{"id":"https://openalex.org/W2099941470","doi":"https://doi.org/10.1145/2213556.2213594","title":"Space-efficient estimation of statistics over sub-sampled streams","display_name":"Space-efficient estimation of statistics over sub-sampled streams","publication_year":2012,"publication_date":"2012-05-21","ids":{"openalex":"https://openalex.org/W2099941470","doi":"https://doi.org/10.1145/2213556.2213594","mag":"2099941470"},"language":"en","primary_location":{"id":"doi:10.1145/2213556.2213594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213556.2213594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGMOD-SIGACT-SIGAI symposium on Principles of Database Systems","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/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew McGregor","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112023986","display_name":"A. Pavan","orcid":"https://orcid.org/0000-0003-1665-5266"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Pavan","raw_affiliation_strings":["Iowa State University, Ames, IA, USA","Iowa state university, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Iowa state university, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047034711","display_name":"Srikanta Tirthapura","orcid":"https://orcid.org/0000-0001-5321-924X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikanta Tirthapura","raw_affiliation_strings":["Iowa State University, Ames, IA, USA","Iowa state university, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Iowa state university, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102861589","display_name":"David P. Woodruff","orcid":"https://orcid.org/0000-0002-2158-1380"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Woodruff","raw_affiliation_strings":["IBM Almaden, Almaden, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden, Almaden, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101979548"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.6528,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90742056,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9909999966621399,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.6732090711593628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6058250069618225},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5840538740158081},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49406054615974426},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.4746808707714081},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.44945070147514343},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4224492609500885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41218769550323486},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3821678161621094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28686583042144775}],"concepts":[{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.6732090711593628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6058250069618225},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5840538740158081},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49406054615974426},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.4746808707714081},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.44945070147514343},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4224492609500885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41218769550323486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3821678161621094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28686583042144775},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2213556.2213594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213556.2213594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGMOD-SIGACT-SIGAI symposium on Principles of Database Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W69989483","https://openalex.org/W135476618","https://openalex.org/W1493892051","https://openalex.org/W1575494040","https://openalex.org/W1878833411","https://openalex.org/W1973266211","https://openalex.org/W1974918169","https://openalex.org/W1977141583","https://openalex.org/W1982682305","https://openalex.org/W1993482412","https://openalex.org/W1998026880","https://openalex.org/W1998272044","https://openalex.org/W2001183701","https://openalex.org/W2006355640","https://openalex.org/W2034417563","https://openalex.org/W2036304306","https://openalex.org/W2058991275","https://openalex.org/W2062822402","https://openalex.org/W2069414131","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2082553115","https://openalex.org/W2085845250","https://openalex.org/W2087982439","https://openalex.org/W2109121608","https://openalex.org/W2119885577","https://openalex.org/W2124430127","https://openalex.org/W2124850309","https://openalex.org/W2126922390","https://openalex.org/W2127455097","https://openalex.org/W2129978406","https://openalex.org/W2159958017","https://openalex.org/W2169636627","https://openalex.org/W2615341736"],"related_works":["https://openalex.org/W4293083682","https://openalex.org/W4389449520","https://openalex.org/W2061507057","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"],"abstract_inverted_index":{"In":[0],"many":[1],"stream":[2,38,64,101],"monitoring":[3],"situations,":[4],"the":[5,23,36,41,50,54,62,69,99,103,107],"data":[6,37,104],"arrival":[7],"rate":[8],"is":[9,14,29],"so":[10],"high":[11],"that":[12,56],"it":[13],"not":[15],"even":[16],"possible":[17],"to":[18,30,43,58],"observe":[19],"each":[20],"element":[21],"of":[22,35,49,72,98],"stream.":[24,52,109],"The":[25],"most":[26],"common":[27],"solution":[28],"sample":[31,42],"a":[32],"small":[33],"fraction":[34],"and":[39,46,74,83,95],"use":[40],"infer":[44],"properties":[45],"estimate":[47],"aggregates":[48],"original":[51,70,100],"However,":[53],"quantities":[55,71],"need":[57],"be":[59],"computed":[60],"on":[61],"sampled":[63,108],"are":[65],"often":[66],"different":[67],"from":[68,102],"interest":[73],"their":[75],"estimation":[76],"requires":[77],"new":[78],"algorithms.":[79],"We":[80],"present":[81],"upper":[82],"lower":[84],"bounds":[85],"(often":[86],"matching)":[87],"for":[88],"estimating":[89],"frequency":[90],"moments,":[91],"support":[92],"size,":[93],"entropy,":[94],"heavy":[96],"hitters":[97],"observed":[105],"in":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}