{"id":"https://openalex.org/W3031902962","doi":"https://doi.org/10.1145/3386723.3387877","title":"Enhanced Duplicate Count Strategy","display_name":"Enhanced Duplicate Count Strategy","publication_year":2020,"publication_date":"2020-03-31","ids":{"openalex":"https://openalex.org/W3031902962","doi":"https://doi.org/10.1145/3386723.3387877","mag":"3031902962"},"language":"en","primary_location":{"id":"doi:10.1145/3386723.3387877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386723.3387877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Networking, Information Systems &amp; Security","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/A5047244165","display_name":"Y. Aassem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youssef Aassem","raw_affiliation_strings":["National School of applied sciences, Khouribga, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National School of applied sciences, Khouribga, Morocco","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023641124","display_name":"Imad Hafidi","orcid":"https://orcid.org/0000-0002-5039-2458"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imad Hafidi","raw_affiliation_strings":["National School of applied sciences, Khouribga, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National School of applied sciences, Khouribga, Morocco","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077494499","display_name":"Noureddine Aboutabit","orcid":"https://orcid.org/0000-0002-6984-4776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noureddine Aboutabit","raw_affiliation_strings":["National School of applied sciences, Khouribga, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National School of applied sciences, Khouribga, Morocco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5577,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70977594,"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753210186958313},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7145615220069885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6624277830123901},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5593403577804565},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5450392961502075},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49955177307128906},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4705871641635895},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4472082555294037},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44208860397338867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4069301187992096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29753631353378296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15710890293121338},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11442452669143677},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08926859498023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753210186958313},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7145615220069885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6624277830123901},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5593403577804565},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5450392961502075},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49955177307128906},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4705871641635895},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4472082555294037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44208860397338867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4069301187992096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29753631353378296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15710890293121338},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11442452669143677},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08926859498023987},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":"doi:10.1145/3386723.3387877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386723.3387877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Networking, Information Systems &amp; Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W175950377","https://openalex.org/W1547612978","https://openalex.org/W1595498733","https://openalex.org/W1612155886","https://openalex.org/W1977340740","https://openalex.org/W2011940398","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2039001182","https://openalex.org/W2077044633","https://openalex.org/W2082696804","https://openalex.org/W2104734478","https://openalex.org/W2128661986","https://openalex.org/W2136517229","https://openalex.org/W2147107544","https://openalex.org/W2154785834","https://openalex.org/W2166988329","https://openalex.org/W2500925358","https://openalex.org/W2594063363","https://openalex.org/W2594735838","https://openalex.org/W2621063299","https://openalex.org/W2765590357","https://openalex.org/W2889154254","https://openalex.org/W4248296022","https://openalex.org/W4254788633"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W2010725720","https://openalex.org/W4310066305"],"abstract_inverted_index":{"Duplicate":[0,91],"detection":[1],"is":[2,16,95,110,131],"the":[3,22,26,36,52,59,73,79,121],"process":[4,60],"of":[5,9,54],"detecting":[6],"multiple":[7],"representations":[8],"same":[10],"real":[11],"world's":[12],"entities.":[13],"Nowadays,":[14],"data":[15],"known":[17],"to":[18,50,136],"be":[19],"heterogeneous,":[20],"and":[21,48,78,128],"larger":[23],"it":[24],"becomes,":[25],"pairwise":[27],"comparisons":[28,57,125],"number":[29,53],"grows":[30],"highly":[31],"as":[32],"well":[33],"which":[34,71,94,133],"makes":[35],"task":[37],"more":[38],"complex.":[39],"In":[40],"recent":[41],"years,":[42],"many":[43],"approaches":[44],"have":[45],"been":[46],"developed":[47],"attempted":[49],"reduce":[51],"record":[55],"pair's":[56],"in":[58,120],"while":[61],"maintaining":[62],"high":[63],"matching":[64,138],"quality.":[65,139],"There":[66],"are":[67,72,126],"two":[68],"well-known":[69],"algorithms,":[70,86],"Sorted":[74],"Neighborhood":[75],"Method":[76],"(SNM)":[77],"Blocking":[80],"algorithms.":[81],"Being":[82],"inspired":[83],"by":[84],"both":[85],"we":[87],"propose":[88],"an":[89],"Enhanced":[90],"Count":[92],"Strategy":[93],"a":[96],"new":[97],"hybrid":[98],"approach":[99],"that":[100],"creates":[101],"iterative":[102],"blocks":[103],"using":[104],"windows":[105],"with":[106,116],"dynamic":[107],"size.":[108],"It":[109],"based":[111],"on":[112],"comparing":[113],"next":[114],"element":[115],"last":[117],"duplicate":[118],"found":[119],"current":[122],"window.":[123],"Consequently,":[124],"saved,":[127],"similarity":[129],"distance":[130],"minimized,":[132],"can":[134],"lead":[135],"higher":[137]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
