{"id":"https://openalex.org/W2020777528","doi":"https://doi.org/10.1109/hpec.2014.7040994","title":"Characterization of semi-synthetic dataset for big-data semantic analysis","display_name":"Characterization of semi-synthetic dataset for big-data semantic analysis","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2020777528","doi":"https://doi.org/10.1109/hpec.2014.7040994","mag":"2020777528"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2014.7040994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5006030786","display_name":"Robert W. Techentin","orcid":null},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert Techentin","raw_affiliation_strings":["'Mayo Clinic College of Medicine, Rochester, MN","Mayo Clinic College of Medicine  Rochester, MN USA"],"affiliations":[{"raw_affiliation_string":"'Mayo Clinic College of Medicine, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Mayo Clinic College of Medicine  Rochester, MN USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032566975","display_name":"Daniel Foti","orcid":"https://orcid.org/0000-0003-4323-9858"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Foti","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN","University of Minnesota, Minneapolis, , USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":"University of Minnesota, Minneapolis, , USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048463103","display_name":"Sinan al-Saffar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119657","display_name":"Semantic Designs (United States)","ror":"https://ror.org/025rxfw41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210119657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sinan Al-Saffar","raw_affiliation_strings":["Semantic Scale, Tampa, FL","Semantic Scale, Tampa FL, USA"],"affiliations":[{"raw_affiliation_string":"Semantic Scale, Tampa, FL","institution_ids":["https://openalex.org/I4210119657"]},{"raw_affiliation_string":"Semantic Scale, Tampa FL, USA","institution_ids":["https://openalex.org/I4210119657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064435741","display_name":"Peter Li","orcid":"https://orcid.org/0000-0001-9602-9550"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Li","raw_affiliation_strings":["'Mayo Clinic College of Medicine, Rochester, MN","Mayo Clinic College of Medicine  Rochester, MN USA"],"affiliations":[{"raw_affiliation_string":"'Mayo Clinic College of Medicine, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Mayo Clinic College of Medicine  Rochester, MN USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036017826","display_name":"Erik Daniel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]},{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Daniel","raw_affiliation_strings":["'Mayo Clinic College of Medicine, Rochester, MN","Mayo Clinic College of Medicine  Rochester, MN USA"],"affiliations":[{"raw_affiliation_string":"'Mayo Clinic College of Medicine, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Mayo Clinic College of Medicine  Rochester, MN USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005717479","display_name":"Barry K. Gilbert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]},{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry Gilbert","raw_affiliation_strings":["'Mayo Clinic College of Medicine, Rochester, MN","Mayo Clinic College of Medicine  Rochester, MN USA"],"affiliations":[{"raw_affiliation_string":"'Mayo Clinic College of Medicine, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Mayo Clinic College of Medicine  Rochester, MN USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038001468","display_name":"David Holmes","orcid":"https://orcid.org/0000-0002-4560-3572"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Holmes","raw_affiliation_strings":["'Mayo Clinic College of Medicine, Rochester, MN","Mayo Clinic College of Medicine  Rochester, MN USA"],"affiliations":[{"raw_affiliation_string":"'Mayo Clinic College of Medicine, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Mayo Clinic College of Medicine  Rochester, MN USA","institution_ids":["https://openalex.org/I1330342723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006030786"],"corresponding_institution_ids":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11556576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9984999895095825,"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":0.9973000288009644,"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":0.8260256052017212},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.5448919534683228},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5391090512275696},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5334014892578125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4902368187904358},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4637506604194641},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.44670119881629944},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.42339447140693665},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.4101486802101135},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3459823727607727},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33095794916152954},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.23732882738113403},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12852922081947327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260256052017212},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.5448919534683228},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5391090512275696},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5334014892578125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4902368187904358},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4637506604194641},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.44670119881629944},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.42339447140693665},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.4101486802101135},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3459823727607727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33095794916152954},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.23732882738113403},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12852922081947327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2014.7040994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4699999988079071,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W99648884","https://openalex.org/W1598377208","https://openalex.org/W1843386722","https://openalex.org/W1988411508","https://openalex.org/W1989009626","https://openalex.org/W1991023629","https://openalex.org/W2019543926","https://openalex.org/W2026427349","https://openalex.org/W2061253631","https://openalex.org/W2118094100","https://openalex.org/W2120356313","https://openalex.org/W2140004302","https://openalex.org/W2147522025","https://openalex.org/W2157443293","https://openalex.org/W2159938093","https://openalex.org/W2161062388","https://openalex.org/W4239696231","https://openalex.org/W4240236473","https://openalex.org/W6604041034"],"related_works":["https://openalex.org/W4281562483","https://openalex.org/W2800353001","https://openalex.org/W4391060474","https://openalex.org/W2382028126","https://openalex.org/W2280628760","https://openalex.org/W2786144403","https://openalex.org/W2364472053","https://openalex.org/W1990650227","https://openalex.org/W4200411507","https://openalex.org/W2779831736"],"abstract_inverted_index":{"Over":[0],"the":[1,4,12,72,80,101,116,147],"past":[2],"decade,":[3],"use":[5],"of":[6,43,47,68,75,115],"semantic":[7,32,83,127],"databases":[8,78],"has":[9],"served":[10],"as":[11,79,100,122],"basis":[13,81,102],"for":[14,39,82,103,125,155],"storing":[15],"and":[16,20,52,93,130,137,151],"analyzing":[17],"complex,":[18],"heterogeneous,":[19],"irregular":[21],"data.":[22,44],"While":[23],"there":[24],"are":[25,153],"similarities":[26],"with":[27],"traditional":[28],"relational":[29,77],"database":[30],"systems,":[31],"data":[33,84,97,139,148],"stores":[34],"provide":[35],"a":[36,60,123],"rich":[37,64],"platform":[38],"conducting":[40],"non-traditional":[41],"analyses":[42,129],"In":[45,86],"support":[46],"new":[48,126],"graph":[49,54,128],"analytic":[50,55],"algorithms":[51],"specialized":[53],"hardware,":[56],"we":[57],"have":[58],"developed":[59],"large":[61,110],"semi-synthetic,":[62],"semantically":[63],"dataset.":[65],"The":[66,113,134],"construction":[67,135],"this":[69],"dataset":[70,118],"mimics":[71],"real-world":[73,90],"scenario":[74],"using":[76],"construction.":[85],"order":[87],"to":[88,107,120,146],"achieve":[89],"variable":[91,94],"distributions":[92],"dependencies,":[95],"data.gov":[96],"was":[98],"used":[99],"developing":[104],"an":[105],"approach":[106],"build":[108],"arbitrarily":[109],"semi-synthetic":[111,117],"datasets.":[112],"intent":[114],"is":[119,141],"serve":[121],"testbed":[124],"computational":[131],"software/hardware":[132],"platforms.":[133],"process":[136],"basic":[138],"characterization":[140],"described.":[142],"All":[143],"code":[144],"related":[145],"collection,":[149],"consolidation,":[150],"augmentation":[152],"available":[154],"distribution.":[156]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
