{"id":"https://openalex.org/W2033809731","doi":"https://doi.org/10.1145/1517303.1517308","title":"Performance evaluation of similarity join for real time information integration","display_name":"Performance evaluation of similarity join for real time information integration","publication_year":2009,"publication_date":"2009-01-09","ids":{"openalex":"https://openalex.org/W2033809731","doi":"https://doi.org/10.1145/1517303.1517308","mag":"2033809731"},"language":"en","primary_location":{"id":"doi:10.1145/1517303.1517308","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1517303.1517308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Bangalore Annual Compute Conference","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/A5082000179","display_name":"Manish Kumar","orcid":"https://orcid.org/0000-0001-6639-8961"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Kumar","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064167934","display_name":"Shane Moriah","orcid":null},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shane Moriah","raw_affiliation_strings":["Stanford University, Palo Alto, California, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Palo Alto, California, CA","institution_ids":["https://openalex.org/I1743320","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415895","display_name":"Srikumar Krishnamoorthy","orcid":"https://orcid.org/0000-0002-2051-571X"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srikumar Krishnamoorthy","raw_affiliation_strings":["Infosys Technologies Ltd, Electronics City, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infosys Technologies Ltd, Electronics City, Bangalore, India","institution_ids":["https://openalex.org/I110675161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7144,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67582964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9991000294685364,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8062264323234558},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7936384677886963},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7531794309616089},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5952586531639099},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5921913385391235},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5180807113647461},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5084885358810425},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.45876994729042053},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4581214189529419},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39251649379730225},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3873707354068756},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34130311012268066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24026888608932495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062264323234558},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7936384677886963},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7531794309616089},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5952586531639099},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5921913385391235},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5180807113647461},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5084885358810425},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.45876994729042053},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4581214189529419},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39251649379730225},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3873707354068756},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34130311012268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24026888608932495},{"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/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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1517303.1517308","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1517303.1517308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Bangalore Annual Compute Conference","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":15,"referenced_works":["https://openalex.org/W1860104593","https://openalex.org/W1970026646","https://openalex.org/W2000982728","https://openalex.org/W2001496424","https://openalex.org/W2018597607","https://openalex.org/W2038281398","https://openalex.org/W2042281163","https://openalex.org/W2094951520","https://openalex.org/W2115159475","https://openalex.org/W2119057313","https://openalex.org/W2132151704","https://openalex.org/W2150916025","https://openalex.org/W2161936973","https://openalex.org/W2171960770","https://openalex.org/W2226407805"],"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/W3044917232","https://openalex.org/W2807741550","https://openalex.org/W794462722","https://openalex.org/W4221165003"],"abstract_inverted_index":{"Approximate":[0,40],"join":[1,29,41,142],"processing":[2,30,42,143],"serves":[3],"a":[4,46,73,124,130,151,169,184],"key":[5],"role":[6],"in":[7,27,64,81],"many":[8],"application":[9],"areas":[10],"such":[11,107],"as":[12],"data":[13,15,86,171],"cleansing,":[14],"integration,":[16],"text":[17],"mining,":[18],"and":[19,149],"bio-informatics.":[20],"There":[21],"has":[22],"been":[23],"much":[24],"research":[25],"interest":[26],"approximate":[28],"based":[31,50],"on":[32,183],"the":[33,55,58,65,68,82,96,133,138,147,157,160,180],"concept":[34],"of":[35,48,57,70,84,99,102,132,140,153,159],"an":[36],"edit":[37],"distance":[38],"metric.":[39],"algorithms":[43,108],"generally":[44],"use":[45],"variety":[47],"qgram":[49,119],"filtering":[51,127],"techniques":[52],"to":[53,136,155],"improve":[54,137],"scalability":[56,139],"system.":[59,161],"The":[60,162,177],"primary":[61],"approach":[62,94],"taken":[63],"literature":[66],"involves":[67,95],"exploitation":[69],"methods":[71],"inside":[72],"particular":[74],"database":[75],"language.":[76],"However,":[77,106],"this":[78],"is":[79,165],"impractical":[80],"case":[83],"heterogeneous":[85],"spread":[87],"across":[88],"multiple":[89],"databases.":[90],"A":[91],"popular":[92],"alternative":[93],"direct":[97],"comparison":[98],"all":[100],"permutations":[101],"two":[103],"string":[104],"pairings.":[105],"don't":[109],"scale":[110],"well":[111],"for":[112],"very":[113],"large":[114],"databases,":[115],"even":[116],"after":[117],"applying":[118],"filters.":[120],"Here":[121],"we":[122],"design":[123],"novel,":[125],"stand-alone":[126],"technique,":[128],"essentially":[129],"modification":[131],"HashJoin":[134],"algorithm,":[135],"similarity":[141],"algorithms.":[144],"We":[145],"implement":[146],"algorithm":[148,164],"conduct":[150],"number":[152],"experiments":[154],"study":[156],"performance":[158,181],"presented":[163],"also":[166],"integrated":[167],"with":[168],"real-life":[170,185],"federation":[172],"solution":[173],"called":[174],"Infosys":[175],"Gradient.":[176],"paper":[178],"presents":[179],"results":[182],"test":[186],"bed.":[187]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}