{"id":"https://openalex.org/W2584010011","doi":"https://doi.org/10.1109/bigdata.2016.7840662","title":"Parallel computation of k-nearest neighbor joins using MapReduce","display_name":"Parallel computation of k-nearest neighbor joins using MapReduce","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584010011","doi":"https://doi.org/10.1109/bigdata.2016.7840662","mag":"2584010011"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5055390798","display_name":"Wooyeol Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wooyeol Kim","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327650","display_name":"Younghoon Kim","orcid":"https://orcid.org/0000-0002-3049-035X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younghoon Kim","raw_affiliation_strings":["Hanyang University"],"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049064713","display_name":"Kyuseok Shim","orcid":"https://orcid.org/0000-0001-8818-0963"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuseok Shim","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055390798"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":2.0404,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88391756,"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":"696","last_page":"705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9901999831199646,"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/joins","display_name":"Joins","score":0.9822865724563599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8568904399871826},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8243145942687988},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6711224913597107},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6674038767814636},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5476778745651245},{"id":"https://openalex.org/keywords/map-reduce","display_name":"Map reduce","score":0.5185054540634155},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4925723671913147},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4766067862510681},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4744490385055542},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43885284662246704},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3393970727920532},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32659560441970825},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2899664640426636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25504133105278015},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.155803382396698}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9822865724563599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568904399871826},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8243145942687988},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6711224913597107},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6674038767814636},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5476778745651245},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.5185054540634155},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4925723671913147},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4766067862510681},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4744490385055542},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43885284662246704},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3393970727920532},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32659560441970825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2899664640426636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25504133105278015},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.155803382396698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2016.7840662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hanyang.ac.kr:20.500.11754/103069","is_oa":false,"landing_page_url":"http://repository.hanyang.ac.kr/handle/20.500.11754/103069","pdf_url":null,"source":{"id":"https://openalex.org/S4306401328","display_name":"The Royal Society of Chemistry\u2019s Journals, Books and Databases (The Royal Society of Chemistry)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2751430930","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/I2751430930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1588513474","https://openalex.org/W1590918896","https://openalex.org/W1987403831","https://openalex.org/W1990111898","https://openalex.org/W2016854254","https://openalex.org/W2046144220","https://openalex.org/W2049003051","https://openalex.org/W2058458206","https://openalex.org/W2083669917","https://openalex.org/W2086504823","https://openalex.org/W2100344784","https://openalex.org/W2118269922","https://openalex.org/W2129281431","https://openalex.org/W2154879298","https://openalex.org/W2156504591","https://openalex.org/W2157057296","https://openalex.org/W2157234796","https://openalex.org/W2161694911","https://openalex.org/W2173213060","https://openalex.org/W2212819718","https://openalex.org/W2296349981","https://openalex.org/W3003570628","https://openalex.org/W3120740533","https://openalex.org/W4242599275","https://openalex.org/W6635003556","https://openalex.org/W6683269862"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W650102067","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W3033055359","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"The":[0],"k-nearest":[1],"neighbor":[2],"(kNN)":[3],"join":[4,29],"has":[5],"recently":[6,64],"attracted":[7],"considerable":[8],"attention":[9],"due":[10,22],"to":[11,23,40,53,81,117,125],"its":[12],"broad":[13],"applications.":[14],"However,":[15],"processing":[16],"fcNN":[17,46,84,96,133],"joins":[18,47,85,97],"is":[19,34],"very":[20],"expensive":[21],"the":[24,28,76,83,92,100,109,129,139,144],"quadratic":[25],"nature":[26],"of":[27,38,69,95,103,131,143],"operation.":[30],"Furthermore,":[31],"since":[32],"there":[33],"an":[35],"increasing":[36],"trend":[37],"applications":[39],"deal":[41],"with":[42],"big":[43,56],"data,":[44,57],"computing":[45,61],"becomes":[48],"more":[49],"challenging.":[50],"In":[51,71],"order":[52],"process":[54,82],"such":[55],"parallel":[58,78],"and":[59,141],"distributed":[60],"using":[62,86],"MapReduce":[63],"have":[65],"received":[66],"a":[67,132],"lot":[68],"attention.":[70],"this":[72],"paper,":[73],"we":[74,107],"propose":[75],"efficient":[77],"algorithm":[79],"KNN-MR":[80],"MapReduce.":[87],"To":[88],"reduce":[89],"not":[90,124],"only":[91],"computational":[93],"cost":[94,102],"but":[98],"also":[99],"network":[101],"communicating":[104],"across":[105],"machines,":[106],"develop":[108],"novel":[110],"vector":[111],"projection":[112],"pruning":[113],"which":[114],"enables":[115],"us":[116],"identify":[118],"non-fcNN":[119],"points":[120],"that":[121],"are":[122],"guaranteed":[123],"be":[126],"included":[127],"in":[128],"result":[130],"join.":[134],"Our":[135],"performance":[136],"study":[137],"confirms":[138],"effectiveness":[140],"scalability":[142],"proposed":[145],"algorithm.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}