{"id":"https://openalex.org/W1971309948","doi":"https://doi.org/10.1109/bigdata.2013.6691567","title":"Algebraic dataflows for big data analysis","display_name":"Algebraic dataflows for big data analysis","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1971309948","doi":"https://doi.org/10.1109/bigdata.2013.6691567","mag":"1971309948"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5022851931","display_name":"Jonas Dias","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Jonas Dias","raw_affiliation_strings":["Federal University of Rio de Janeiro - COPPE/UFRJ"],"affiliations":[{"raw_affiliation_string":"Federal University of Rio de Janeiro - COPPE/UFRJ","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027399495","display_name":"Eduardo Ogasawara","orcid":"https://orcid.org/0000-0002-0466-0626"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]},{"id":"https://openalex.org/I158509141","display_name":"Federal Center for Technological Education Celso Suckow da Fonseca","ror":"https://ror.org/03j8tnm47","country_code":"BR","type":"education","lineage":["https://openalex.org/I1293487690","https://openalex.org/I158509141","https://openalex.org/I2801200668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eduardo Ogasawara","raw_affiliation_strings":["CEFET/RJ","Federal University of Rio de Janeiro-COPPE/UFRJ"],"affiliations":[{"raw_affiliation_string":"CEFET/RJ","institution_ids":["https://openalex.org/I158509141"]},{"raw_affiliation_string":"Federal University of Rio de Janeiro-COPPE/UFRJ","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050455034","display_name":"Daniel de Oliveira","orcid":"https://orcid.org/0000-0001-9346-7651"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel de Oliveira","raw_affiliation_strings":["Flumiuense Federal University-UFF"],"affiliations":[{"raw_affiliation_string":"Flumiuense Federal University-UFF","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040979175","display_name":"F\u00e1bio Porto","orcid":"https://orcid.org/0000-0002-4597-4832"},"institutions":[{"id":"https://openalex.org/I4210142352","display_name":"Laborat\u00f3rio Nacional de Computa\u00e7\u00e3o Cient\u00edfica","ror":"https://ror.org/0498ekt05","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142352"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fabio Porto","raw_affiliation_strings":["LNCC National Laboratory for Scientific Computing, Brazil"],"affiliations":[{"raw_affiliation_string":"LNCC National Laboratory for Scientific Computing, Brazil","institution_ids":["https://openalex.org/I4210142352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041964026","display_name":"Patrick Valduriez","orcid":"https://orcid.org/0000-0001-6506-7538"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4412460525"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Valduriez","raw_affiliation_strings":["LIRMM, INRIA, France"],"affiliations":[{"raw_affiliation_string":"LIRMM, INRIA, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039896734","display_name":"Marta Mattoso","orcid":"https://orcid.org/0000-0002-0870-3371"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marta Mattoso","raw_affiliation_strings":["Federal University of Rio de Janeiro-COPPE/UFRJ"],"affiliations":[{"raw_affiliation_string":"Federal University of Rio de Janeiro-COPPE/UFRJ","institution_ids":["https://openalex.org/I122140584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022851931"],"corresponding_institution_ids":["https://openalex.org/I122140584"],"apc_list":null,"apc_paid":null,"fwci":7.7501,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96938699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":null,"first_page":"150","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9921000003814697,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9914000034332275,"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/dataflow","display_name":"Dataflow","score":0.989150881767273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8302933573722839},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7452504634857178},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7178269624710083},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.49193716049194336},{"id":"https://openalex.org/keywords/algebraic-operation","display_name":"Algebraic operation","score":0.44159939885139465},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4132336378097534},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37245726585388184},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.336497962474823},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1790032982826233},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14444169402122498},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06985822319984436}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.989150881767273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302933573722839},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7452504634857178},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7178269624710083},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.49193716049194336},{"id":"https://openalex.org/C136003732","wikidata":"https://www.wikidata.org/wiki/Q3854337","display_name":"Algebraic operation","level":3,"score":0.44159939885139465},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4132336378097534},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37245726585388184},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.336497962474823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1790032982826233},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14444169402122498},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06985822319984436},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2013.6691567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:lirmm-00857221v1","is_oa":false,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-00857221","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cci.drexel.edu/bigdata/bigdata2013/","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W135267584","https://openalex.org/W180519810","https://openalex.org/W1502629466","https://openalex.org/W1582870960","https://openalex.org/W1834532152","https://openalex.org/W1978924650","https://openalex.org/W1983704199","https://openalex.org/W1987523920","https://openalex.org/W2011105550","https://openalex.org/W2022280610","https://openalex.org/W2029084939","https://openalex.org/W2036971997","https://openalex.org/W2040842686","https://openalex.org/W2042875222","https://openalex.org/W2073308643","https://openalex.org/W2083036816","https://openalex.org/W2098935637","https://openalex.org/W2114854276","https://openalex.org/W2115570304","https://openalex.org/W2133986470","https://openalex.org/W2160967997","https://openalex.org/W2173213060","https://openalex.org/W2183478929","https://openalex.org/W6605500462","https://openalex.org/W6634741927","https://openalex.org/W6639007902"],"related_works":["https://openalex.org/W196064004","https://openalex.org/W2372854171","https://openalex.org/W3143745619","https://openalex.org/W1484338948","https://openalex.org/W4211175933","https://openalex.org/W1815267262","https://openalex.org/W2049562662","https://openalex.org/W2392216692","https://openalex.org/W2162655755","https://openalex.org/W2185957598"],"abstract_inverted_index":{"Analyzing":[0],"big":[1,75,101],"data":[2,76,102],"requires":[3],"the":[4,18,35,61,109,119,122,148],"support":[5],"of":[6,60,64,88,121,140,154],"dataflows":[7],"with":[8,124],"many":[9],"activities":[10,89],"to":[11,30,41,142,152],"extract":[12],"and":[13,85,90,118,150],"explore":[14],"relevant":[15],"information":[16],"from":[17],"data.":[19],"Recent":[20],"approaches":[21],"such":[22,32,45],"as":[23,46],"Pig":[24],"Latin":[25],"propose":[26,71],"a":[27,42,100,158],"high-level":[28],"language":[29],"model":[31],"dataflows.":[33],"However,":[34],"dataflow":[36,104,123,149],"execution":[37,87,120],"is":[38],"typically":[39],"delegated":[40],"MapRe-duce":[43],"implementation":[44],"Hadoop,":[47],"which":[48,82],"does":[49],"not":[50],"follow":[51],"an":[52,72,112,126],"algebraic":[53,80,145],"approach,":[54],"thus":[55],"it":[56],"cannot":[57],"take":[58],"advantage":[59],"optimization":[62,84],"opportunities":[63],"PigLatin":[65],"algebra.":[66,110],"In":[67],"this":[68],"paper,":[69],"we":[70,132],"approach":[73,136],"for":[74],"analysis":[77],"based":[78],"on":[79,157],"workflows,":[81],"yields":[83,137],"parallel":[86],"supports":[91,129],"user":[92,159],"steering":[93,160],"using":[94,108,115,144],"provenance":[95],"queries.":[96],"We":[97],"illustrate":[98],"how":[99],"processing":[103],"can":[105],"be":[106],"modeled":[107],"Through":[111],"experimental":[113],"evaluation":[114],"real":[116],"datasets":[117],"Chiron,":[125],"engine":[127],"that":[128,134],"our":[130,135],"algebra,":[131],"show":[133],"performance":[138],"gains":[139],"up":[141,151],"19.6%":[143],"optimizations":[146],"in":[147],"39.1%":[153],"time":[155],"saved":[156],"scenario.":[161]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
