{"id":"https://openalex.org/W4392667206","doi":"https://doi.org/10.1109/access.2024.3375750","title":"Metadata-Based Clustering and Selection of Metadata Items for Similar Dataset Discovery and Data Combination Tasks","display_name":"Metadata-Based Clustering and Selection of Metadata Items for Similar Dataset Discovery and Data Combination Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392667206","doi":"https://doi.org/10.1109/access.2024.3375750"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3375750","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3375750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10464313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10464313.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063175599","display_name":"Takeshi Sakumoto","orcid":"https://orcid.org/0000-0002-7589-3283"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Sakumoto","raw_affiliation_strings":["Department of Engineering, Nagaoka University of Technology, Nagaoka, Niigata, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7589-3283","affiliations":[{"raw_affiliation_string":"Department of Engineering, Nagaoka University of Technology, Nagaoka, Niigata, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015928651","display_name":"Teruaki Hayashi","orcid":"https://orcid.org/0000-0002-1806-5852"},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"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":"Teruaki Hayashi","raw_affiliation_strings":["Department of Engineering, The University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1806-5852","affiliations":[{"raw_affiliation_string":"Department of Engineering, The University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028823648","display_name":"Hiroki Sakaji","orcid":"https://orcid.org/0000-0001-5030-625X"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Sakaji","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027540609","display_name":"Hirofumi Nonaka","orcid":"https://orcid.org/0000-0001-8484-1541"},"institutions":[{"id":"https://openalex.org/I190508380","display_name":"Aichi Institute of Technology","ror":"https://ror.org/02qsepw74","country_code":"JP","type":"education","lineage":["https://openalex.org/I190508380"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Nonaka","raw_affiliation_strings":["Faculty of Business Administration, Aichi Institute of Technology, Toyota, Aichi, Japan","mayolab Co., Ltd, Nagaoka, Niigata, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Business Administration, Aichi Institute of Technology, Toyota, Aichi, Japan","institution_ids":["https://openalex.org/I190508380"]},{"raw_affiliation_string":"mayolab Co., Ltd, Nagaoka, Niigata, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1995,"currency":"USD","value_usd":1995},"apc_paid":{"value":1995,"currency":"USD","value_usd":1995},"fwci":0.9203,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77736806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"40213","last_page":"40224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9972000122070312,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9959999918937683,"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":0.8331509828567505},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7894738912582397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7459579706192017},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6294639110565186},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.586351215839386},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5147097706794739},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5049441456794739},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44878458976745605},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26377660036087036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2171688675880432},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07990849018096924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07789617776870728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331509828567505},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7894738912582397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7459579706192017},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6294639110565186},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.586351215839386},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5147097706794739},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5049441456794739},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44878458976745605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26377660036087036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2171688675880432},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07990849018096924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07789617776870728},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3375750","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3375750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10464313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:35ad149ab17f48fbb1733fdb323e33ec","is_oa":true,"landing_page_url":"https://doaj.org/article/35ad149ab17f48fbb1733fdb323e33ec","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 40213-40224 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3375750","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3375750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10464313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1031001114","display_name":"Fundamental study of a technology search and creation model that mimics the patent examination process","funder_award_id":"19K12116","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3486879496","display_name":"System Design and Dynamics of Data Exchange Market","funder_award_id":"20H02384","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392667206.pdf","grobid_xml":"https://content.openalex.org/works/W4392667206.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1554829397","https://openalex.org/W1604277348","https://openalex.org/W1614298861","https://openalex.org/W2294768397","https://openalex.org/W2404652541","https://openalex.org/W2613704683","https://openalex.org/W2788550262","https://openalex.org/W2790400697","https://openalex.org/W2793379979","https://openalex.org/W2896457183","https://openalex.org/W2899286282","https://openalex.org/W2907648650","https://openalex.org/W2926805670","https://openalex.org/W2964918724","https://openalex.org/W2975452411","https://openalex.org/W3003952093","https://openalex.org/W3014616325","https://openalex.org/W3021792233","https://openalex.org/W3081749234","https://openalex.org/W3087595142","https://openalex.org/W3094230039","https://openalex.org/W3099839495","https://openalex.org/W3102264439","https://openalex.org/W3108941002","https://openalex.org/W3130880317","https://openalex.org/W3137087849","https://openalex.org/W3152153867","https://openalex.org/W3154140311","https://openalex.org/W3172420892","https://openalex.org/W3209329314","https://openalex.org/W4205961906","https://openalex.org/W4206294234","https://openalex.org/W4210515742","https://openalex.org/W4211124270","https://openalex.org/W4281763099","https://openalex.org/W4285820222","https://openalex.org/W4294558859","https://openalex.org/W4319660025","https://openalex.org/W6636510571","https://openalex.org/W6732414893","https://openalex.org/W6747248625","https://openalex.org/W6755207826","https://openalex.org/W6796775955"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2327130486"],"abstract_inverted_index":{"Data":[0],"integration,":[1],"which":[2],"aims":[3],"to":[4,39,107],"solve":[5],"problems":[6],"and":[7,68,120,148,166],"create":[8],"new":[9],"services":[10],"by":[11],"combining":[12],"datasets,":[13,67],"has":[14],"attracted":[15],"considerable":[16],"attention.":[17],"The":[18],"discovery":[19,43,58],"of":[20,85,88,101,124,127,171,174],"similar":[21,33],"datasets":[22,149],"that":[23,113,157,169],"can":[24,177],"be":[25,115,161],"combined":[26],"is":[27,37],"critical.":[28],"In":[29],"the":[30,51,74,82,86,99,102,110,122,172],"literature":[31],"on":[32,130,139],"dataset":[34],"discovery,":[35],"it":[36],"important":[38],"select":[40],"an":[41],"appropriate":[42,75],"method":[44,76],"for":[45,78,117,150,163],"each":[46,79,118,164],"information":[47],"need,":[48],"such":[49,63],"as":[50,64],"domain.":[52],"However,":[53],"conventional":[54,96],"studies":[55,97],"have":[56],"evaluated":[57,133],"methods":[59,90,176],"in":[60],"different":[61,89,128,140,175],"ways,":[62],"domains,":[65],"test":[66],"evaluation":[69,146],"metrics.":[70],"This":[71,104],"factor":[72],"prevents":[73],"selection":[77],"situation.":[80],"Furthermore,":[81],"specific":[83],"effects":[84,123],"combination":[87,126],"are":[91],"not":[92],"well":[93],"known":[94],"despite":[95],"arguing":[98],"importance":[100],"combination.":[103],"study":[105],"attempts":[106],"understand":[108],"(1)":[109,155],"similarity":[111,142,158],"indicators":[112,129,159],"should":[114,160],"employed":[116],"domain":[119,165],"(2)":[121,167],"a":[125],"performance.":[131,180],"We":[132],"16":[134],"inter-dataset":[135],"clustering":[136,179],"models":[137],"based":[138],"metadata-based":[141],"indicators,":[143],"using":[144],"unified":[145],"metrics":[147],"15":[151],"domains.":[152],"Our":[153],"results":[154],"suggest":[156],"used":[162],"demonstrate":[168],"most":[170],"combinations":[173],"improve":[178]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}