{"id":"https://openalex.org/W2004539934","doi":"https://doi.org/10.1007/s10618-009-0155-0","title":"An incremental clustering scheme for data de-duplication","display_name":"An incremental clustering scheme for data de-duplication","publication_year":2009,"publication_date":"2009-10-27","ids":{"openalex":"https://openalex.org/W2004539934","doi":"https://doi.org/10.1007/s10618-009-0155-0","mag":"2004539934"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-009-0155-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10618-009-0155-0","pdf_url":null,"source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","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/A5076708603","display_name":"Gianni Costa","orcid":"https://orcid.org/0000-0003-2267-9280"},"institutions":[{"id":"https://openalex.org/I179420787","display_name":"Indian Council of Agricultural Research","ror":"https://ror.org/04fw54a43","country_code":"IN","type":"funder","lineage":["https://openalex.org/I179420787"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gianni Costa","raw_affiliation_strings":["ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","ICAR-CNR, Rende, Italy 87036"],"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","institution_ids":[]},{"raw_affiliation_string":"ICAR-CNR, Rende, Italy 87036","institution_ids":["https://openalex.org/I179420787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004372595","display_name":"Giuseppe Manco","orcid":"https://orcid.org/0000-0001-9672-3833"},"institutions":[{"id":"https://openalex.org/I179420787","display_name":"Indian Council of Agricultural Research","ror":"https://ror.org/04fw54a43","country_code":"IN","type":"funder","lineage":["https://openalex.org/I179420787"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Giuseppe Manco","raw_affiliation_strings":["ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","ICAR-CNR, Rende, Italy 87036"],"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","institution_ids":[]},{"raw_affiliation_string":"ICAR-CNR, Rende, Italy 87036","institution_ids":["https://openalex.org/I179420787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078466922","display_name":"Riccardo Ortale","orcid":"https://orcid.org/0000-0002-1763-9121"},"institutions":[{"id":"https://openalex.org/I179420787","display_name":"Indian Council of Agricultural Research","ror":"https://ror.org/04fw54a43","country_code":"IN","type":"funder","lineage":["https://openalex.org/I179420787"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Riccardo Ortale","raw_affiliation_strings":["ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","ICAR-CNR, Rende, Italy 87036"],"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Via P. Bucci 41c, 87036, Rende, CS, Italy","institution_ids":[]},{"raw_affiliation_string":"ICAR-CNR, Rende, Italy 87036","institution_ids":["https://openalex.org/I179420787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076708603"],"corresponding_institution_ids":["https://openalex.org/I179420787"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.6683,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.84810475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"152","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9973999857902527,"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/tuple","display_name":"Tuple","score":0.9307175278663635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6946984529495239},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6182270646095276},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.592352032661438},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.579865574836731},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5170896053314209},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4896257519721985},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.48454371094703674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36495304107666016},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3575863838195801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24522939324378967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2367440164089203},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08121451735496521},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07524770498275757}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.9307175278663635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6946984529495239},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6182270646095276},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.592352032661438},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.579865574836731},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5170896053314209},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4896257519721985},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.48454371094703674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36495304107666016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3575863838195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24522939324378967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2367440164089203},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08121451735496521},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07524770498275757},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10618-009-0155-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10618-009-0155-0","pdf_url":null,"source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W41404523","https://openalex.org/W46452414","https://openalex.org/W130948412","https://openalex.org/W938539187","https://openalex.org/W1502916507","https://openalex.org/W1523728576","https://openalex.org/W1541459201","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1646278814","https://openalex.org/W1673310716","https://openalex.org/W1990061958","https://openalex.org/W1991800036","https://openalex.org/W1992419399","https://openalex.org/W2024770506","https://openalex.org/W2029873015","https://openalex.org/W2036216970","https://openalex.org/W2038044292","https://openalex.org/W2043481183","https://openalex.org/W2055405704","https://openalex.org/W2057712948","https://openalex.org/W2065528935","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2082938030","https://openalex.org/W2087209402","https://openalex.org/W2095644746","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2111625757","https://openalex.org/W2121093772","https://openalex.org/W2124410446","https://openalex.org/W2127675794","https://openalex.org/W2129598390","https://openalex.org/W2131687179","https://openalex.org/W2140212450","https://openalex.org/W2146474310","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2150698190","https://openalex.org/W2152565070","https://openalex.org/W2154785834","https://openalex.org/W2157092487","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2610179052","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W2101053337","https://openalex.org/W2041478992","https://openalex.org/W2239248532"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
