{"id":"https://openalex.org/W2029798546","doi":"https://doi.org/10.1145/2505515.2505756","title":"Entropy-based histograms for selectivity estimation","display_name":"Entropy-based histograms for selectivity estimation","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2029798546","doi":"https://doi.org/10.1145/2505515.2505756","mag":"2029798546"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","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/A5109374362","display_name":"Hien To","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hien To","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080122010","display_name":"Kuorong Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158714","display_name":"Teradata (United States)","ror":"https://ror.org/04vkkat38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuorong Chiang","raw_affiliation_strings":["Teradata Cooporation, El Segundo, CA, USA","Teradata Cooporation, El Segundo, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Teradata Cooporation, El Segundo, CA, USA","institution_ids":["https://openalex.org/I4210158714"]},{"raw_affiliation_string":"Teradata Cooporation, El Segundo, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210158714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012068017","display_name":"Cyrus Shahabi","orcid":"https://orcid.org/0000-0001-9118-0681"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyrus Shahabi","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9047,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.85926753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1939","last_page":"1948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9915000200271606,"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/histogram","display_name":"Histogram","score":0.8903580904006958},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6781367063522339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5846517086029053},{"id":"https://openalex.org/keywords/joint-entropy","display_name":"Joint entropy","score":0.527062177658081},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"Entropy estimation","score":0.5033769011497498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44280803203582764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4109220504760742},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.39335429668426514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3688904941082001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35841405391693115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32819145917892456},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21855372190475464}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8903580904006958},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6781367063522339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5846517086029053},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.527062177658081},{"id":"https://openalex.org/C95546049","wikidata":"https://www.wikidata.org/wiki/Q1345207","display_name":"Entropy estimation","level":3,"score":0.5033769011497498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44280803203582764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4109220504760742},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.39335429668426514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3688904941082001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35841405391693115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32819145917892456},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21855372190475464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2505515.2505756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W58109815","https://openalex.org/W1493098199","https://openalex.org/W1581547316","https://openalex.org/W1822348499","https://openalex.org/W1968829657","https://openalex.org/W1978220611","https://openalex.org/W2005188603","https://openalex.org/W2010890196","https://openalex.org/W2015202227","https://openalex.org/W2021993549","https://openalex.org/W2022825068","https://openalex.org/W2026896584","https://openalex.org/W2057058417","https://openalex.org/W2083970667","https://openalex.org/W2136382072","https://openalex.org/W2138793904","https://openalex.org/W2142201263","https://openalex.org/W2143672210","https://openalex.org/W2144628669","https://openalex.org/W2150779766","https://openalex.org/W2153464267","https://openalex.org/W2171903035","https://openalex.org/W2993383518","https://openalex.org/W2998032620","https://openalex.org/W3003326083","https://openalex.org/W3104298728","https://openalex.org/W4205780337","https://openalex.org/W4206294999","https://openalex.org/W4230112007","https://openalex.org/W4236226996","https://openalex.org/W4246006899","https://openalex.org/W6648982606","https://openalex.org/W6839823709"],"related_works":["https://openalex.org/W2889261288","https://openalex.org/W1519338247","https://openalex.org/W3041490575","https://openalex.org/W1550757207","https://openalex.org/W2949821122","https://openalex.org/W2970690932","https://openalex.org/W4321135767","https://openalex.org/W1895696520","https://openalex.org/W1999129037","https://openalex.org/W2029798546"],"abstract_inverted_index":{"Histograms":[0],"have":[1,11],"been":[2,13],"extensively":[3],"used":[4,63],"for":[5,25,133],"selectivity":[6,47],"estimation":[7,20],"by":[8,15],"academics":[9],"and":[10,28,46,108,115,136],"successfully":[12],"adopted":[14],"database":[16],"industry.":[17],"However,":[18],"the":[19,56,80,88,91,113,127,130],"error":[21],"is":[22],"usually":[23],"large":[24],"skewed":[26],"distributions":[27],"biased":[29],"attributes,":[30],"which":[31],"are":[32,61],"typical":[33],"in":[34],"real-world":[35,109],"data.":[36],"Therefore,":[37],"we":[38,78],"propose":[39],"effective":[40],"models":[41,53],"to":[42,64,96,111],"quantitatively":[43],"measure":[44],"bias":[45],"based":[48],"on":[49],"information":[50],"entropy.":[51],"These":[52],"together":[54],"with":[55,105,121],"principles":[57],"of":[58,68,83,90,103,117,129],"maximum":[59],"entropy":[60,73],"then":[62],"develop":[65],"a":[66],"class":[67],"entropy-based":[69,131],"histograms.":[70],"Moreover,":[71],"since":[72],"can":[74],"be":[75],"computed":[76],"incrementally,":[77],"present":[79],"incremental":[81],"variations":[82],"our":[84,118],"algorithms":[85],"that":[86],"reduce":[87],"complexities":[89],"histogram":[92],"construction":[93],"from":[94],"quadratic":[95],"linear.":[97],"We":[98],"conducted":[99],"an":[100],"extensive":[101],"set":[102],"experiments":[104],"both":[106,134],"synthetic":[107],"datasets":[110],"compare":[112],"accuracy":[114],"efficiency":[116],"proposed":[119],"techniques":[120],"many":[122],"other":[123],"histogram-based":[124],"techniques,":[125],"showing":[126],"superiority":[128],"approaches":[132],"equality":[135],"range":[137],"queries.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}