{"id":"https://openalex.org/W4206203855","doi":"https://doi.org/10.1109/icsai53574.2021.9664187","title":"Automatic Feature Weighting and Selection for Similar Duplicate Record Detection Based on Ant Colony Optimization","display_name":"Automatic Feature Weighting and Selection for Similar Duplicate Record Detection Based on Ant Colony Optimization","publication_year":2021,"publication_date":"2021-11-13","ids":{"openalex":"https://openalex.org/W4206203855","doi":"https://doi.org/10.1109/icsai53574.2021.9664187"},"language":"en","primary_location":{"id":"doi:10.1109/icsai53574.2021.9664187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai53574.2021.9664187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Systems and Informatics (ICSAI)","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/A5103035568","display_name":"Jianjun Cao","orcid":"https://orcid.org/0000-0002-4281-8324"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Cao","raw_affiliation_strings":["The 63rd Research Institute, National University of Defense Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 63rd Research Institute, National University of Defense Technology, Nanjing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560065","display_name":"Yuxin Xu","orcid":"https://orcid.org/0000-0003-1995-8334"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Xu","raw_affiliation_strings":["School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035305012","display_name":"Zhixian Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixian Zeng","raw_affiliation_strings":["The 63rd Research Institute, National University of Defense Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 63rd Research Institute, National University of Defense Technology, Nanjing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010940938","display_name":"Chumei Gu","orcid":"https://orcid.org/0000-0003-3854-2772"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chumei Gu","raw_affiliation_strings":["School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037267015","display_name":"Mengda Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengda Wang","raw_affiliation_strings":["School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3088,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57488117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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/T11719","display_name":"Data Quality and Management","score":0.9937999844551086,"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":0.9922000169754028,"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/sliding-window-protocol","display_name":"Sliding window protocol","score":0.8133580088615417},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7398107051849365},{"id":"https://openalex.org/keywords/ant-colony-optimization-algorithms","display_name":"Ant colony optimization algorithms","score":0.7090157270431519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6150372624397278},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4921538233757019},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4902656376361847},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.47538769245147705},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47044625878334045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4676349461078644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4662550687789917},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4542158842086792},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38410866260528564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3719019889831543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36584532260894775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3547779321670532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19784221053123474},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10325980186462402}],"concepts":[{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.8133580088615417},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7398107051849365},{"id":"https://openalex.org/C40128228","wikidata":"https://www.wikidata.org/wiki/Q460851","display_name":"Ant colony optimization algorithms","level":2,"score":0.7090157270431519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6150372624397278},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4921538233757019},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4902656376361847},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.47538769245147705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47044625878334045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4676349461078644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4662550687789917},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4542158842086792},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38410866260528564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3719019889831543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36584532260894775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3547779321670532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19784221053123474},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10325980186462402},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsai53574.2021.9664187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai53574.2021.9664187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4625568477","display_name":null,"funder_award_id":"61371196","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W1647671624","https://openalex.org/W1991232287","https://openalex.org/W1995849952","https://openalex.org/W2041183606","https://openalex.org/W2125552507","https://openalex.org/W2130028860","https://openalex.org/W2143381319","https://openalex.org/W2362883194","https://openalex.org/W2379248298","https://openalex.org/W2585538791","https://openalex.org/W2758358862","https://openalex.org/W2788402714","https://openalex.org/W2884749649","https://openalex.org/W2891186800","https://openalex.org/W6636915900","https://openalex.org/W6679228677","https://openalex.org/W6733119734"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1612029326","https://openalex.org/W2125776999","https://openalex.org/W3014558862"],"abstract_inverted_index":{"To":[0],"solve":[1],"the":[2,61,65,76,82,91,108,111,115,121,124,130,133,143,149,154,159,162,170],"problem":[3],"of":[4,68,94,123,174],"attributes":[5],"similarity":[6,9],"weighting":[7,24,34],"and":[8,27,35,71,74,101,129,136],"selecting":[10,36],"towards":[11],"records":[12],"for":[13,32,64,85,110,126,132],"similar":[14,178],"duplicate":[15,179],"record":[16,180],"detection":[17,72],"in":[18,177],"structured":[19],"data":[20],"sources,":[21],"a":[22,28,44,52],"feature":[23,33],"mathematical":[25],"model":[26,31],"multi-object":[29],"optimization":[30],"are":[37,41,139],"built.":[38],"The":[39],"models":[40],"solved":[42],"by":[43,97],"continuous":[45,163],"domain":[46,164],"ant":[47,86,103,165],"colony":[48,87,104,166],"algorithm":[49,105,167],"based":[50,168],"on":[51,169],"sliding":[53,138,145,175],"window":[54,63,125,127,137,144,176],"grid":[55,98,171],"partitioning":[56,172],"strategy.":[57],"First":[58],"separately":[59],"set":[60],"search":[62,83,109,131],"two":[66,77],"variables":[67,96],"attribute":[69],"rank":[70],"threshold,":[73],"combine":[75],"variable":[78],"windows":[79],"to":[80,106,156],"form":[81],"space":[84],"optimization.":[88],"Then":[89],"balance":[90],"heuristic":[92],"information":[93],"different":[95],"width":[99],"ratio,":[100],"use":[102],"perform":[107],"optimal":[112,116,134,150],"solution.":[113,151],"Finally,":[114],"solution":[117,135],"is":[118],"used":[119],"as":[120],"center":[122],"sliding,":[128],"performed":[140],"again":[141],"until":[142],"does":[146],"not":[147],"change":[148],"By":[152],"applying":[153],"method":[155],"engineering":[157],"practice,":[158],"verified":[160],"that":[161],"strategy":[173],"detection.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
