{"id":"https://openalex.org/W2015666340","doi":"https://doi.org/10.1145/2347673.2347676","title":"MapReduce-based similarity join for metric spaces","display_name":"MapReduce-based similarity join for metric spaces","publication_year":2012,"publication_date":"2012-08-31","ids":{"openalex":"https://openalex.org/W2015666340","doi":"https://doi.org/10.1145/2347673.2347676","mag":"2015666340"},"language":"en","primary_location":{"id":"doi:10.1145/2347673.2347676","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2347673.2347676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Cloud Intelligence","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/A5088912009","display_name":"Yasin N. Silva","orcid":"https://orcid.org/0000-0003-1852-1683"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasin N. Silva","raw_affiliation_strings":["Arizona State University, Glendale, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Glendale, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065710004","display_name":"Jason M. Reed","orcid":"https://orcid.org/0009-0009-9738-404X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason M. Reed","raw_affiliation_strings":["Arizona State University, Glendale, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Glendale, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062979355","display_name":"Lisa M. Tsosie","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa M. Tsosie","raw_affiliation_strings":["Arizona State University, Glendale, AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Glendale, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7338,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87301587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9997000098228455,"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":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9171051979064941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062154054641724},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.757125973701477},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6619284152984619},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6410495638847351},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5864867568016052},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5481508374214172},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.48861366510391235},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4866843819618225},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4156700074672699},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41441625356674194},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.31690889596939087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09748682379722595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09243103861808777}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9171051979064941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062154054641724},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.757125973701477},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6619284152984619},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6410495638847351},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5864867568016052},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5481508374214172},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48861366510391235},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4866843819618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4156700074672699},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41441625356674194},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31690889596939087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09748682379722595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09243103861808777},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2347673.2347676","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2347673.2347676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Cloud Intelligence","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":18,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W2043099794","https://openalex.org/W2061601738","https://openalex.org/W2065528935","https://openalex.org/W2093050254","https://openalex.org/W2115500858","https://openalex.org/W2121516976","https://openalex.org/W2125520775","https://openalex.org/W2128793454","https://openalex.org/W2151930506","https://openalex.org/W2154894831","https://openalex.org/W2161936973","https://openalex.org/W2173213060","https://openalex.org/W2188179155","https://openalex.org/W2205071250","https://openalex.org/W3120740533","https://openalex.org/W6635687051","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Cloud":[0],"enabled":[1],"systems":[2],"have":[3,51],"become":[4],"a":[5,40,87,116],"crucial":[6],"component":[7],"to":[8,91,112,123,149],"efficiently":[9,92,100],"process":[10],"and":[11,23,48,77,102,143,172],"analyze":[12],"massive":[13],"amounts":[14],"of":[15,18,64,80,162],"data.":[16],"One":[17],"the":[19,27,62,74,94,104,107,151],"key":[20],"data":[21,33,105,127,141],"processing":[22],"analysis":[24],"operations":[25],"is":[26,120],"Similarity":[28,55,65,82,95],"Join,":[29],"which":[30],"retrieves":[31],"all":[32],"pairs":[34],"whose":[35],"distances":[36],"are":[37,109],"smaller":[38],"than":[39],"predefined":[41],"threshold":[42],"\u03b5.":[43],"Even":[44],"though":[45],"multiple":[46,140],"algorithms":[47],"implementation":[49,78],"techniques":[50,79],"been":[52],"proposed":[53],"for":[54,67],"Joins,":[56],"very":[57,168],"little":[58],"work":[59],"has":[60,167],"addressed":[61],"study":[63],"Joins":[66],"cloud":[68,157],"systems.":[69],"This":[70,98],"paper":[71],"focuses":[72],"on":[73],"study,":[75],"design":[76],"cloud-based":[81],"Joins.":[83],"We":[84,146],"present":[85,147],"MRSimJoin,":[86],"MapReduce":[88],"based":[89],"algorithm":[90,99,152],"solve":[93],"Join":[96],"problem.":[97],"partitions":[101],"distributes":[103],"until":[106],"subsets":[108],"small":[110],"enough":[111,122],"be":[113,124,137],"processed":[114],"in":[115,130,153],"single":[117],"node.":[118],"MRSimJoin":[119,163],"general":[121],"used":[125,138],"with":[126,139],"that":[128,165],"lies":[129],"any":[131],"metric":[132],"space,":[133],"thus":[134],"it":[135,166],"can":[136],"types":[142],"distance":[144],"functions.":[145],"guidelines":[148],"implement":[150],"Hadoop,":[154],"an":[155],"open-source":[156],"system.":[158],"The":[159],"experimental":[160],"evaluation":[161],"shows":[164],"good":[169],"execution":[170],"time":[171],"scalability":[173],"properties.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
