{"id":"https://openalex.org/W4388517795","doi":"https://doi.org/10.1109/fuzz52849.2023.10309759","title":"Scalable Computation of Fuzzy Joins Over Large Collections of JSON Data","display_name":"Scalable Computation of Fuzzy Joins Over Large Collections of JSON Data","publication_year":2023,"publication_date":"2023-08-13","ids":{"openalex":"https://openalex.org/W4388517795","doi":"https://doi.org/10.1109/fuzz52849.2023.10309759"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz52849.2023.10309759","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fuzz52849.2023.10309759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Fuzzy Systems (FUZZ)","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/A5093228305","display_name":"Remi Uhartegaray","orcid":null},"institutions":[{"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":"Remi Uhartegaray","raw_affiliation_strings":["Univ Rennes, ENSSAT,Lannion,France","UR - Universit\u00e9 de Rennes (Campus de Beaulieu, 263 avenue G\u00e9n\u00e9ral Leclerc, CS 74205, 35042 RENNES CEDEX - France)","ENSSAT - \u00c9cole Nationale Sup\u00e9rieure des Sciences Appliqu\u00e9es et de Technologie (6 rue de Kerampont - BP 80518 - 22305 Lannion Cedex - France)"],"affiliations":[{"raw_affiliation_string":"Univ Rennes, ENSSAT,Lannion,France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"UR - Universit\u00e9 de Rennes (Campus de Beaulieu, 263 avenue G\u00e9n\u00e9ral Leclerc, CS 74205, 35042 RENNES CEDEX - France)","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"ENSSAT - \u00c9cole Nationale Sup\u00e9rieure des Sciences Appliqu\u00e9es et de Technologie (6 rue de Kerampont - BP 80518 - 22305 Lannion Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023360779","display_name":"Laurent d\u2019Orazio","orcid":"https://orcid.org/0000-0001-8614-1848"},"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":false,"raw_author_name":"Laurent D'Orazio","raw_affiliation_strings":["Univ Rennes, CNRS, IRISA,Lannion,France","IRISA - Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires (Avenue du g\u00e9n\u00e9ral Leclerc\r\nCampus de Beaulieu \r\n35042 RENNES CEDEX - 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":"IRISA - Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires (Avenue du g\u00e9n\u00e9ral Leclerc\r\nCampus de Beaulieu \r\n35042 RENNES CEDEX - France)","institution_ids":["https://openalex.org/I2802519937"]},{"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/A5011408035","display_name":"Matthew Damigos","orcid":"https://orcid.org/0000-0003-0431-1482"},"institutions":[{"id":"https://openalex.org/I187792471","display_name":"Ionian University","ror":"https://ror.org/01xm4n520","country_code":"GR","type":"education","lineage":["https://openalex.org/I187792471"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Matthew Damigos","raw_affiliation_strings":["Library Science & Museology Ionian University,Department of Archives,Corfu,Greece","Ionian University [Corfu] (Greece)"],"affiliations":[{"raw_affiliation_string":"Library Science & Museology Ionian University,Department of Archives,Corfu,Greece","institution_ids":["https://openalex.org/I187792471"]},{"raw_affiliation_string":"Ionian University [Corfu] (Greece)","institution_ids":["https://openalex.org/I187792471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066065255","display_name":"Eleftherios Kalogeros","orcid":"https://orcid.org/0000-0001-8080-6343"},"institutions":[{"id":"https://openalex.org/I187792471","display_name":"Ionian University","ror":"https://ror.org/01xm4n520","country_code":"GR","type":"education","lineage":["https://openalex.org/I187792471"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Eleftherios Kalogeros","raw_affiliation_strings":["Library Science & Museology Ionian University,Department of Archives,Corfu,Greece","Ionian University [Corfu] (Greece)"],"affiliations":[{"raw_affiliation_string":"Library Science & Museology Ionian University,Department of Archives,Corfu,Greece","institution_ids":["https://openalex.org/I187792471"]},{"raw_affiliation_string":"Ionian University [Corfu] (Greece)","institution_ids":["https://openalex.org/I187792471"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093228305"],"corresponding_institution_ids":["https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15605634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987000226974487,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/joins","display_name":"Joins","score":0.9225236177444458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839289665222168},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.8382935523986816},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5466894507408142},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.484872430562973},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46207359433174133},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4598582088947296},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4354482889175415},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37865719199180603},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15400898456573486}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9225236177444458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839289665222168},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8382935523986816},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5466894507408142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.484872430562973},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46207359433174133},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4598582088947296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4354482889175415},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37865719199180603},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15400898456573486},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fuzz52849.2023.10309759","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fuzz52849.2023.10309759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Fuzzy Systems (FUZZ)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04354170v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04354170","pdf_url":null,"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":"2023 IEEE International Conference on Fuzzy Systems (FUZZ), Aug 2023, Incheon, South Korea. ⟨10.1109/fuzz52849.2023.10309759⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1870305865","https://openalex.org/W2001700730","https://openalex.org/W2015666340","https://openalex.org/W2016885468","https://openalex.org/W2061601738","https://openalex.org/W2065259291","https://openalex.org/W2075620950","https://openalex.org/W2085922539","https://openalex.org/W2093050254","https://openalex.org/W2107412086","https://openalex.org/W2114353347","https://openalex.org/W2136393336","https://openalex.org/W2151930506","https://openalex.org/W2161443453","https://openalex.org/W2164329923","https://openalex.org/W2164634022","https://openalex.org/W2166400748","https://openalex.org/W2169387919","https://openalex.org/W2171909018","https://openalex.org/W2173213060","https://openalex.org/W2207847180","https://openalex.org/W2256384365","https://openalex.org/W2277471751","https://openalex.org/W2463897726","https://openalex.org/W2493109812","https://openalex.org/W2521506077","https://openalex.org/W2521888566","https://openalex.org/W2574472735","https://openalex.org/W2766209620","https://openalex.org/W2883952940","https://openalex.org/W2889189030","https://openalex.org/W2940589476","https://openalex.org/W2992058379","https://openalex.org/W3082524322","https://openalex.org/W3098667566","https://openalex.org/W3204225708","https://openalex.org/W4281720128","https://openalex.org/W4296011030","https://openalex.org/W4300494090","https://openalex.org/W4301217393","https://openalex.org/W6636915900","https://openalex.org/W6844496471"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W2365783963","https://openalex.org/W2622139626"],"abstract_inverted_index":{"Fuzzy":[0],"joins":[1,30,50,59,98],"are":[2],"widely":[3],"used":[4],"in":[5,66,93],"a":[6],"variety":[7],"of":[8,25,72,102,113],"data":[9,14,16,20,53,62],"analysis":[10],"applications":[11],"such":[12],"as":[13,117,119],"integration,":[15],"mining,":[17],"and":[18,40,54],"master":[19],"management.":[21],"In":[22,83],"the":[23,35,41,56,67,70,76,111,114],"context":[24],"Big":[26],"Data,":[27],"computing":[28],"fuzzy":[29,49,97],"is":[31,78],"challenging":[32],"due":[33],"to":[34,69,95],"high":[36],"computational":[37],"cost":[38],"required":[39],"communication":[42],"cost.":[43],"While":[44],"on":[45,51,55,60],"one":[46],"hand":[47,58],"big":[48],"relational":[52],"other":[57],"tree-structured":[61],"have":[63],"been":[64],"investigated":[65],"literature,":[68],"best":[71],"our":[73],"knowledge,":[74],"combining":[75],"two":[77],"still":[79],"an":[80],"open":[81],"problem.":[82],"this":[84],"context,":[85],"we":[86],"study":[87],"methods":[88],"for":[89],"leveraging":[90],"distributed":[91],"environments":[92],"order":[94],"compute":[96],"over":[99],"large":[100],"collections":[101],"JSON":[103],"documents.":[104],"Our":[105],"algorithms":[106],"take":[107],"into":[108],"account":[109],"both":[110],"text-similarity":[112],"joining":[115],"data,":[116],"well":[118],"its":[120],"structural":[121],"similarity.":[122]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}