{"id":"https://openalex.org/W3007803181","doi":"https://doi.org/10.1109/bigdata47090.2019.9006440","title":"CS*: Approximate Query Processing on Big Data using Scalable Join Correlated Sample Synopsis","display_name":"CS*: Approximate Query Processing on Big Data using Scalable Join Correlated Sample Synopsis","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007803181","doi":"https://doi.org/10.1109/bigdata47090.2019.9006440","mag":"3007803181"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big 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/A5103764451","display_name":"Feng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Feng Yu","raw_affiliation_strings":["Youngstown State University,Department of Computer Science and Information Systems,Youngstown,OH,USA","Department of Computer Science and Information Systems, Youngstown State University, Youngstown, OH, USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University,Department of Computer Science and Information Systems,Youngstown,OH,USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Department of Computer Science and Information Systems, Youngstown State University, Youngstown, OH, USA","institution_ids":["https://openalex.org/I161203489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111414478","display_name":"Wen\u2010Chi Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I110378019","display_name":"Southern Illinois University Carbondale","ror":"https://ror.org/049kefs16","country_code":"US","type":"education","lineage":["https://openalex.org/I110378019","https://openalex.org/I2801502357"]},{"id":"https://openalex.org/I4210094983","display_name":"ScienceSouth","ror":"https://ror.org/00my6s217","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210094983"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Chi Hou","raw_affiliation_strings":["Southern Illinois University,Department of Computer Science,Carbondale,IL,USA","Department of Computer Science, Southern Illinois University, Carbondale, IL, USA"],"affiliations":[{"raw_affiliation_string":"Southern Illinois University,Department of Computer Science,Carbondale,IL,USA","institution_ids":["https://openalex.org/I110378019"]},{"raw_affiliation_string":"Department of Computer Science, Southern Illinois University, Carbondale, IL, USA","institution_ids":["https://openalex.org/I110378019","https://openalex.org/I4210094983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103764451"],"corresponding_institution_ids":["https://openalex.org/I161203489"],"apc_list":null,"apc_paid":null,"fwci":0.1768,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5761884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9995999932289124,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7835839986801147},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7350872755050659},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6623476147651672},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6434308290481567},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5394668579101562},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4867306053638458},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4459781348705292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3427397310733795},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3422393500804901},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29737210273742676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12898460030555725},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06116291880607605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835839986801147},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7350872755050659},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6623476147651672},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6434308290481567},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5394668579101562},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4867306053638458},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4459781348705292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3427397310733795},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3422393500804901},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29737210273742676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12898460030555725},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06116291880607605},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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":56,"referenced_works":["https://openalex.org/W1505808391","https://openalex.org/W1569403765","https://openalex.org/W1