-fei Yang, Jian-pei Zhang, Yang Jing, Li Xiang","doi":"10.1109/CINC.2010.5643822","DOIUrl":null,"url":null,"abstract":"Burst Change of probability distribution at any moment is an important characteristic in data streams. When it has happened, data mining algorithm must adapt itself to new probability distribution. So how to detect burst change in data streams is an important part of data stream mining. In this paper, we proposed an algorithm BCDADS to detect it by using hoeffding theorem and independent identical distribution central limit theorem. Theory and experiment indicated this algorithm can effectively detect burst change in data streams.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 Second International Conference on Computational Intelligence and Natural Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CINC.2010.5643822","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Burst Change of probability distribution at any moment is an important characteristic in data streams. When it has happened, data mining algorithm must adapt itself to new probability distribution. So how to detect burst change in data streams is an important part of data stream mining. In this paper, we proposed an algorithm BCDADS to detect it by using hoeffding theorem and independent identical distribution central limit theorem. Theory and experiment indicated this algorithm can effectively detect burst change in data streams.