{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T14:31:08Z","timestamp":1746196268451,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/icsai48974.2019.9010154","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T09:58:47Z","timestamp":1582883927000},"page":"1534-1542","source":"Crossref","is-referenced-by-count":5,"title":["The Detection Algorithms for Similar Duplicate Data"],"prefix":"10.1109","author":[{"given":"Jin-yu","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruo-yu","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"An efficient domain independent algorithm for detecting approximately. duplicate database records","author":"monge","year":"1997","journal-title":"Proc ACM SIGMOD Workshop Data Mining Knowledge Discovery"},{"key":"ref11","article-title":"An adaptive and efficient algorithm for detecting approximately duplicate database records","volume":"2001","author":"monge","year":"0","journal-title":"Proc of the SIGMOD"},{"key":"ref12","first-page":"61","article-title":"Incremental Algorithm for Detecting Approximately Duplicate Database Records Based on Priority Queue Strategy","volume":"23","author":"she","year":"2003","journal-title":"Computer Applications"},{"journal-title":"Data Mining and Knowledge Discovery","year":"2010","author":"li","key":"ref13"},{"journal-title":"Technology and Application of Data Mining","year":"2010","author":"liu","key":"ref14"},{"key":"ref15","first-page":"981","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"ester","year":"1996","journal-title":"Proceedings of the International Conference on Knowledge Discovering in Databases and Data Mining"},{"journal-title":"Research and Implementation of Data Anomaly Detection Clustering Algorithm","year":"2015","author":"dong-zhang","key":"ref16"},{"key":"ref17","first-page":"11","author":"yang","year":"2006","journal-title":"Study of Data Cleaning Algorithms Based on Data Warehouse"},{"key":"ref18","article-title":"Research for Replacement Algorithm of LRU","author":"chu","year":"2012","journal-title":"Journal of Jixi University"},{"key":"ref19","article-title":"Comparison of merged and non-merged similarity clustering analysis methods","author":"liu","year":"2013","journal-title":"Acta Ecologica Sinica"},{"key":"ref28","first-page":"2736","article-title":"Amelioration method of SNM based on flexible window and ranking adjusting","author":"chen","year":"2013","journal-title":"Application Research of Computers"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1515693.1516680"},{"key":"ref27","article-title":"Analysis and Comparison of Sorting Algorithms","author":"yun","year":"2008","journal-title":"Science & Technology Information"},{"key":"ref3","first-page":"245","author":"authore","year":"2010","journal-title":"Translation Executing Data Quality Projects"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1515693.1516680"},{"key":"ref5","first-page":"1","volume":"35","author":"han","year":"2008","journal-title":"An Overview of Data Qual ity Research Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1087.2013.02208"},{"key":"ref7","first-page":"1","article-title":"An Overview of Data Quality Research","volume":"35","author":"han","year":"2008","journal-title":"Computer Science"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48309-8_70"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1145\/568271.223807","article-title":"The merge\/purge problem for large databases","author":"hern\u00e1ndez","year":"1995","journal-title":"Proc Of ACM SIGMOD International Conference on Management of Data"},{"key":"ref1","first-page":"2076","article-title":"Research on Data Quality and Data Cleaning:a Survey","volume":"13","author":"guo","year":"2002","journal-title":"Journal of Software"},{"key":"ref20","article-title":"Research on Analysis and Comparison on Similarity Algorithm","author":"chen","year":"2016","journal-title":"Computer Knowledge and Technology"},{"key":"ref22","first-page":"286","author":"loshin","year":"2010","journal-title":"The Practitioner's Guide to Data Quality Improvement"},{"key":"ref21","first-page":"10","author":"dai","year":"2010","journal-title":"An Improved Method for Detecting Incremental Approximately Duplicate Records Based on Clustering Tree"},{"journal-title":"Introduction to Algorithms","year":"2001","author":"cormen","key":"ref24"},{"key":"ref23","first-page":"118","article-title":"A Synthetical Approach for Detecting Approximately Duplicate Database Records of Multi-Language Data","volume":"29","author":"yu","year":"2002","journal-title":"Computer Science"},{"key":"ref26","article-title":"Comparison and Analysis of Classic Search Engine Sorting Algorithms","author":"wang","year":"2012","journal-title":"Industrial & Science Tribune"},{"key":"ref25","article-title":"Summary of Several Classical Sorting Algorithms","author":"huang","year":"2016","journal-title":"Computer Programming Skills & Maintenance"}],"event":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","start":{"date-parts":[[2019,11,2]]},"location":"Shanghai, China","end":{"date-parts":[[2019,11,4]]}},"container-title":["2019 6th International Conference on Systems and Informatics (ICSAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8974456\/9010069\/09010154.pdf?arnumber=9010154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:49:59Z","timestamp":1658094599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9010154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icsai48974.2019.9010154","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}