{"id":"https://openalex.org/W7139962046","doi":"https://doi.org/10.1016/j.knosys.2026.115800","title":"LLM-based harmonized data ingestion for dataspace: a novel system for automating data ingestion across heterogeneous data sources","display_name":"LLM-based harmonized data ingestion for dataspace: a novel system for automating data ingestion across heterogeneous data sources","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7139962046","doi":"https://doi.org/10.1016/j.knosys.2026.115800"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.115800","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115800","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2026.115800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130226064","display_name":"Parwinder Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Parwinder Singh","raw_affiliation_strings":["Department of Business Development and Technology, Aarhus University, Herning, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-4106-111X","affiliations":[{"raw_affiliation_string":"Department of Business Development and Technology, Aarhus University, Herning, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michele Gaspari","orcid":"https://orcid.org/0009-0002-3640-9134"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michele Gaspari","raw_affiliation_strings":["Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":"https://orcid.org/0009-0002-3640-9134","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003885813","display_name":"Nirvana Meratnia","orcid":"https://orcid.org/0000-0002-8379-770X"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nirvana Meratnia","raw_affiliation_strings":["Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8379-770X","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050370124","display_name":"Mirko Presser","orcid":"https://orcid.org/0000-0001-7357-2796"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mirko Presser","raw_affiliation_strings":["Department of Business Development and Technology, Aarhus University, Herning, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7357-2796","affiliations":[{"raw_affiliation_string":"Department of Business Development and Technology, Aarhus University, Herning, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5130226064"],"corresponding_institution_ids":["https://openalex.org/I204337017","https://openalex.org/I83019370"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":{"value":3130,"currency":"USD","value_usd":3130},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30265622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"342","issue":null,"first_page":"115800","last_page":"115800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.5094000101089478,"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":0.5094000101089478,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.039400000125169754,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.03660000115633011,"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/ingestion","display_name":"Ingestion","score":0.3873000144958496},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2639999985694885},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2168000042438507},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.2046000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.413100004196167},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.4036000072956085},{"id":"https://openalex.org/C193230392","wikidata":"https://www.wikidata.org/wiki/Q1663054","display_name":"Ingestion","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23960000276565552},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2168000042438507},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2046000063419342},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.1988999992609024},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.19580000638961792},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.19509999454021454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.knosys.2026.115800","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115800","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/f7229835-a9bb-4ece-bddf-565e4fcaaa78","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/f7229835-a9bb-4ece-bddf-565e4fcaaa78","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Singh, P, Gaspari, M, Meratnia, N & Presser, M 2026, 'LLM-based harmonized data ingestion for dataspace : a novel system for automating data ingestion across heterogeneous data sources', Knowledge-Based Systems, vol. 342, 115800. https://doi.org/10.1016/j.knosys.2026.115800","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.tue.nl:openaire/2a5ce1b6-ceb3-41cb-bb98-22487c06050f","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/2a5ce1b6-ceb3-41cb-bb98-22487c06050f","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Singh, P, Gaspari, M, Meratnia, N & Presser, M 2026, 'LLM-based harmonized data ingestion