{"id":"https://openalex.org/W2049127440","doi":"https://doi.org/10.1145/1066157.1066159","title":"Sampling algorithms in a stream operator","display_name":"Sampling algorithms in a stream operator","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2049127440","doi":"https://doi.org/10.1145/1066157.1066159","mag":"2049127440"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103350641","display_name":"Theodore Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Theodore Johnson","raw_affiliation_strings":["AT&T Labs Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075159410","display_name":"S. Muthukrishnan","orcid":"https://orcid.org/0009-0007-8936-5709"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Rutgers University","Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028824739","display_name":"Irina Rozenbaum","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Irina Rozenbaum","raw_affiliation_strings":["Rutgers University","Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103350641"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":20.0946,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.99357837,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8223669528961182},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7075029611587524},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.6617946028709412},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6104257702827454},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5960926413536072},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5604290962219238},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5256979465484619},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.42058077454566956},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3678116500377655},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3356361985206604},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32306969165802},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07942447066307068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223669528961182},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7075029611587524},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.6617946028709412},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6104257702827454},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5960926413536072},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5604290962219238},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5256979465484619},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.42058077454566956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3678116500377655},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3356361985206604},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32306969165802},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07942447066307068},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1066157.1066159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.9929","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.9929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://paul.rutgers.edu/~rozenbau/final_SIGMOD05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.911.7228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.911.7228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mathcs.emory.edu/%7Echeung/Courses/584-StreamDB/Syllabus/papers/2005-Sampling-Alg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32332503","https://openalex.org/W139562302","https://openalex.org/W1546474256","https://openalex.org/W1601435884","https://openalex.org/W1655765388","https://openalex.org/W1979367563","https://openalex.org/W2001474264","https://openalex.org/W2029207367","https://openalex.org/W2069980026","https://openalex.org/W2112452856","https://openalex.org/W2118828104","https://openalex.org/W2119885577","https://openalex.org/W2122174571","https://openalex.org/W2132069633","https://openalex.org/W2132461362","https://openalex.org/W2134786002","https://openalex.org/W2144261930","https://openalex.org/W2148732449","https://openalex.org/W2150569458","https://openalex.org/W2151575925","https://openalex.org/W2152092514","https://openalex.org/W2152592483","https://openalex.org/W2161569281","https://openalex.org/W4232534713","https://openalex.org/W6605656404"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W2802243998","https://openalex.org/W1521014365"],"abstract_inverted_index":{"Complex":[0],"queries":[1],"over":[2],"high":[3,99,142],"speed":[4,100,143,196],"data":[5,146,199],"streams":[6],"often":[7],"need":[8],"to":[9,13,74,91,122,159],"rely":[10],"on":[11,27,139],"approximations":[12],"keep":[14],"up":[15],"with":[16],"their":[17],"input.":[18],"The":[19],"research":[20],"community":[21],"has":[22],"developed":[23],"a":[24,62,76,98,140,155,173,187,198],"rich":[25],"literature":[26],"approximate":[28],"streaming":[29],"algorithms":[30,37,80,193],"for":[31,104,131,162,186],"this":[32,52,137],"application.":[33],"Many":[34],"of":[35,40,79,128,190],"these":[36],"produce":[38],"samples":[39],"the":[41,56,93,115,152,169,179],"input":[42],"stream,":[43],"providing":[44],"better":[45],"properties":[46],"than":[47],"conventional":[48],"random":[49],"sampling.":[50],"In":[51],"paper,":[53],"we":[54,88,113,183],"abstract":[55],"stream":[57,64,101,147,191,200],"sampling":[58,83,125,192],"process":[59],"and":[60,84,148,164,167],"design":[61],"new":[63],"sample":[65],"operator.":[66],"We":[67,135],"show":[68,89],"how":[69,90],"it":[70],"can":[71],"be":[72],"used":[73],"implement":[75,92],"wide":[77,188],"variety":[78,189],"that":[81,150],"perform":[82,123],"sampling-based":[85],"aggregations.":[86],"Also,":[87],"operator":[94,116,153,170],"in":[95],"Gigascope":[96,121,160],"-":[97],"database":[102],"specialized":[103],"IP":[105,132],"network":[106,133],"monitoring":[107],"applications.":[108],"As":[109],"an":[110,119],"example":[111],"study,":[112],"apply":[114],"within":[117,197],"such":[118],"enhanced":[120],"subset-sum":[124],"which":[126],"is":[127,154,178],"great":[129],"interest":[130],"management.":[134],"evaluate":[136],"implemention":[138],"live,":[141],"internet":[144],"traffic":[145],"find":[149],"(a)":[151],"flexible,":[156],"versatile":[157],"addition":[158],"suitable":[161],"tuning":[163],"algorithm":[165],"engineering,":[166],"(b)":[168],"imposes":[171],"only":[172],"small":[174],"evaluation":[175],"overhead.":[176],"This":[177],"first":[180],"operational":[181],"implementation":[182],"know":[184],"of,":[185],"at":[194],"line":[195],"management":[201],"system.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}