{"id":"https://openalex.org/W1991909257","doi":"https://doi.org/10.14778/1920841.1920938","title":"Efficient and effective similarity search over probabilistic data based on earth mover's distance","display_name":"Efficient and effective similarity search over probabilistic data based on earth mover's distance","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W1991909257","doi":"https://doi.org/10.14778/1920841.1920938","mag":"1991909257"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920938","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920938","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5011019948","display_name":"Jia Xu","orcid":"https://orcid.org/0000-0001-7887-5913"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Xu","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633293","display_name":"Zhenjie Zhang","orcid":"https://orcid.org/0000-0003-1079-8784"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhenjie Zhang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023925931","display_name":"Anthony K. H. Tung","orcid":"https://orcid.org/0000-0002-5125-855X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Anthony K. H. Tung","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.57,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94370123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":"1-2","first_page":"758","last_page":"769"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9945999979972839,"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/earth-movers-distance","display_name":"Earth mover's distance","score":0.890428900718689},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7432806491851807},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7309136390686035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6738452911376953},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6279454231262207},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.56218421459198},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5334795713424683},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5276095867156982},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5241551399230957},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4631826877593994},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.42728888988494873},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4202856421470642},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3454418182373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31498074531555176},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3124490976333618},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2804860770702362},{"id":"https://openalex.org/keywords/database-model","display_name":"Database model","score":0.19702571630477905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19108659029006958}],"concepts":[{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.890428900718689},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7432806491851807},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7309136390686035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6738452911376953},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6279454231262207},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.56218421459198},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5334795713424683},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5276095867156982},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5241551399230957},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4631826877593994},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.42728888988494873},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4202856421470642},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3454418182373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31498074531555176},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3124490976333618},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2804860770702362},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.19702571630477905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19108659029006958},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/1920841.1920938","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920938","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.6672","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.6672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/%7Ezhangzh2/papers/TR-emd.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.8093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.8093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~vldb2010/proceedings/files/papers/R68.pdf","raw_type":"text"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39485","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39485","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"Scopus","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1490591387","https://openalex.org/W1512485814","https://openalex.org/W1545155892","https://openalex.org/W1978933387","https://openalex.org/W2003571118","https://openalex.org/W2005797502","https://openalex.org/W2024400846","https://openalex.org/W2041763948","https://openalex.org/W2042502381","https://openalex.org/W2044494469","https://openalex.org/W2045921448","https://openalex.org/W2053913299","https://openalex.org/W2054577069","https://openalex.org/W2069323107","https://openalex.org/W2076705731","https://openalex.org/W2078686663","https://openalex.org/W2088422262","https://openalex.org/W2101319014","https://openalex.org/W2108009586","https://openalex.org/W2109067452","https://openalex.org/W2112129552","https://openalex.org/W2117616929","https://openalex.org/W2120342618","https://openalex.org/W2121433213","https://openalex.org/W2125101937","https://openalex.org/W2130808343","https://openalex.org/W2132520482","https://openalex.org/W2134414349","https://openalex.org/W2134627110","https://openalex.org/W2136114025","https://openalex.org/W2137243801","https://openalex.org/W2140237757","https://openalex.org/W2143668817","https://openalex.org/W2149465349","https://openalex.org/W2154368191","https://openalex.org/W2163380389","https://openalex.org/W2166632516","https://openalex.org/W2166916904","https://openalex.org/W2168720188","https://openalex.org/W2169275758","https://openalex.org/W2666600683","https://openalex.org/W6672615329","https://openalex.org/W6684648153","https://openalex.org/W7008583937"],"related_works":["https://openalex.org/W2827250223","https://openalex.org/W2113053869","https://openalex.org/W1876081586","https://openalex.org/W3020377904","https://openalex.org/W2595721259","https://openalex.org/W1716383435","https://openalex.org/W4255001338","https://openalex.org/W2744606804","https://openalex.org/W4256561748","https://openalex.org/W1991909257"],"abstract_inverted_index":{"Probabilistic":[0],"data":[1],"is":[2,25,96],"coming":[3],"as":[4],"a":[5,114],"new":[6,37,115],"deluge":[7],"along":[8],"with":[9,89,109],"the":[10,30,47,51,56,61,77,85,90,97,130,139,164],"technical":[11],"advances":[12],"on":[13,102,126,129],"geographical":[14],"tracking,":[15],"multimedia":[16],"processing,":[17],"sensor":[18],"network":[19],"and":[20,105,122,145],"RFID.":[21],"While":[22],"similarity":[23,86],"search":[24,87],"an":[26,106],"important":[27],"functionality":[28],"supporting":[29],"manipulation":[31],"of":[32,50,132,166],"probabilistic":[33,78,103,127,167],"data,":[34,128],"it":[35],"raises":[36],"challenges":[38],"to":[39,118],"traditional":[40],"relational":[41],"database.":[42],"The":[43],"problem":[44,88],"stems":[45],"from":[46],"limited":[48],"effectiveness":[49],"distance":[52,66,100],"metric":[53,101],"supported":[54],"by":[55],"existing":[57],"database":[58,116],"system.":[59],"On":[60],"other":[62],"hand,":[63],"some":[64],"complicated":[65],"operators":[67],"have":[68],"proven":[69],"their":[70],"values":[71],"for":[72,152],"better":[73],"distinguishing":[74],"ability":[75],"in":[76,142],"domain.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83],"discuss":[84],"Earth":[91,133],"Mover's":[92,134],"Distance":[93],",":[94],"which":[95],"most":[98],"successful":[99],"histograms":[104],"expensive":[107],"operator":[108],"cubic":[110],"complexity.":[111],"We":[112],"present":[113],"approach":[117],"answer":[119],"range":[120],"queries":[121,125],"k-nearest":[123],"neighbor":[124],"basis":[131],"Distance.":[135],"Our":[136],"solution":[137],"utilizes":[138],"primal-dual":[140],"theory":[141],"linear":[143],"programming":[144],"deploys":[146],"B":[147],"+":[148],"tree":[149],"index":[150],"structures":[151],"effective":[153],"candidate":[154],"pruning.":[155],"Extensive":[156],"experiments":[157],"show":[158],"that":[159],"our":[160],"proposal":[161],"dramatically":[162],"improves":[163],"scalability":[165],"databases.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}