{"id":"https://openalex.org/W3138303598","doi":"https://doi.org/10.1109/bigdata50022.2020.9377797","title":"Clustering-Based Predictive Analytics to Improve Scientific Data Discovery","display_name":"Clustering-Based Predictive Analytics to Improve Scientific Data Discovery","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138303598","doi":"https://doi.org/10.1109/bigdata50022.2020.9377797","mag":"3138303598"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1777750","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023450342","display_name":"Ranjeet Devarakonda","orcid":"https://orcid.org/0000-0003-2661-1937"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ranjeet Devarakonda","raw_affiliation_strings":["Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417949","display_name":"Jitendra Kumar","orcid":"https://orcid.org/0000-0002-0159-0546"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jitendra Kumar","raw_affiliation_strings":["Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036705067","display_name":"Giri Prakash","orcid":"https://orcid.org/0000-0002-2590-5848"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giri Prakash","raw_affiliation_strings":["Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Environmental Sciences Division,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023450342"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.26879133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5658","last_page":"5661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11719","display_name":"Data Quality and Management","score":0.9871000051498413,"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":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394875526428223},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7208849191665649},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6408182978630066},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5906832814216614},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.576814591884613},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.5631853342056274},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5208826065063477},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4905809462070465},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4454110562801361},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42195209860801697},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.41584813594818115},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.41182610392570496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4102873206138611},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21967029571533203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20847254991531372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15475136041641235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394875526428223},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7208849191665649},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6408182978630066},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5906832814216614},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.576814591884613},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.5631853342056274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5208826065063477},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4905809462070465},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4454110562801361},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42195209860801697},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.41584813594818115},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.41182610392570496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4102873206138611},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21967029571533203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20847254991531372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15475136041641235},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1777750","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1777750","pdf_url":"https://www.osti.gov/servlets/purl/1777750","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1777750","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1777750","pdf_url":"https://www.osti.gov/servlets/purl/1777750","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1637692498","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320337509","funder_display_name":"Biological and Environmental Research"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2042897603","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3121793570","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320337509","funder_display_name":"Biological and Environmental Research"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6129992089","display_name":null,"funder_award_id":"DE-AC05-","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6864165199","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7340972926","display_name":null,"funder_award_id":"other","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8813984943","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337509","display_name":"Biological and Environmental Research","ror":"https://ror.org/0114b2m14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3138303598.pdf","grobid_xml":"https://content.openalex.org/works/W3138303598.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1505483501","https://openalex.org/W1973965874","https://openalex.org/W1998871699","https://openalex.org/W2067084426","https://openalex.org/W2136480620","https://openalex.org/W2210543184","https://openalex.org/W2403514165","https://openalex.org/W2974334446","https://openalex.org/W3008083858","https://openalex.org/W6712952576"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W2794907032","https://openalex.org/W4255802207","https://openalex.org/W4299701476","https://openalex.org/W2904574413","https://openalex.org/W2462007151"],"abstract_inverted_index":{"Given":[0],"the":[1,9,13,53,90,93,103,119,126,138,144,167],"sheer":[2],"volume":[3],"of":[4,16,95],"scientific":[5],"data":[6,25,44,54,59,80,97,104,145,156,163],"archived":[7],"within":[8],"data-intensive":[10],"projects":[11],"at":[12,135],"US":[14],"Department":[15],"Energy's":[17],"Oak":[18],"Ridge":[19],"National":[20],"Laboratory,":[21],"finding":[22],"precisely":[23],"what":[24,64],"we":[26,37,50],"are":[27,132],"looking":[28,134],"for":[29],"may":[30,38],"not":[31],"be":[32,68],"a":[33,41,114,154],"trivial":[34],"task;":[35],"conversely,":[36],"also":[39],"miss":[40],"more":[42],"prominent":[43],"product.":[45],"To":[46],"address":[47],"such":[48,128],"issues,":[49],"propose":[51],"improving":[52],"discovery":[55],"system":[56],"and":[57,78,99,137],"using":[58],"analytics":[60],"methods":[61],"to":[62,88,143,152,164,166],"comprehend":[63],"specific":[65],"users":[66,101],"might":[67],"interested":[69],"in":[70],"based":[71,117],"on":[72,118],"their":[73,108],"physiological":[74],"state,":[75],"search":[76],"patterns,":[77],"past":[79],"usage":[81],"history.":[82],"This":[83],"work's":[84],"primary":[85],"goal":[86],"is":[87,149],"prune":[89],"complexity,":[91],"increase":[92],"visibility":[94],"popular":[96],"products,":[98],"direct":[100],"toward":[102],"that":[105],"best":[106],"meet":[107],"needs.":[109],"The":[110,147],"proposed":[111],"algorithm":[112],"constructs":[113],"user":[115],"profile":[116],"user's":[120],"explicit":[121],"or":[122],"implicit":[123],"interactions":[124],"with":[125],"system,":[127],"as":[129],"items":[130],"they":[131],"currently":[133],"on-site":[136],"key":[139],"metadata":[140],"mappings":[141],"related":[142],"set.":[146],"pattern":[148],"then":[150],"used":[151],"build":[153],"training":[155],"set,":[157],"which":[158],"will":[159],"help":[160],"find":[161],"relevant":[162],"recommend":[165],"user.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}
