Stamatios-Aggelos N. Alexandropoulos, S. Kotsiantis, Violetta E. Piperigou, M. Vrahatis
{"title":"一种新的离群值识别集成方法","authors":"Stamatios-Aggelos N. Alexandropoulos, S. Kotsiantis, Violetta E. Piperigou, M. Vrahatis","doi":"10.1109/Confluence47617.2020.9058219","DOIUrl":null,"url":null,"abstract":"A vast number of factors influence the applicability of machine learning methods and the use of statistical models for a given task. The existence of outliers in a data set is a common issue that needs to be tackled. The identification of such values is a difficult, yet very useful project. In many cases errors or dissimilar values to the majority of the data are useless. Nevertheless, valuable information can be hidden in outliers’ set. During the last years, although several models have been developed for outlier detection, there is always space for new, intelligent, more efficient and less time consuming techniques for this issue. In the present work we provide a new ensemble method for outlier detection. In order to test the proposed methodology, comparisons are made with widely used techniques for outlier detection. The results obtained indicate that our model is robust and quite competitive to the other methods.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"A new ensemble method for outlier identification\",\"authors\":\"Stamatios-Aggelos N. Alexandropoulos, S. Kotsiantis, Violetta E. Piperigou, M. Vrahatis\",\"doi\":\"10.1109/Confluence47617.2020.9058219\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A vast number of factors influence the applicability of machine learning methods and the use of statistical models for a given task. The existence of outliers in a data set is a common issue that needs to be tackled. The identification of such values is a difficult, yet very useful project. In many cases errors or dissimilar values to the majority of the data are useless. Nevertheless, valuable information can be hidden in outliers’ set. During the last years, although several models have been developed for outlier detection, there is always space for new, intelligent, more efficient and less time consuming techniques for this issue. In the present work we provide a new ensemble method for outlier detection. In order to test the proposed methodology, comparisons are made with widely used techniques for outlier detection. The results obtained indicate that our model is robust and quite competitive to the other methods.\",\"PeriodicalId\":180005,\"journal\":{\"name\":\"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/Confluence47617.2020.9058219\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/Confluence47617.2020.9058219","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A vast number of factors influence the applicability of machine learning methods and the use of statistical models for a given task. The existence of outliers in a data set is a common issue that needs to be tackled. The identification of such values is a difficult, yet very useful project. In many cases errors or dissimilar values to the majority of the data are useless. Nevertheless, valuable information can be hidden in outliers’ set. During the last years, although several models have been developed for outlier detection, there is always space for new, intelligent, more efficient and less time consuming techniques for this issue. In the present work we provide a new ensemble method for outlier detection. In order to test the proposed methodology, comparisons are made with widely used techniques for outlier detection. The results obtained indicate that our model is robust and quite competitive to the other methods.