{"id":"https://openalex.org/W2731426225","doi":"https://doi.org/10.1504/ijbdi.2017.10006111","title":"Improving execution speed of incremental runs of MapReduce using provenance","display_name":"Improving execution speed of incremental runs of MapReduce using provenance","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2731426225","doi":"https://doi.org/10.1504/ijbdi.2017.10006111","mag":"2731426225"},"language":"en","primary_location":{"id":"doi:10.1504/ijbdi.2017.10006111","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbdi.2017.10006111","pdf_url":null,"source":{"id":"https://openalex.org/S4210219838","display_name":"International Journal of Big Data Intelligence","issn_l":"2053-1389","issn":["2053-1389","2053-1397"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Big Data Intelligence","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/A5100754541","display_name":"Anish Gupta","orcid":"https://orcid.org/0000-0002-6121-9706"},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anish Gupta","raw_affiliation_strings":["Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India","institution_ids":["https://openalex.org/I114845381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103637844","display_name":"S. Madhu","orcid":null},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Madhu","raw_affiliation_strings":["Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India","institution_ids":["https://openalex.org/I114845381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037556887","display_name":"S. D. Madhu Kumar","orcid":"https://orcid.org/0000-0002-5276-8842"},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.D. Madhu Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India","institution_ids":["https://openalex.org/I114845381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059861184","display_name":"Anu Mary Chacko","orcid":"https://orcid.org/0000-0001-7830-8679"},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anu Mary Chacko","raw_affiliation_strings":["Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering National Institute of Technology, Calicut Kerala India","institution_ids":["https://openalex.org/I114845381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114845381"],"apc_list":null,"apc_paid":null,"fwci":2.4801,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91419512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"4","issue":"3","first_page":"186","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9952999949455261,"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":0.9952999949455261,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9919999837875366,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9315999746322632,"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/provenance","display_name":"Provenance","score":0.7154356241226196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7018862962722778},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5024197101593018},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10916215181350708},{"id":"https://openalex.org/keywords/petrology","display_name":"Petrology","score":0.08373886346817017}],"concepts":[{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.7154356241226196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7018862962722778},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5024197101593018},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10916215181350708},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.08373886346817017}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijbdi.2017.10006111","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbdi.2017.10006111","pdf_url":null,"source":{"id":"https://openalex.org/S4210219838","display_name":"International Journal of Big Data Intelligence","issn_l":"2053-1389","issn":["2053-1389","2053-1397"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Big Data Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613"],"abstract_inverted_index":{"Hadoop":[0,123],"MapReduce":[1,15,107,131],"is":[2],"an":[3,149],"analytic":[4],"tool":[5],"used":[6,102],"to":[7,18,36,59,88,103],"solve":[8],"big":[9],"data":[10,23,28,35],"problems":[11],"that":[12,77],"are":[13,30,75],"parallelisable.":[14],"jobs":[16],"need":[17],"be":[19,101],"rerun":[20],"frequently":[21],"for":[22,108,143],"changes.":[24],"Many":[25],"times":[26],"these":[27],"changes":[29],"made":[31],"by":[32],"appending":[33],"new":[34,61,152],"the":[37,48,51,56,60,66,72,79,84],"existing":[38,122],"file.":[39],"So":[40],"in":[41,138,146],"a":[42],"rerun,":[43],"if":[44],"we":[45,63,96],"can":[46,64,100],"reuse":[47],"output":[49],"of":[50,81,121,129,148,151],"previous":[52],"run":[53],"and":[54],"limit":[55],"job":[57,68],"execution":[58,69],"data,":[62],"reduce":[65],"overall":[67],"time.":[70],"In":[71,93],"literature,":[73],"there":[74],"schemes":[76],"use":[78],"concept":[80],"memoisation,":[82],"storing":[83],"intermediate":[85],"result,":[86],"etc.":[87],"implement":[89,104],"efficient":[90],"incremental":[91,106,144],"rerun.":[92],"this":[94],"paper,":[95],"explain":[97],"how":[98],"provenance":[99,136],"transparent":[105],"'append":[109],"only'":[110],"input":[111],"files.":[112],"Our":[113],"approach":[114],"requires":[115],"no":[116],"additional":[117],"storage":[118],"or":[119,125],"modification":[120],"infrastructure":[124],"scheduler.":[126],"Experimental":[127],"evaluation":[128],"running":[130],"on":[132],"multinode":[133],"cluster":[134],"with":[135],"stored":[137],"HBase":[139],"gave":[140],"good":[141],"results":[142],"runs":[145],"cases":[147],"addition":[150],"file/new":[153],"data.":[154]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
