{"id":"https://openalex.org/W3082524322","doi":"https://doi.org/10.1109/fuzz48607.2020.9177610","title":"Optimization for Large-Scale Fuzzy Joins Using Fuzzy Filters in MapReduce","display_name":"Optimization for Large-Scale Fuzzy Joins Using Fuzzy Filters in MapReduce","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082524322","doi":"https://doi.org/10.1109/fuzz48607.2020.9177610","mag":"3082524322"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz48607.2020.9177610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz48607.2020.9177610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03107555v1/file/fuzzieee2020.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034304045","display_name":"Thi-To-Quyen Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thi-To-Quyen TRAN","raw_affiliation_strings":["Univ Rennes, CNRS, IRISA, Lannion, France","SHAMAN - A Symbolic and Human-centric view of dAta MANagement ( IRISA/ENSSAT 6 rue de Kerampont -  BP 80518 - 22305 Lannion cedex - France)"],"affiliations":[{"raw_affiliation_string":"Univ Rennes, CNRS, IRISA, Lannion, France","institution_ids":["https://openalex.org/I56067802","https://openalex.org/I2802519937","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"SHAMAN - A Symbolic and Human-centric view of dAta MANagement ( IRISA/ENSSAT 6 rue de Kerampont -  BP 80518 - 22305 Lannion cedex - France)","institution_ids":["https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056921599","display_name":"Thuong\u2010Cang Phan","orcid":"https://orcid.org/0000-0002-4807-2463"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thuong-Cang PHAN","raw_affiliation_strings":["Can Tho University, Can Tho, Vietnam","CTU - Can Tho University [Vietnam] (Campus II, 3/2 street, Ninh Kieu district, Can Tho city - Vietnam)"],"affiliations":[{"raw_affiliation_string":"Can Tho University, Can Tho, Vietnam","institution_ids":["https://openalex.org/I177733328"]},{"raw_affiliation_string":"CTU - Can Tho University [Vietnam] (Campus II, 3/2 street, Ninh Kieu district, Can Tho city - Vietnam)","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003036813","display_name":"Anne Laurent","orcid":"https://orcid.org/0000-0003-3708-6429"},"institutions":[{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anne LAURENT","raw_affiliation_strings":["Univ Montpellier, LIRMM, CNRS, Monpellier, France","WEB3 - WEB Architecture x Semantic WEB x WEB of Data (LIRMM, 161 rue Ada, 34000 Montpellier - France)"],"affiliations":[{"raw_affiliation_string":"Univ Montpellier, LIRMM, CNRS, Monpellier, France","institution_ids":["https://openalex.org/I4210101743","https://openalex.org/I19894307","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WEB3 - WEB Architecture x Semantic WEB x WEB of Data (LIRMM, 161 rue Ada, 34000 Montpellier - France)","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023360779","display_name":"Laurent d\u2019Orazio","orcid":"https://orcid.org/0000-0001-8614-1848"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent D'ORAZIO","raw_affiliation_strings":["SHAMAN - A Symbolic and Human-centric view of dAta MANagement ( IRISA/ENSSAT 6 rue de Kerampont -  BP 80518 - 22305 Lannion cedex - France)"],"affiliations":[{"raw_affiliation_string":"SHAMAN - A Symbolic and Human-centric view of dAta MANagement ( IRISA/ENSSAT 6 rue de Kerampont -  BP 80518 - 22305 Lannion cedex - France)","institution_ids":["https://openalex.org/I2802519937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034304045"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":0.3043,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.54495114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11478","display_name":"Caching and Content Delivery","score":0.9990000128746033,"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/T11719","display_name":"Data Quality and Management","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8503621220588684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287694215774536},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.6447471380233765},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6414592266082764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6352553367614746},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5416325926780701},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5275799036026001},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4854620099067688},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4762842059135437},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.346586674451828},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3329349160194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26633769273757935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21564450860023499}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8503621220588684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287694215774536},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.6447471380233765},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6414592266082