{"id":"https://openalex.org/W2022475295","doi":"https://doi.org/10.1109/ghtc.2014.6970340","title":"Next generation data classification and linkage: Role of probabilistic models and artificial intelligence","display_name":"Next generation data classification and linkage: Role of probabilistic models and artificial intelligence","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2022475295","doi":"https://doi.org/10.1109/ghtc.2014.6970340","mag":"2022475295"},"language":"en","primary_location":{"id":"doi:10.1109/ghtc.2014.6970340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ghtc.2014.6970340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Global Humanitarian Technology Conference (GHTC 2014)","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/A5079813742","display_name":"Gayan Prasad Hettiarachchi","orcid":"https://orcid.org/0000-0002-2553-483X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gayan Prasad Hettiarachchi","raw_affiliation_strings":["Department of Physics, Osaka University, Osaka, Japan","Department of Physics, Osaka University, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Physics, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Department of Physics, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048872784","display_name":"Nadeeka Nilmini Hettiarachchi","orcid":null},"institutions":[{"id":"https://openalex.org/I113198587","display_name":"National Institute of Genetics","ror":"https://ror.org/02xg1m795","country_code":"JP","type":"facility","lineage":["https://openalex.org/I113198587","https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nadeeka Nilmini Hettiarachchi","raw_affiliation_strings":["Department of Population Genetics, National Institute of Genetics, Mishima, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Population Genetics, National Institute of Genetics, Mishima, Japan","institution_ids":["https://openalex.org/I113198587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455198","display_name":"Dhammika Suresh Hettiarachchi","orcid":null},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dhammika Suresh Hettiarachchi","raw_affiliation_strings":["Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo, Japan","Dept. of Electrical Engineering and Information systems, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Dept. of Electrical Engineering and Information systems, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064286185","display_name":"Azusa Ebisuya","orcid":null},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Azusa Ebisuya","raw_affiliation_strings":["Graduate School of Economics, Osaka University, Osaka, Japan","Graduate Sch. of Econ., Osaka Univ., Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Economics, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I14314212"]},{"raw_affiliation_string":"Graduate Sch. of Econ., Osaka Univ., Japan","institution_ids":["https://openalex.org/I14314212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079813742"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.1161023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"569","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9896000027656555,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541107535362244},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6943777203559875},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6666566133499146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6209251284599304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5621265172958374},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5593894720077515},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5179735422134399},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5105692148208618},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49869203567504883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4636259078979492},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.44341564178466797},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4259444773197174},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.42426663637161255},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09268113970756531},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.0770183801651001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541107535362244},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6943777203559875},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6666566133499146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209251284599304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5621265172958374},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5593894720077515},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5179735422134399},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5105692148208618},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49869203567504883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4636259078979492},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.44341564178466797},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4259444773197174},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.42426663637161255},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09268113970756531},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0770183801651001},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ghtc.2014.6970340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ghtc.2014.6970340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Global Humanitarian Technology Conference (GHTC 2014)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1487746570","https://openalex.org/W1489489715","https://openalex.org/W1531857721","https://openalex.org/W2034190452","https://openalex.org/W2075509956","https://openalex.org/W2093533529","https://openalex.org/W2114793173","https://openalex.org/W2163756102","https://openalex.org/W2171574281","https://openalex.org/W2196611479","https://openalex.org/W2330816906","https://openalex.org/W2920943913","https://openalex.org/W6601892241","https://openalex.org/W6631775930"],"related_works":["https://openalex.org/W2784199898","https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W2024018837","https://openalex.org/W2895059799","https://openalex.org/W3211905090","https://openalex.org/W1936317645"],"abstract_inverted_index":{"Data":[0],"classification":[1,26,118,147],"and":[2,27,107,119,129,137,141,148,195],"linkage":[3,28,149,161],"is":[4,39,61,162,166,189],"the":[5,12,62,112,171,184],"task":[6],"of":[7,45,55,86,101,175,181,186],"identifying":[8],"information":[9],"corresponding":[10],"to":[11,23,52,73,80,123],"same":[13],"entity":[14,188],"from":[15],"one":[16],"or":[17,68],"more":[18],"data":[19,25,117,124,146],"sources.":[20],"Methods":[21],"used":[22,37,51,72],"tackle":[24],"problems":[29],"fall":[30],"into":[31],"two":[32],"broad":[33],"categories.":[34],"One":[35],"commonly":[36],"method":[38],"deterministic":[40],"models,":[41,132],"in":[42,65,191],"which":[43,66],"sets":[44],"often":[46],"very":[47],"complex":[48],"rules":[49],"are":[50,71,84,151],"classify":[53,74],"pairs":[54],"entities":[56],"as":[57],"links.":[58],"The":[59],"other":[60],"probabilistic":[63,69],"model,":[64],"statistical":[67],"approaches":[70],"pairs.":[75],"However,":[76],"these":[77],"models":[78,115],"fail":[79],"deliver":[81],"when":[82],"there":[83],"lots":[85],"missing":[87,193],"values,":[88],"typographical":[89],"errors,":[90],"non-standardized":[91],"entities,":[92,177],"etc.":[93],"To":[94],"this":[95],"end,":[96],"intelligent":[97],"routines":[98],"making":[99],"use":[100],"artificial":[102],"neural":[103],"networks,":[104],"genetic":[105],"algorithms":[106,109],"clustering":[108],"can":[110,196],"provide":[111,197],"next":[113,144],"generation":[114,145],"for":[116,143,160],"linkage.":[120],"An":[121],"introduction":[122],"linkage,":[125],"impact":[126],"on":[127],"humanity":[128],"community,":[130],"current":[131],"associated":[133],"pitfalls,":[134],"new":[135,158],"directions":[136],"issues":[138],"both":[139],"technical":[140],"social":[142],"systems":[150],"discussed":[152],"using":[153],"an":[154,187],"example":[155],"prototype.":[156],"A":[157],"model":[159],"proposed,":[163],"where":[164],"it":[165],"highlighted":[167],"that":[168],"not":[169],"only":[170],"relationships":[172,182],"between":[173],"attributes":[174,185],"different":[176],"but":[178],"also":[179],"identification":[180],"within":[183],"important":[190],"handling":[192],"values":[194],"better":[198],"accuracy.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
