{"id":"https://openalex.org/W2335232344","doi":"https://doi.org/10.1109/icdse.2014.6974602","title":"Efficient structuring of data in big data","display_name":"Efficient structuring of data in big data","publication_year":2014,"publication_date":"2014-08-01","ids":{"openalex":"https://openalex.org/W2335232344","doi":"https://doi.org/10.1109/icdse.2014.6974602","mag":"2335232344"},"language":"en","primary_location":{"id":"doi:10.1109/icdse.2014.6974602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdse.2014.6974602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science & Engineering (ICDSE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066277688","display_name":"Tarun Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I2800216316","display_name":"Oklahoma State University System","ror":"https://ror.org/045ntgf29","country_code":"US","type":"education","lineage":["https://openalex.org/I2800216316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T K Ashwin Kumar","raw_affiliation_strings":["Oklahoma State University System, Stillwater, OK, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University System, Stillwater, OK, US","institution_ids":["https://openalex.org/I2800216316"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101657252","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-0573-5853"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Department of Computer Science, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056232741","display_name":"Johnson P. Thomas","orcid":"https://orcid.org/0000-0002-4698-8072"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johnson P Thomas","raw_affiliation_strings":["Department of Computer Science, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1039,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77940503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5732","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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":0.9994000196456909,"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/unstructured-data","display_name":"Unstructured data","score":0.8755142688751221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8167375326156616},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7578728199005127},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.7145978808403015},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6669458150863647},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5204375386238098},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5185495018959045},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4473520815372467},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.4245559871196747},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4159458875656128},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40074455738067627},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3808160722255707},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3158682882785797}],"concepts":[{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.8755142688751221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167375326156616},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7578728199005127},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.7145978808403015},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6669458150863647},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5204375386238098},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5185495018959045},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4473520815372467},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.4245559871196747},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4159458875656128},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40074455738067627},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3808160722255707},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3158682882785797},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdse.2014.6974602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdse.2014.6974602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science & Engineering (ICDSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1530276735","https://openalex.org/W1742677423","https://openalex.org/W2034331023","https://openalex.org/W2085761430","https://openalex.org/W2093830031","https://openalex.org/W2121564430","https://openalex.org/W2145360759","https://openalex.org/W2148572968","https://openalex.org/W2156543375","https://openalex.org/W2251291469","https://openalex.org/W2501518699","https://openalex.org/W6637772234"],"related_works":["https://openalex.org/W2142354878","https://openalex.org/W2034595671","https://openalex.org/W2163934370","https://openalex.org/W2281126075","https://openalex.org/W2405464607","https://openalex.org/W2942479669","https://openalex.org/W4379260090","https://openalex.org/W3034384113","https://openalex.org/W4327649155","https://openalex.org/W2527777278"],"abstract_inverted_index":{"Unstructured":[0],"data":[1,29,45,53,67,74,84,107,113],"brings":[2],"enormous":[3],"challenges":[4],"to":[5,41,69,94],"Bigdata.":[6,21],"This":[7,22,38],"is":[8],"a":[9,24,36,47,89],"major":[10],"reason":[11],"why":[12],"traditional":[13],"relational":[14],"databases":[15],"cannot":[16],"meet":[17],"the":[18,43,52,79],"needs":[19],"of":[20,66,73],"becomes":[23],"concern":[25],"particularly":[26],"when":[27],"unstructured":[28,44,112],"from":[30,111],"multiple":[31],"sources":[32],"are":[33],"integrated":[34],"in":[35,46,88],"query.":[37],"paper":[39],"aims":[40],"structure":[42],"structured":[48,90,106],"form":[49],"so":[50],"that":[51,102],"can":[54,92,108],"be":[55,109],"queried":[56],"efficiently.":[57],"Our":[58,98],"research":[59],"harnesses":[60],"both":[61],"context":[62,116],"and":[63,75,85,104,117],"usage":[64,118],"patterns":[65],"items":[68],"extract":[70],"individual":[71],"pieces":[72],"determine":[76],"relationships":[77,86],"between":[78],"extracted":[80],"data.":[81],"The":[82],"transformed":[83],"placed":[87],"schema":[91],"help":[93],"ensure":[95],"good":[96],"performance.":[97],"experimental":[99],"results":[100],"identify":[101],"efficient":[103],"user-friendly":[105],"constructed":[110],"by":[114],"using":[115],"patterns.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}