589269155","https://openalex.org/W1608665031","https://openalex.org/W1964857063","https://openalex.org/W1988144572","https://openalex.org/W2020147322","https://openalex.org/W2020584928","https://openalex.org/W2022858489","https://openalex.org/W2045938805","https://openalex.org/W2046437776","https://openalex.org/W2063546264","https://openalex.org/W2066588467","https://openalex.org/W2071989194","https://openalex.org/W2090403603","https://openalex.org/W2097484305","https://openalex.org/W2099601885","https://openalex.org/W2107443258","https://openalex.org/W2110076987","https://openalex.org/W2110086534","https://openalex.org/W2114029045","https://openalex.org/W2119885577","https://openalex.org/W2126917089","https://openalex.org/W2134786002","https://openalex.org/W2135194391","https://openalex.org/W2138793904","https://openalex.org/W2139783012","https://openalex.org/W2153329411","https://openalex.org/W2153406069","https://openalex.org/W2161463763","https://openalex.org/W2189465200","https://openalex.org/W2243803726","https://openalex.org/W2293896416","https://openalex.org/W2296677182","https://openalex.org/W2421547754","https://openalex.org/W2424452828","https://openalex.org/W2585664214","https://openalex.org/W2612048434","https://openalex.org/W2613577383","https://openalex.org/W2614565221","https://openalex.org/W2795530455","https://openalex.org/W2798499404","https://openalex.org/W2891345706","https://openalex.org/W2893661430","https://openalex.org/W2999362268","https://openalex.org/W3100965700","https://openalex.org/W4232849517","https://openalex.org/W4241185933","https://openalex.org/W4251617391","https://openalex.org/W6630164444","https://openalex.org/W6648171237","https://openalex.org/W6676268515","https://openalex.org/W6679775555","https://openalex.org/W6687322159","https://openalex.org/W6733129084","https://openalex.org/W7075682605"],"related_works":["https://openalex.org/W4205996836","https://openalex.org/W2151692181","https://openalex.org/W4392498349","https://openalex.org/W2093960938","https://openalex.org/W3214148052","https://openalex.org/W4392216655","https://openalex.org/W2807741550","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4256664196"],"abstract_inverted_index":{"Complex":[0],"join":[1,16,109,121,130,145,174,183,204],"queries":[2,17,101,175],"are":[3,163],"expensive":[4],"to":[5,15,89,97,115,148,167],"process":[6],"on":[7,43,82,102,165,191],"big":[8,55],"data.":[9],"Providing":[10],"fast":[11,169],"and":[12,35,79,93,124,144,170,185,201],"accurate":[13,171,203],"approximations":[14,172],"with":[18,176,207],"common":[19,177],"aggregate":[20,178],"functions":[21],"can":[22,51,76,94,197],"bring":[23],"tremendous":[24],"benefits":[25],"in":[26,155],"many":[27],"fields":[28],"such":[29],"as":[30],"data":[31,33,56,139],"management,":[32],"mining,":[34],"machine":[36],"learning.":[37],"The":[38,188],"state-of-the-art":[39],"methods":[40],"mainly":[41],"focus":[42],"generating":[44],"non-reusable":[45],"samples":[46],"during":[47],"query":[48,158,205],"time":[49],"which":[50,75],"be":[52,77,90,95,198],"costly":[53],"for":[54,173],"applications.":[57],"In":[58],"this":[59],"research,":[60],"we":[61],"develop":[62],"a":[63,125],"scalable":[64,120],"sample-based":[65],"synopsis,":[66],"called":[67,129],"Scalable":[68],"Join":[69],"Correlated":[70],"Sample":[71],"Synopsis":[72],"(or":[73,132],"CS*),":[74],"pre-computed":[78],"doesn\u2019t":[80],"rely":[81],"any":[83],"index":[84],"structure.":[85],"CS*":[86,166,196],"only":[87],"needs":[88],"generated":[91,200],"once":[92],"used":[96],"answer":[98],"all":[99],"future":[100],"the":[103,116,150],"same":[104],"database.":[105],"It":[106],"efficiently":[107,199],"maintains":[108],"relationships":[110],"between":[111],"sampled":[112],"tuples":[113],"thanks":[114],"introduced":[117],"scheme":[118],"of":[119,152],"correlated":[122,146],"sampling":[123,209],"unique":[126],"numerical":[127],"value":[128],"ratio":[131],"JR).":[133],"We":[134],"further":[135],"introduce":[136],"two":[137],"novel":[138],"structures,":[140],"namely":[141],"count":[142],"trace":[143],"histogram,":[147],"optimize":[149],"calculation":[151],"JR":[153],"values":[154],"map-reduce.":[156],"For":[157],"estimations,":[159],"multiple":[160],"unbiased":[161],"estimators":[162],"developed":[164],"provide":[168],"functions,":[179],"acyclic":[180],"or":[181],"cyclic":[182],"graphs,":[184],"dangling":[186],"tuples.":[187],"experimental":[189],"study":[190],"large":[192],"datasets":[193],"demonstrates":[194],"that":[195],"provides":[202],"estimations":[206],"small":[208],"fractions.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}