A. J. Tallón-Ballesteros, José Cristóbal Riquelme Santos
{"title":"为分类器训练删除或保留异常值?","authors":"A. J. Tallón-Ballesteros, José Cristóbal Riquelme Santos","doi":"10.1109/NaBIC.2014.6921892","DOIUrl":null,"url":null,"abstract":"This paper introduces two statistical outlier detection approaches by classes. Experiments on binary and multi-class classification problems reveal that the partial removal of outliers improves significantly one or two performance measures for C4.5 and 1-nearest neighbour classifiers. Also, a taxonomy of problems according to the amount of outliers is proposed.","PeriodicalId":209716,"journal":{"name":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":"{\"title\":\"Deleting or keeping outliers for classifier training?\",\"authors\":\"A. J. Tallón-Ballesteros, José Cristóbal Riquelme Santos\",\"doi\":\"10.1109/NaBIC.2014.6921892\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper introduces two statistical outlier detection approaches by classes. Experiments on binary and multi-class classification problems reveal that the partial removal of outliers improves significantly one or two performance measures for C4.5 and 1-nearest neighbour classifiers. Also, a taxonomy of problems according to the amount of outliers is proposed.\",\"PeriodicalId\":209716,\"journal\":{\"name\":\"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"18\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NaBIC.2014.6921892\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NaBIC.2014.6921892","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deleting or keeping outliers for classifier training?
This paper introduces two statistical outlier detection approaches by classes. Experiments on binary and multi-class classification problems reveal that the partial removal of outliers improves significantly one or two performance measures for C4.5 and 1-nearest neighbour classifiers. Also, a taxonomy of problems according to the amount of outliers is proposed.