{"id":"https://openalex.org/W1993320880","doi":"https://doi.org/10.1109/cloudcom.2012.6427480","title":"RPig: A scalable framework for machine learning and advanced statistical functionalities","display_name":"RPig: A scalable framework for machine learning and advanced statistical functionalities","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1993320880","doi":"https://doi.org/10.1109/cloudcom.2012.6427480","mag":"1993320880"},"language":"en","primary_location":{"id":"doi:10.1109/cloudcom.2012.6427480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom.2012.6427480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th IEEE International Conference on Cloud Computing Technology and Science Proceedings","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/A5115590731","display_name":"Mingxue Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150373","display_name":"Ericsson (Ireland)","ror":"https://ror.org/04swdfh12","country_code":"IE","type":"company","lineage":["https://openalex.org/I1306339040","https://openalex.org/I4210150373"]},{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["IE","SE"],"is_corresponding":true,"raw_author_name":"MingXue Wang","raw_affiliation_strings":["Network Management Lab, Ericsson Ireland","Network Management Lab, Ericsson Ireland#TAB#"],"affiliations":[{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland","institution_ids":["https://openalex.org/I4210150373"]},{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland#TAB#","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043619137","display_name":"Sidath Handurukande","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150373","display_name":"Ericsson (Ireland)","ror":"https://ror.org/04swdfh12","country_code":"IE","type":"company","lineage":["https://openalex.org/I1306339040","https://openalex.org/I4210150373"]},{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["IE","SE"],"is_corresponding":false,"raw_author_name":"Sidath B. Handurukande","raw_affiliation_strings":["Network Management Lab, Ericsson Ireland","Network Management Lab, Ericsson Ireland#TAB#"],"affiliations":[{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland","institution_ids":["https://openalex.org/I4210150373"]},{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland#TAB#","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043344581","display_name":"Mohamed Nassar","orcid":"https://orcid.org/0000-0001-8857-4436"},"institutions":[{"id":"https://openalex.org/I4210150373","display_name":"Ericsson (Ireland)","ror":"https://ror.org/04swdfh12","country_code":"IE","type":"company","lineage":["https://openalex.org/I1306339040","https://openalex.org/I4210150373"]},{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["IE","SE"],"is_corresponding":false,"raw_author_name":"Mohamed Nassar","raw_affiliation_strings":["Network Management Lab, Ericsson Ireland","Network Management Lab, Ericsson Ireland#TAB#"],"affiliations":[{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland","institution_ids":["https://openalex.org/I4210150373"]},{"raw_affiliation_string":"Network Management Lab, Ericsson Ireland#TAB#","institution_ids":["https://openalex.org/I1306339040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115590731"],"corresponding_institution_ids":["https://openalex.org/I1306339040","https://openalex.org/I4210150373"],"apc_list":null,"apc_paid":null,"fwci":2.2268,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90198233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9925000071525574,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9743000268936157,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8649568557739258},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7414265275001526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5914888978004456},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5444594025611877},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5043491125106812},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.49009740352630615},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48939481377601624},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4635334312915802},{"id":"https://openalex.org/keywords/eclipse","display_name":"Eclipse","score":0.4520646035671234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45169565081596375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27833282947540283},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2771255373954773},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21547406911849976},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16306009888648987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8649568557739258},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7414265275001526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5914888978004456},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