for dataspace : a novel system for automating data ingestion across heterogeneous data sources', Knowledge-Based Systems, vol. 342, 115800. https://doi.org/10.1016/j.knosys.2026.115800","raw_type":"info:eu-repo/semantics/review"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2026.115800","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115800","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.4151974618434906}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321651","display_name":"Technische Universiteit Eindhoven","ror":"https://ror.org/02c2kyt77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2089634871","https://openalex.org/W2116341502","https://openalex.org/W2126624111","https://openalex.org/W2396881363","https://openalex.org/W3010180782","https://openalex.org/W3036098508","https://openalex.org/W3090471584","https://openalex.org/W3130855082","https://openalex.org/W3167537240","https://openalex.org/W4213432829","https://openalex.org/W4281878921","https://openalex.org/W4312663643","https://openalex.org/W4313439128","https://openalex.org/W4378194956","https://openalex.org/W4387810009","https://openalex.org/W4391222025","https://openalex.org/W4391403580","https://openalex.org/W4391462029","https://openalex.org/W4392023437","https://openalex.org/W4400020954"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,13,24,35,45],"Offers":[1],"a":[2,26,140,175,190,232,245,265],"new":[3,161],"vision":[4],"on":[5,63,134],"automated":[6,38,194,212],"data":[7,39,55,69,90,106,116,128,143,151,162,195,229,238,256,273,279,294],"harmonization":[8,154,196,254],"in":[9,185,275],"Dataspace":[10],"(DS)":[11,58],"systems.":[12],"Introduces":[14],"LLM-based":[15,217],"methods":[16],"for":[17,33,193,253],"scalable":[18,272],"DS":[19,78,131,184,200],"ingestion":[20,40,198,257],"of":[21,77,138,183],"heterogeneous":[22,54,146],"datasources.":[23],"Presents":[25],"system":[27,48,93,213,241],"with":[28,49],"Harmonizer,":[29],"Transformer,":[30],"Evaluator":[31],"components":[32],"ingestion.":[34],"Demonstrated":[36],"an":[37,211],"prototype":[41],"using":[42],"LLM":[43],"agents.":[44,219],"Validates":[46],"the":[47,73,86,118,136,179,259],"healthcare":[50,246],"use":[51,247],"case":[52],"harmonizing":[53],"sources.":[56],"Dataspaces":[57],"enable":[59],"stakeholders":[60],"to":[61,82,172,178,285],"collaborate":[62],"innovative,":[64],"data-driven":[65],"services":[66],"by":[67,215],"integrating":[68],"across":[70],"domains.":[71],"However,":[72],"realization":[74,180],"and":[75,89,94,108,148,155,170,181,207,225,271],"adoption":[76,182],"remain":[79],"challenging":[80],"due":[81],"domain-specific":[83],"heterogeneity":[84,96,224,295],"at":[85],"system,":[87],"service,":[88],"levels.":[91],"While":[92],"service-level":[95],"can":[97],"often":[98],"be":[99],"addressed":[100],"through":[101,244],"standards,":[102],"data-level":[103,223],"heterogeneity,":[104],"namely":[105],"structures":[107],"semantics":[109],"variations,":[110],"remains":[111],"challenging.":[112],"To":[113],"effectively":[114],"ingest":[115],"into":[117,199,258],"DS,":[119],"two":[120],"communication":[121],"endpoints":[122],"must":[123],"correctly":[124],"interpret":[125],"each":[126],"other\u2019s":[127],"models,":[129,230],"therefore,":[130],"ecosystems":[132],"rely":[133],"\u201charmonization\u201d,":[135],"process":[137],"generating":[139],"unified":[141],"target":[142,228],"model":[144],"from":[145,235],"sources":[147,163],"transforming":[149],"incoming":[150],"accordingly.":[152],"Currently,":[153],"transformation":[156],"are":[157,164],"performed":[158],"manually":[159],"whenever":[160],"integrated.":[165],"This":[166,187],"is":[167,242],"time-consuming,":[168],"costly,":[169],"difficult":[171],"scale,":[173],"posing":[174],"critical":[176],"barrier":[177],"practice.":[186],"study":[188],"proposes":[189],"novel":[191],"methodology":[192],"during":[197,255],"ecosystems.":[201],"The":[202,240],"approach":[203],"integrates":[204],"harmonization,":[205,280],"transformation,":[206],"human-in-the-loop":[208],"evaluation":[209],"within":[210],"powered":[214],"modern":[216],"AI":[218],"These":[220],"agents":[221],"address":[222],"generate":[226],"harmonized":[227],"representing":[231],"substantial":[233,283],"departure":[234],"current":[236],"manually-handled":[237],"harmonization.":[239],"validated":[243],"case,":[248],"demonstrating":[249],"its":[250],"practical":[251],"feasibility":[252],"DS.":[260,276],"Overall,":[261],"this":[262],"work":[263],"provides":[264],"foundational":[266],"step":[267],"toward":[268],"seamless,":[269],"efficient,":[270],"integration":[274],"By":[277],"automating":[278],"it":[281],"delivers":[282],"value":[284],"industry":[286],"digital":[287],"solutions":[288],"as":[289,291],"well":[290],"domains":[292],"where":[293],"persists,":[296],"including":[297],"IoT":[298],"or":[299],"Big":[300],"Data":[301],"platforms.":[302]},"counts_by_year":[],"updated_date":"2026-04-03T16:38:21.277918","created_date":"2026-03-21T00:00:00"}