764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6352553367614746},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5416325926780701},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5275799036026001},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4854620099067688},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4762842059135437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.346586674451828},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3329349160194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26633769273757935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21564450860023499},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fuzz48607.2020.9177610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz48607.2020.9177610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03107555v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03107555","pdf_url":"https://hal.science/hal-03107555v1/file/fuzzieee2020.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://wcci2020.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03107555v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03107555","pdf_url":"https://hal.science/hal-03107555v1/file/fuzzieee2020.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://wcci2020.org/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082524322.pdf","grobid_xml":"https://content.openalex.org/works/W3082524322.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1870305865","https://openalex.org/W1916323520","https://openalex.org/W1993284846","https://openalex.org/W2001040824","https://openalex.org/W2001700730","https://openalex.org/W2005207433","https://openalex.org/W2015666340","https://openalex.org/W2033258621","https://openalex.org/W2043099794","https://openalex.org/W2061601738","https://openalex.org/W2065259291","https://openalex.org/W2075620950","https://openalex.org/W2085922539","https://openalex.org/W2093050254","https://openalex.org/W2093080729","https://openalex.org/W2097184821","https://openalex.org/W2099194763","https://openalex.org/W2104599107","https://openalex.org/W2104615308","https://openalex.org/W2114353347","https://openalex.org/W2121516976","https://openalex.org/W2123845384","https://openalex.org/W2139599340","https://openalex.org/W2151930506","https://openalex.org/W2152565070","https://openalex.org/W2161443453","https://openalex.org/W2161936973","https://openalex.org/W2164329923","https://openalex.org/W2164634022","https://openalex.org/W2166400748","https://openalex.org/W2169387919","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2207847180","https://openalex.org/W2270660075","https://openalex.org/W2277471751","https://openalex.org/W2463897726","https://openalex.org/W2521888566","https://openalex.org/W2662027200","https://openalex.org/W2724806710","https://openalex.org/W2798891709","https://openalex.org/W2883952940","https://openalex.org/W2889189030","https://openalex.org/W2940589476","https://openalex.org/W6648522431","https://openalex.org/W6683401941","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2016456293","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"A":[0],"fuzzy":[1,43,87,109,113],"or":[2,35],"similarity":[3,127],"join":[4,44,91],"is":[5,32,45,53,117,149],"one":[6],"of":[7,26,84,155],"the":[8,30,90],"most":[9],"useful":[10],"data":[11,121],"processing":[12],"and":[13,58,60,139,162],"analysis":[14],"operations":[15],"for":[16,28,89],"Big":[17],"Data":[18],"in":[19,47,56],"a":[20,38,82,107,118,131],"general":[21],"context.":[22],"It":[23],"combines":[24],"pairs":[25],"tuples":[27],"which":[29],"distance":[31],"lower":[33],"than":[34,152],"equal":[36],"to":[37,75,111],"given":[39],"threshold":[40],"\u03b5.":[41],"The":[42],"used":[46],"many":[48],"practical":[49],"applications,":[50],"but":[51],"it":[52],"extremely":[54],"costly":[55],"time":[57],"space,":[59],"may":[61],"even":[62],"not":[63],"be":[64],"executed":[65],"on":[66],"large-scale":[67],"datasets.":[68],"Although":[69],"there":[70],"have":[71],"been":[72,94],"some":[73],"studies":[74],"improve":[76],"its":[77],"performance":[78],"by":[79,105,129],"applying":[80],"filters,":[81],"solution":[83],"an":[85],"effective":[86],"filter":[88,110,116],"has":[92],"never":[93],"conducted.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"thus":[100],"extend":[101],"our":[102,147],"previous":[103],"work":[104],"proposing":[106],"novel":[108],"optimize":[112],"joins.":[114],"This":[115],"compact,":[119],"probabilistic":[120],"structure":[122],"that":[123,146],"supports":[124],"very":[125],"fast":[126],"queries":[128],"maintaining":[130],"bit":[132],"matrix,":[133],"with":[134],"small":[135],"false":[136,141],"positive":[137],"rate":[138],"zero":[140],"negative":[142],"rate.":[143],"We":[144],"show":[145],"proposal":[148],"more":[150],"efficient":[151],"others":[153],"because":[154],"eliminating":[156],"redundant":[157],"data,":[158],"reducing":[159],"computation":[160],"cost":[161],"avoiding":[163],"duplicate":[164],"output.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}