5444594025611877},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5043491125106812},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.49009740352630615},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48939481377601624},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4635334312915802},{"id":"https://openalex.org/C2778505590","wikidata":"https://www.wikidata.org/wiki/Q141022","display_name":"Eclipse","level":2,"score":0.4520646035671234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45169565081596375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27833282947540283},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2771255373954773},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21547406911849976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16306009888648987},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cloudcom.2012.6427480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom.2012.6427480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th IEEE International Conference on Cloud Computing Technology and Science Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.newhaven.edu:electricalcomputerengineering-facpubs-1118","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/6427480","pdf_url":null,"source":{"id":"https://openalex.org/S4377196522","display_name":"Digital Commons - New Heaven (University of New Haven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40253897","host_organization_name":"University of New Haven","host_organization_lineage":["https://openalex.org/I40253897"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical & Computer Engineering and Computer Science Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1591482979","https://openalex.org/W1595364929","https://openalex.org/W2013373704","https://openalex.org/W2078382802","https://openalex.org/W2098935637","https://openalex.org/W2102458936","https://openalex.org/W2117990954","https://openalex.org/W2132641846","https://openalex.org/W2173213060","https://openalex.org/W2995564009","https://openalex.org/W6677732001"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W137217271","https://openalex.org/W1567818861","https://openalex.org/W91167106","https://openalex.org/W2987774938","https://openalex.org/W4390608645","https://openalex.org/W4256492088"],"abstract_inverted_index":{"In":[0,130],"many":[1],"domains":[2],"such":[3,39,58,101,115],"as":[4,40,59,102],"Telecom":[5,206],"various":[6],"scenarios":[7,203],"necessitate":[8],"the":[9,30,48,73,94,141,190,198,205,210,216,221,227,233],"processing":[10,37,155],"of":[11,14,50,63,143,157,212,229,235],"large":[12],"amounts":[13],"data":[15,31,154,166],"using":[16],"statistical":[17,55,98,106,149,173],"and":[18,42,54,87,124,148,152,172,193,214,232],"machine":[19,52,66,146,170],"learning":[20,53,67,147,171],"algorithms.":[21],"A":[22],"noticeable":[23],"effort":[24],"has":[25],"been":[26],"made":[27],"to":[28,91],"move":[29],"management":[32],"systems":[33,46],"into":[34],"MapReduce":[35],"parallel":[36,153],"environments":[38],"Hadoop":[41,64],"Pig.":[43,158],"Nevertheless":[44],"these":[45],"lack":[47],"features":[49],"advanced":[51,109,165],"analysis.":[56,174],"Frame-works":[57],"Mahout":[60,78],"on":[61,120],"top":[62],"support":[65],"but":[68],"their":[69],"implementations":[70],"are":[71,111],"at":[72],"preliminary":[74],"stage.":[75],"For":[76],"example":[77],"does":[79],"not":[80,128],"provide":[81],"Support":[82],"Vector":[83],"Machine":[84],"(SVM)":[85],"algorithms":[86,107],"it":[88,126],"is":[89,127],"difficult":[90],"use.":[92],"On":[93],"other":[95],"hand":[96],"traditional":[97],"software":[99,116],"tools":[100],"R":[103,144],"containing":[104],"comprehensive":[105],"for":[108,169,197,237],"analysis":[110,150,167,238],"widely":[112],"used.":[113],"But":[114],"can":[117,177,218],"only":[118],"run":[119],"a":[121,163],"single":[122],"computer":[123],"therefore":[125],"scalable.":[129],"this":[131],"paper":[132],"we":[133,208],"propose":[134],"an":[135,194],"integrated":[136],"solution":[137,168],"RPig":[138,160,182,199,213],"which":[139],"takes":[140],"advantages":[142],"(for":[145],"capabilities)":[151],"capabilities":[156],"The":[159,224],"framework":[161,217,231],"offers":[162],"scalable":[164],"Analysis":[175],"jobs":[176],"be":[178],"easily":[179],"developed":[180],"with":[181],"script":[183],"in":[184],"high":[185],"level":[186],"languages.":[187],"We":[188],"describe":[189],"design":[191],"implementation":[192],"eclipse-based":[195],"RPigEditor":[196],"framework.":[200],"Using":[201],"application":[202],"from":[204],"domain":[207],"show":[209],"usage":[211],"how":[215],"significantly":[219],"reduce":[220],"development":[222],"effort.":[223],"results":[225],"demonstrate":[226],"scalability":[228],"our":[230],"simplicity":[234],"deployment":[236],"jobs.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}