{"id":"https://openalex.org/W2920128502","doi":"https://doi.org/10.1145/3297156.3297249","title":"Methodology of Big Data Integration from A Priori Unknown Heterogeneous Data Sources","display_name":"Methodology of Big Data Integration from A Priori Unknown Heterogeneous Data Sources","publication_year":2018,"publication_date":"2018-12-08","ids":{"openalex":"https://openalex.org/W2920128502","doi":"https://doi.org/10.1145/3297156.3297249","mag":"2920128502"},"language":"en","primary_location":{"id":"doi:10.1145/3297156.3297249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297249","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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/A5005801896","display_name":"Alexey Samoylov","orcid":"https://orcid.org/0000-0001-8107-1617"},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexey Samoylov","raw_affiliation_strings":["Southern Federal University, Taganrog, Russia"],"affiliations":[{"raw_affiliation_string":"Southern Federal University, Taganrog, Russia","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053119750","display_name":"Nikolay Sergeev","orcid":null},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nikolay Sergeev","raw_affiliation_strings":["Southern Federal University, Taganrog, Russia"],"affiliations":[{"raw_affiliation_string":"Southern Federal University, Taganrog, Russia","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023564918","display_name":"Margarita Kucherova","orcid":null},"institutions":[{"id":"https://openalex.org/I137534880","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92","country_code":"RU","type":"education","lineage":["https://openalex.org/I137534880"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Margarita Kucherova","raw_affiliation_strings":["Southern Federal University, Taganrog, Russia"],"affiliations":[{"raw_affiliation_string":"Southern Federal University, Taganrog, Russia","institution_ids":["https://openalex.org/I137534880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109356532","display_name":"Boris Denisov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Denisov","raw_affiliation_strings":["Green Oasis School, Tianmian, Futian District, Shenzhen, Guangdong, The People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Green Oasis School, Tianmian, Futian District, Shenzhen, Guangdong, The People's Republic of China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005801896"],"corresponding_institution_ids":["https://openalex.org/I137534880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28698752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"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":0.9966999888420105,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944000244140625,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.7790849208831787},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7327494621276855},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6997693777084351},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.633298397064209},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.614391028881073},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5906159281730652},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.5829219222068787},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5693833827972412},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5583008527755737},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.5452235341072083},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5267944931983948},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.516760528087616},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.474132776260376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4444335997104645},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.4307381808757782},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41565608978271484},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38093751668930054},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19098559021949768},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.16769039630889893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0888204276561737},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08776068687438965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790849208831787},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7327494621276855},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6997693777084351},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.633298397064209},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.614391028881073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5906159281730652},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.5829219222068787},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5693833827972412},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5583008527755737},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.5452235341072083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5267944931983948},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.516760528087616},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.474132776260376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4444335997104645},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.4307381808757782},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41565608978271484},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38093751668930054},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19098559021949768},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.16769039630889893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0888204276561737},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08776068687438965},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297156.3297249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297249","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329065","display_name":"Southern Federal University","ror":"https://ror.org/01tv9ph92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1893018","https://openalex.org/W184387631","https://openalex.org/W821644386","https://openalex.org/W1453506303","https://openalex.org/W1508333423","https://openalex.org/W1533278430","https://openalex.org/W1534626598","https://openalex.org/W2003041138","https://openalex.org/W2004505745","https://openalex.org/W2090403712","https://openalex.org/W2124684568","https://openalex.org/W2166006219","https://openalex.org/W2170571644","https://openalex.org/W2252784340","https://openalex.org/W2258887958","https://openalex.org/W2268301633","https://openalex.org/W2294693675","https://openalex.org/W2401543523","https://openalex.org/W2405571848","https://openalex.org/W2413971534","https://openalex.org/W2465777981","https://openalex.org/W2508591424","https://openalex.org/W2521059179","https://openalex.org/W2571879191","https://openalex.org/W4240673911"],"related_works":["https://openalex.org/W3110550032","https://openalex.org/W4216703","https://openalex.org/W2949279097","https://openalex.org/W2020045149","https://openalex.org/W167181451","https://openalex.org/W2479844588","https://openalex.org/W4385163218","https://openalex.org/W4295062697","https://openalex.org/W2920128502","https://openalex.org/W2368593332"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,14,44,48,73,78,87,102],"data":[3,15,19,45,61,95,118,124],"preparation":[4,113],"for":[5,34,93,110],"Big":[6,111],"Data":[7,112],"analytics":[8],"directly":[9],"depends":[10],"on":[11],"the":[12,39,42,53,94,100,104],"quality":[13],"integration":[16],"from":[17,119],"heterogeneous":[18,123],"sources.":[20,125],"Extract,":[21],"Transform":[22],"and":[23,51,71,90],"Load":[24],"(ETL)":[25],"systems":[26],"have":[27],"proved":[28],"to":[29,38,81,115],"be":[30],"an":[31],"efficient":[32],"solution":[33],"this":[35],"task.":[36],"But":[37],"moment,":[40],"in":[41,64],"stages":[43],"selection,":[46],"definition":[47],"extraction":[49],"rules":[50,79],"transformation,":[52],"decision":[54],"is":[55],"usually":[56],"made":[57],"exclusively":[58],"by":[59,106],"a":[60,84,120],"specialist.":[62],"This,":[63],"turn,":[65],"causes":[66],"such":[67],"problems":[68],"as":[69],"redundancy":[70],"inconsistency":[72],"imported":[74],"data,":[75],"narrow":[76],"specialization":[77],"(up":[80],"uniqueness)":[82],"with":[83],"limited":[85],"number":[86],"analytical":[88],"models":[89],"known":[91],"requirements":[92],"mart.":[96],"This":[97],"paper":[98],"presents":[99],"concept":[101],"solving":[103],"problem":[105],"providing":[107],"methodological":[108],"support":[109],"procedure":[114],"efficiently":[116],"collect":[117],"priory":[121],"unknown":[122]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}