{"id":"https://openalex.org/W2337865759","doi":null,"title":"An Expectation Maximisation Algorithm for One-to-Many Record Linkage, Illustrated on the Problem of Matching Far Infra-Red Astronomical Sources to Optical Counterparts","display_name":"An Expectation Maximisation Algorithm for One-to-Many Record Linkage, Illustrated on the Problem of Matching Far Infra-Red Astronomical Sources to Optical Counterparts","publication_year":2005,"publication_date":"2005-08-01","ids":{"openalex":"https://openalex.org/W2337865759","mag":"2337865759"},"language":"en","primary_location":{"id":"mag:2337865759","doi":null,"is_oa":false,"landing_page_url":"http://homepages.inf.ed.ac.uk/amos/publications/StorkeyEtAl2005AnEMAlgorithmForRecordLinkage.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5007901825","display_name":"Amos Storkey","orcid":"https://orcid.org/0000-0002-8100-506X","observed_orcids":["https://orcid.org/0000-0002-8100-506X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amos Storkey","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christopher R. Williams","orcid":"https://orcid.org/0000-0002-8736-1591","observed_orcids":["https://orcid.org/0000-0002-8736-1591"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher R. Williams","raw_affiliation_strings":["School of Informatics"],"raw_orcid":"https://orcid.org/0000-0002-8736-1591","affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Emma Taylor","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emma Taylor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050835191","display_name":"Robert G. Mann","orcid":"https://orcid.org/0000-0002-8894-1838","observed_orcids":["https://orcid.org/0000-0002-8894-1838"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert G. Mann","raw_affiliation_strings":["School of Physics and Astronomy"],"raw_orcid":"https://orcid.org/0000-0002-8894-1838","affiliations":[{"raw_affiliation_string":"School of Physics and Astronomy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5752,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77646776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9843999743461609,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9843999743461609,"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/T10026","display_name":"Galaxies: Formation, Evolution, Phenomena","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/data-linkage","display_name":"data linkage","score":0.9919999837875366},{"id":"https://openalex.org/keywords/one-to-many-matching","display_name":"one-to-many matching","score":0.871999979019165},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.8330000042915344},{"id":"https://openalex.org/keywords/far-infrared-sources","display_name":"far-infrared sources","score":0.7559999823570251},{"id":"https://openalex.org/keywords/optical-analogues","display_name":"optical counterparts","score":0.8550000190734863},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7210000157356262}],"concepts":[{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.765807032585144},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6956026554107666},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6121706366539001},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6109117269515991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5798923373222351},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5781646966934204},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5447507500648499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3593929409980774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3327445387840271},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09237831830978394},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2337865759","doi":null,"is_oa":false,"landing_page_url":"http://homepages.inf.ed.ac.uk/amos/publications/StorkeyEtAl2005AnEMAlgorithmForRecordLinkage.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W146123230","https://openalex.org/W1774330103","https://openalex.org/W1963623641","https://openalex.org/W1975723136","https://openalex.org/W1980040441","https://openalex.org/W2049855118","https://openalex.org/W2052390074","https://openalex.org/W2073471108","https://openalex.org/W2095714716","https://openalex.org/W2101561981","https://openalex.org/W2133416927","https://openalex.org/W2147555557","https://openalex.org/W2151103935","https://openalex.org/W2168190036","https://openalex.org/W3214380909"],"related_works":["https://openalex.org/W7096502297","https://openalex.org/W1547087245","https://openalex.org/W2176311362","https://openalex.org/W7096298559","https://openalex.org/W798336070","https://openalex.org/W3115636677","https://openalex.org/W7023910466","https://openalex.org/W2609569926","https://openalex.org/W2985964348","https://openalex.org/W1942524156"],"abstract_inverted_index":{"The":[0,128],"problem":[1,136],"of":[2,11,61,81,114,137,154],"record":[3,156],"linkage":[4,68,157],"is":[5,34,41,63,76,130,146],"often":[6,42],"seen":[7],"simply":[8],"in":[9,26,46,55,73,84],"terms":[10],"making":[12],"links":[13],"between":[14],"data":[15],"points":[16],"that":[17,124],"might":[18],"be":[19,103],"generated":[20],"from":[21],"the":[22,29,64,89,98,112,122,133,152],"same":[23],"source.":[24],"However,":[25],"many":[67],"cases":[28],"grounds":[30],"for":[31,105,132],"linking":[32,138],"items":[33],"itself":[35],"not":[36,161],"certain.":[37],"In":[38],"fact":[39],"it":[40],"desirable":[43],"to":[44,66,79,110,118,142],"learn,":[45],"an":[47],"unsupervised":[48],"manner,":[49],"what":[50],"form":[51],"linked":[52,78],"objects":[53,83,126],"take":[54],"dierent":[56],"databases.":[57],"One":[58],"simple":[59],"case":[60],"this":[62,106,155],"one":[74,80],"problem,":[69,108],"where":[70,88],"each":[71],"object":[72],"dataset":[75],"potentially":[77],"another":[85],"dataset,":[86],"and":[87,117],"candidate":[90],"matches":[91],"are":[92],"mutually":[93],"exclusive.":[94],"We":[95],"show":[96],"how":[97],"Expectation":[99],"Maximisation":[100],"algorithm":[101],"can":[102],"used":[104],"matching":[107],"both":[109],"calculate":[111],"probability":[113],"a":[115],"match,":[116],"learn":[119],"something":[120],"about":[121],"characteristics":[123],"matched":[125],"have.":[127],"approach":[129],"derived":[131],"specific":[134],"astronomical":[135],"far":[139],"infra-red":[140],"observations":[141],"optical":[143],"counterparts,":[144],"but":[145,159],"generally":[147],"applicable.":[148],"This":[149],"report":[150],"outlines":[151],"theory":[153],"procedure,":[158],"does":[160],"discuss":[162],"its":[163],"application":[164],"or":[165],"any":[166],"implementational":[167],"details.":[168]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
