{"id":"https://openalex.org/W2547742189","doi":"https://doi.org/10.14778/3007263.3007315","title":"Large-scale complex analytics on semi-structured datasets using asterixDB and spark","display_name":"Large-scale complex analytics on semi-structured datasets using asterixDB and spark","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2547742189","doi":"https://doi.org/10.14778/3007263.3007315","mag":"2547742189"},"language":"en","primary_location":{"id":"doi:10.14778/3007263.3007315","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3007263.3007315","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5017222256","display_name":"Wail Y. Alkowaileet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wail Y. Alkowaileet","raw_affiliation_strings":["Center for Complex Engineering Systems at KACST and MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Engineering Systems at KACST and MIT","institution_ids":["https://openalex.org/I4210116219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036044228","display_name":"Sattam Alsubaiee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sattam Alsubaiee","raw_affiliation_strings":["Center for Complex Engineering Systems at KACST and MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Engineering Systems at KACST and MIT","institution_ids":["https://openalex.org/I4210116219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011512061","display_name":"Michael J. Carey","orcid":"https://orcid.org/0000-0003-1561-4059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael J. Carey","raw_affiliation_strings":["University of California and Couchbase"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California and Couchbase","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064813143","display_name":"Till Westmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141151","display_name":"Teulades i Fa\u00e7anes Multifuncionals (Spain)","ror":"https://ror.org/03jtwqj24","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210141151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Till Westmann","raw_affiliation_strings":["Couchbase"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Couchbase","institution_ids":["https://openalex.org/I4210141151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102099238","display_name":"Yingyi Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141151","display_name":"Teulades i Fa\u00e7anes Multifuncionals (Spain)","ror":"https://ror.org/03jtwqj24","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210141151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Yingyi Bu","raw_affiliation_strings":["Couchbase"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Couchbase","institution_ids":["https://openalex.org/I4210141151"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2504,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8124547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":"13","first_page":"1585","last_page":"1588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7549268007278442},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7379381060600281},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7099816799163818},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.709011435508728},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6805703639984131},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5801406502723694},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5318781137466431},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.47627729177474976},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4720008373260498},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.46487051248550415},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39262858033180237},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31332600116729736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2199825644493103},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19326791167259216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549268007278442},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7379381060600281},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7099816799163818},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.709011435508728},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6805703639984131},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5801406502723694},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5318781137466431},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.47627729177474976},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4720008373260498},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.46487051248550415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39262858033180237},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31332600116729736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2199825644493103},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19326791167259216},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3007263.3007315","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3007263.3007315","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"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":8,"referenced_works":["https://openalex.org/W2013344760","https://openalex.org/W2083541728","https://openalex.org/W2131975293","https://openalex.org/W2189465200","https://openalex.org/W2210479044","https://openalex.org/W2265297126","https://openalex.org/W2283604078","https://openalex.org/W4301373165"],"related_works":["https://openalex.org/W3191926225","https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W2980555063","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W4382315681","https://openalex.org/W2794907032","https://openalex.org/W4255802207"],"abstract_inverted_index":{"Large":[0],"quantities":[1],"of":[2,38,65,79,115,133,139,168],"raw":[3],"data":[4,32,106,111,122,135,146],"are":[5],"being":[6],"generated":[7],"by":[8,164],"many":[9],"different":[10,13],"sources":[11],"in":[12,68,158],"formats.":[14],"Private":[15],"and":[16,24,46,54,70,90,102,121,131,136,141,172],"public":[17],"sectors":[18],"alike":[19],"acclaim":[20],"the":[21,36,77,153,166],"valuable":[22],"information":[23],"insights":[25,163],"that":[26,83],"can":[27,148],"be":[28,150],"mined":[29],"from":[30,108],"such":[31,41,98],"to":[33,94,124,160],"better":[34],"understand":[35],"dynamics":[37],"everyday":[39],"life,":[40],"as":[42,99],"traffic,":[43],"worldwide":[44],"logistics,":[45],"social":[47],"behavior.":[48],"For":[49],"this":[50,73],"reason,":[51],"storing,":[52],"managing,":[53],"analyzing":[55],"\"Big":[56],"Data\"":[57],"at":[58],"scale":[59],"is":[60],"getting":[61],"a":[62,80],"tremendous":[63],"amount":[64],"attention,":[66],"both":[67],"academia":[69],"industry.":[71],"In":[72],"paper,":[74],"we":[75,84],"demonstrate":[76],"power":[78,167],"parallel":[81],"connection":[82],"have":[85],"built":[86],"between":[87],"Apache":[88,91],"Spark":[89],"AsterixDB":[92,126,155],"(Incubating)":[93],"enable":[95],"complex":[96],"analytics":[97,147],"machine":[100,170],"learning":[101,171],"graph":[103,173],"analysis":[104],"on":[105,152],"drawn":[107],"large":[109],"semi-structured":[110,134],"collections.":[112],"The":[113],"integration":[114],"these":[116],"two":[117],"systems":[118],"allows":[119],"researchers":[120],"scientists":[123],"leverage":[125],"capabilities,":[127],"including":[128],"fast":[129],"ingestion":[130],"indexing":[132],"efficient":[137],"answering":[138],"geo-spatial":[140],"fuzzy":[142],"text":[143],"queries.":[144],"Complex":[145],"then":[149],"performed":[151],"resulting":[154],"query":[156],"output":[157],"order":[159],"obtain":[161],"additional":[162],"leveraging":[165],"Spark's":[169],"libraries.":[174]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}