{"id":"https://openalex.org/W2126943629","doi":"https://doi.org/10.1142/s0218213099000117","title":"PREPROCESSING AND INTEGRATION OF DATA FROM MULTIPLE SOURCES FOR KNOWLEDGE DISCOVERY","display_name":"PREPROCESSING AND INTEGRATION OF DATA FROM MULTIPLE SOURCES FOR KNOWLEDGE DISCOVERY","publication_year":1999,"publication_date":"1999-06-01","ids":{"openalex":"https://openalex.org/W2126943629","doi":"https://doi.org/10.1142/s0218213099000117","mag":"2126943629"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213099000117","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213099000117","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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/A5111904556","display_name":"Marion G. Ceruti","orcid":null},"institutions":[{"id":"https://openalex.org/I1339224429","display_name":"Naval Information Warfare Center Pacific","ror":"https://ror.org/01gs1cg95","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330347796","https://openalex.org/I1339224429","https://openalex.org/I2802223155","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MARION G. CERUTI","raw_affiliation_strings":["Space and Naval Warfare Systems Center - San Diego, Code D4121, 53560 Hull St., San Diego, CA, 92152-5001, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space and Naval Warfare Systems Center - San Diego, Code D4121, 53560 Hull St., San Diego, CA, 92152-5001, USA","institution_ids":["https://openalex.org/I1339224429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109130385","display_name":"Magdi N. Kamel","orcid":null},"institutions":[{"id":"https://openalex.org/I35364215","display_name":"Naval Postgraduate School","ror":"https://ror.org/033yfkj90","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I35364215"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MAGDI N. KAMEL","raw_affiliation_strings":["Department of Systems Management, Naval Postgraduate School, 555 Dyer Rd., Monterey, CA, 93943, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Management, Naval Postgraduate School, 555 Dyer Rd., Monterey, CA, 93943, USA","institution_ids":["https://openalex.org/I35364215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0414,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82874479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"08","issue":"02","first_page":"157","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8805522918701172},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6952449083328247},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6184654235839844},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6152072548866272},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5702102780342102},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5693801641464233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5464916229248047},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5271425247192383},{"id":"https://openalex.org/keywords/knowledge-integration","display_name":"Knowledge integration","score":0.4602782428264618},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43311020731925964},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4191637635231018},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33367347717285156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30019015073776245},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.2737324833869934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805522918701172},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6952449083328247},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6184654235839844},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6152072548866272},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5702102780342102},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5693801641464233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5464916229248047},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5271425247192383},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.4602782428264618},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43311020731925964},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4191637635231018},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33367347717285156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30019015073776245},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2737324833869934},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213099000117","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213099000117","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W85444739","https://openalex.org/W130652938","https://openalex.org/W1859296291","https://openalex.org/W1963607545","https://openalex.org/W2002187527","https://openalex.org/W2016758618","https://openalex.org/W2046005538","https://openalex.org/W2056855682","https://openalex.org/W2072300809","https://openalex.org/W2075043418","https://openalex.org/W2140037779"],"related_works":["https://openalex.org/W102552829","https://openalex.org/W3119469335","https://openalex.org/W2947585550","https://openalex.org/W2612285664","https://openalex.org/W962149676","https://openalex.org/W62488488","https://openalex.org/W1569044753","https://openalex.org/W811092902","https://openalex.org/W2187154034","https://openalex.org/W1995497218"],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"in":[3,26],"the":[4,78,84,107,121],"generation":[5,18],"and":[6,21,31,63,70,72,75,89,129],"collection":[7],"of":[8,19,77,86,109,136],"data":[9,29,57,65,87,110],"has":[10],"generated":[11],"an":[12,39],"urgent":[13],"need":[14],"for":[15,91,99,127],"a":[16,52,96,124],"new":[17],"techniques":[20],"tools":[22],"that":[23,43,55,103],"can":[24],"assist":[25],"transforming":[27],"these":[28],"intelligently":[30],"automatically":[32],"into":[33],"useful":[34],"knowledge.":[35,80],"Knowledge":[36,49],"discovery":[37,50,93],"is":[38,51],"emerging":[40],"multidisciplinary":[41],"field":[42],"attempts":[44],"to":[45],"fulfill":[46],"this":[47],"need.":[48],"large":[53],"process":[54],"includes":[56],"selection,":[58,68],"cleaning,":[59],"preprocessing,":[60],"integration,":[61],"transformation":[62],"reduction,":[64],"mining,":[66],"model":[67],"evaluation":[69],"interpretation,":[71],"finally":[73],"consolidation":[74],"use":[76],"extracted":[79],"This":[81],"paper":[82,122],"addresses":[83],"issues":[85],"cleaning":[88],"integration":[90,108],"knowledge":[92],"by":[94],"proposing":[95],"systematic":[97],"approach":[98],"resolving":[100,130],"semantic":[101,131],"conflicts":[102,132],"are":[104],"encountered":[105],"during":[106],"from":[111,118],"multiple":[112],"sources.":[113],"Illustrated":[114],"with":[115],"examples":[116],"derived":[117],"military":[119],"databases,":[120],"presents":[123],"heuristics-based":[125],"algorithm":[126],"identifying":[128],"at":[133],"different":[134],"levels":[135],"information":[137],"granularity.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
