{"id":"https://openalex.org/W2213270071","doi":"https://doi.org/10.1109/bigdata.2015.7363765","title":"Composable and efficient functional big data processing framework","display_name":"Composable and efficient functional big data processing framework","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2213270071","doi":"https://doi.org/10.1109/bigdata.2015.7363765","mag":"2213270071"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (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/A5076162396","display_name":"Dongyao Wu","orcid":"https://orcid.org/0000-0002-7092-0940"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Dongyao Wu","raw_affiliation_strings":["Data61, Eveleigh, NSW, AU"],"affiliations":[{"raw_affiliation_string":"Data61, Eveleigh, NSW, AU","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000296607","display_name":"Sherif Sakr","orcid":"https://orcid.org/0000-0002-2503-523X"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I185203018","display_name":"King Saud bin Abdulaziz University for Health Sciences","ror":"https://ror.org/0149jvn88","country_code":"SA","type":"education","lineage":["https://openalex.org/I185203018"]}],"countries":["AU","SA"],"is_corresponding":false,"raw_author_name":"Sherif Sakr","raw_affiliation_strings":["King Saud bin Abdulaziz University for Health Sciences, Saudi Arabia","Software Systems Research Group, NICTA, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"King Saud bin Abdulaziz University for Health Sciences, Saudi Arabia","institution_ids":["https://openalex.org/I185203018"]},{"raw_affiliation_string":"Software Systems Research Group, NICTA, Sydney, Australia","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064683660","display_name":"Liming Zhu","orcid":"https://orcid.org/0000-0001-5839-3765"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liming Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","Software Systems Research Group, NICTA, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Software Systems Research Group, NICTA, Sydney, Australia","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075900594","display_name":"Qinghua Lu","orcid":"https://orcid.org/0000-0002-7783-5183"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Qinghua Lu","raw_affiliation_strings":["College of Computer and Communication Engineering, University of Petroleum, Qingdao, China","Software Systems Research Group, NICTA, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"College of Computer and Communication Engineering, University of Petroleum, Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]},{"raw_affiliation_string":"Software Systems Research Group, NICTA, Sydney, Australia","institution_ids":["https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076162396"],"corresponding_institution_ids":["https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":3.1784,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93002312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":1.0,"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":1.0,"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":0.9958000183105469,"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":0.9957000017166138,"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":0.8400789499282837},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.739641010761261},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.735135555267334},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.641413152217865},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49172356724739075},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4408056139945984},{"id":"https://openalex.org/keywords/data-flow-analysis","display_name":"Data-flow analysis","score":0.43777304887771606},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41829124093055725},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.3761667013168335},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29902005195617676},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25839048624038696},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22684985399246216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400789499282837},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.739641010761261},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.735135555267334},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.641413152217865},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49172356724739075},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4408056139945984},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.43777304887771606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41829124093055725},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.3761667013168335},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29902005195617676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25839048624038696},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22684985399246216},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1978924650","https://openalex.org/W2027860831","https://openalex.org/W2097484305","https://openalex.org/W2098935637","https://openalex.org/W2119738171","https://openalex.org/W2121810937","https://openalex.org/W2131975293","https://openalex.org/W2158056686","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W6679815717","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2391715591","https://openalex.org/W1754116331","https://openalex.org/W2383362428","https://openalex.org/W59945861","https://openalex.org/W2382137162","https://openalex.org/W1551967076","https://openalex.org/W2151163382","https://openalex.org/W4256382613","https://openalex.org/W316163056","https://openalex.org/W2092972345"],"abstract_inverted_index":{"Over":[0],"the":[1,15,25,63,69,82,111,121,134,156,167],"past":[2],"years,":[3],"frameworks":[4,29],"such":[5],"as":[6,35],"MapReduce":[7],"and":[8,22,33,54,75],"Spark":[9],"have":[10],"been":[11],"introduced":[12],"to":[13,109,132,153],"ease":[14],"task":[16],"of":[17,72,113,126,136,150,155,161,170],"developing":[18],"big":[19,98],"data":[20,70,93,99,123],"programs":[21],"applications.":[23,100],"However,":[24],"jobs":[26,49],"in":[27],"these":[28],"are":[30,50,130],"roughly":[31],"defined":[32],"packaged":[34],"executable":[36],"jars":[37],"without":[38],"any":[39],"functionality":[40],"being":[41],"exposed":[42],"or":[43],"described.":[44],"This":[45],"means":[46],"that":[47,144],"deployed":[48],"not":[51],"natively":[52],"composable":[53,97],"reusable":[55],"for":[56,65,95,158],"subsequent":[57],"development.":[58],"Besides,":[59],"it":[60],"also":[61],"hampers":[62],"ability":[64],"applying":[66],"optimizations":[67,129,146],"on":[68,116,120],"flow":[71],"job":[73],"sequences":[74,163],"pipelines.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"present":[81],"Hierarchically":[83],"Distributed":[84],"Data":[85],"Matrix":[86],"(HDM)":[87],"which":[88],"is":[89,107],"a":[90,104],"functional,":[91],"strongly-typed":[92],"representation":[94],"writing":[96],"Along":[101],"with":[102,166],"HDM,":[103,127],"runtime":[105],"framework":[106],"provided":[108],"support":[110],"execution":[112],"HDM":[114,138],"applications":[115],"distributed":[117],"infrastructures.":[118],"Based":[119],"functional":[122],"dependency":[124],"graph":[125],"multiple":[128],"applied":[131],"improve":[133],"performance":[135],"executing":[137],"jobs.":[139],"The":[140],"experimental":[141],"results":[142],"show":[143],"our":[145],"can":[147],"achieve":[148],"improvements":[149],"between":[151],"10%":[152],"60%":[154],"Job-Completion-Time":[157],"different":[159],"types":[160],"operation":[162],"when":[164],"compared":[165],"current":[168],"state":[169],"art,":[171],"Apache":[172],"Spark.":[173]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}