{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:16:26Z","timestamp":1740132986283,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2020,4,1]]},"DOI":"10.1109\/tkde.2019.2893175","type":"journal-article","created":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T20:08:26Z","timestamp":1547669306000},"page":"768-781","source":"Crossref","is-referenced-by-count":6,"title":["Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2403-0266","authenticated-orcid":false,"given":"Davood","family":"Rafiei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-012-0305-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1206049.1206056"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2000824.2000825"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/69.842246"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915247"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807222"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/2947618.2947620"},{"key":"ref28","first-page":"381","article-title":"Sketching sampled data","author":"rusu","year":"2009","journal-title":"Proc ICDE Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9323-8_11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3240491"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.250581"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/303976.303978"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687702"},{"key":"ref21","first-page":"13","article-title":"Sketching streams through the net: distributed approximate query tracking","author":"cormode","year":"2005","journal-title":"Proc VLDB Conf"},{"key":"ref24","first-page":"432","article-title":"An efficient algorithm for mining association rules in large databases","author":"savasere","year":"1995","journal-title":"Proc VLDB Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50038-X"},{"key":"ref25","first-page":"134","article-title":"Sampling large databases for association rules","author":"toivonen","year":"1996","journal-title":"Proc VLDB Conf"},{"article-title":"New estimation algorithms for streaming data: Count-min can do more","year":"2007","author":"deng","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1386118.1386121"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816721"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.127"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14778\/2732296.2732299"},{"key":"ref52","first-page":"1402","article-title":"Efficient jaccard-based diversity analysis of large document collections","author":"deng","year":"2011","journal-title":"Proc ACM Int Conf Inf Knowl Manag"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/00949658908811160"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233342"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"792","DOI":"10.14778\/2977797.2977805","article-title":"Streaming similarity self-join","volume":"9","author":"morales","year":"2016","journal-title":"Proc VLDB Endowment"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242592"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2494266.2494312"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027729"},{"key":"ref16","article-title":"On the resemblance and containment of documents","author":"broder","year":"1997","journal-title":"Proc Compression Complexity Sequences Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872796"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/1978665.1978666"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1545"},{"key":"ref4","article-title":"Practical skew handling in parallel joins","author":"dewitt","year":"1992","journal-title":"Proc VLDB Conf"},{"article-title":"Systems and methods for estimating functional relationships in a database","year":"2009","author":"chaudhuri","key":"ref3"},{"key":"ref6","first-page":"24","article-title":"Managing skew in hadoop","volume":"36","author":"kwon","year":"2013","journal-title":"IEEE Data Eng Bulletin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454227"},{"article-title":"(oracle) zfs deduplication","year":"2009","author":"bonwick","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-005-0645-7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.001"},{"article-title":"Pay-as-you-go data cleaning and integration","year":"2008","author":"jeffery","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453883"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1361348.1361351"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(03)00400-6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661885"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564742"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(02)00031-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375727"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/9027048\/08613820.pdf?arnumber=8613820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:41:50Z","timestamp":1651070510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8613820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,1]]},"references-count":55,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2019.2893175","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"type":"print","value":"1041-4347"},{"type":"electronic","value":"1558-2191"},{"type":"electronic","value":"2326-3865"}],"subject":[],"published":{"date-parts":[[2020,4,1]]}}}