{"id":"https://openalex.org/W4312050775","doi":"https://doi.org/10.1109/tpds.2022.3221210","title":"A Utility-Based Distributed Pattern Mining Algorithm With Reduced Shuffle Overhead","display_name":"A Utility-Based Distributed Pattern Mining Algorithm With Reduced Shuffle Overhead","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4312050775","doi":"https://doi.org/10.1109/tpds.2022.3221210"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3221210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3221210","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5073624587","display_name":"Sunil Kumar","orcid":"https://orcid.org/0000-0002-9778-6550"},"institutions":[{"id":"https://openalex.org/I76777374","display_name":"Central University of Rajasthan","ror":"https://ror.org/056y7zx62","country_code":"IN","type":"education","lineage":["https://openalex.org/I76777374"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar","raw_affiliation_strings":["Department of Computer Science, Central University of Rajasthan, Ajmer, Rajasthan, India"],"raw_orcid":"https://orcid.org/0000-0002-9778-6550","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Central University of Rajasthan, Ajmer, Rajasthan, India","institution_ids":["https://openalex.org/I76777374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036428718","display_name":"Krishna Kumar Mohbey","orcid":"https://orcid.org/0000-0002-7566-0703"},"institutions":[{"id":"https://openalex.org/I76777374","display_name":"Central University of Rajasthan","ror":"https://ror.org/056y7zx62","country_code":"IN","type":"education","lineage":["https://openalex.org/I76777374"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishna Kumar Mohbey","raw_affiliation_strings":["Department of Computer Science, Central University of Rajasthan, Ajmer, Rajasthan, India"],"raw_orcid":"https://orcid.org/0000-0002-7566-0703","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Central University of Rajasthan, Ajmer, Rajasthan, India","institution_ids":["https://openalex.org/I76777374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76777374"],"apc_list":null,"apc_paid":null,"fwci":2.4779,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91386944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"1","first_page":"416","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","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/T10538","display_name":"Data Mining Algorithms and Applications","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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8977820873260498},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7147548198699951},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.650536835193634},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5305706858634949},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5129055976867676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3540945053100586},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1806548535823822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8977820873260498},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7147548198699951},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.650536835193634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5305706858634949},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5129055976867676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3540945053100586},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1806548535823822},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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:10.1109/tpds.2022.3221210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3221210","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W80315153","https://openalex.org/W102878473","https://openalex.org/W1484413656","https://openalex.org/W1842433003","https://openalex.org/W1978733175","https://openalex.org/W1986572138","https://openalex.org/W2017663296","https://openalex.org/W2041884065","https://openalex.org/W2056910091","https://openalex.org/W2058244074","https://openalex.org/W2067403986","https://openalex.org/W2071242348","https://openalex.org/W2081420846","https://openalex.org/W2094830079","https://openalex.org/W2095535748","https://openalex.org/W2099398039","https://openalex.org/W2105768086","https://openalex.org/W2115482638","https://openalex.org/W2115625429","https://openalex.org/W2125352627","https://openalex.org/W2143428105","https://openalex.org/W2148792092","https://openalex.org/W2151201497","https://openalex.org/W2153028052","https://openalex.org/W2155763376","https://openalex.org/W2157355837","https://openalex.org/W2161637667","https://openalex.org/W2163404313","https://openalex.org/W2173213060","https://openalex.org/W2329285245","https://openalex.org/W2340848227","https://openalex.org/W2347204429","https://openalex.org/W2492357902","https://openalex.org/W2512377082","https://openalex.org/W2513061279","https://openalex.org/W2517850251","https://openalex.org/W2584045454","https://openalex.org/W2614083095","https://openalex.org/W2622645393","https://openalex.org/W2750037802","https://openalex.org/W2756096685","https://openalex.org/W2773435160","https://openalex.org/W2782600073","https://openalex.org/W2783772867","https://openalex.org/W2798457757","https://openalex.org/W2806417443","https://openalex.org/W2894237557","https://openalex.org/W2901583666","https://openalex.org/W2904135900","https://openalex.org/W2922254267","https://openalex.org/W2960197288","https://openalex.org/W2974887589","https://openalex.org/W3013103502","https://openalex.org/W3134069806","https://openalex.org/W3165845972","https://openalex.org/W3173999987","https://openalex.org/W4200316921","https://openalex.org/W4293398578","https://openalex.org/W4293731856","https://openalex.org/W6604227873","https://openalex.org/W6626400616","https://openalex.org/W6628750762","https://openalex.org/W6682189057","https://openalex.org/W6795688835"],"related_works":["https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049","https://openalex.org/W2792181990","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1852113167","https://openalex.org/W1493858311","https://openalex.org/W1824242903","https://openalex.org/W3151146928"],"abstract_inverted_index":{"With":[0],"the":[1,4,9,29,40,54,67,98,113,151,156],"arrival":[2],"of":[3,11,25,31,61,142,213],"current":[5],"digital":[6],"era":[7],"and":[8,39,94,173,206,220],"advancement":[10],"information":[12,27],"transmission":[13],"technologies,":[14],"there":[15],"has":[16,33],"been":[17],"an":[18],"unprecedented":[19],"rise":[20],"in":[21,50,128,195,211],"data.":[22],"Efficient":[23],"extraction":[24],"useful":[26],"from":[28,37],"volumes":[30],"data":[32,90,143,168],"garnered":[34],"growing":[35],"interest":[36],"academics":[38],"industry.":[41],"Data":[42],"mining":[43,68],"research":[44],"focuses":[45],"on":[46,112,167],"finding":[47],"utility":[48],"patterns":[49],"large":[51,71],"datasets.":[52,72],"But":[53],"inherent":[55],"complications":[56],"like":[57],"frequent":[58],"scans,":[59],"creation":[60],"substantial":[62],"candidate":[63],"sets,":[64],"etc.":[65],"plague":[66],"process":[69,189],"for":[70,170],"Distributive":[73],"architecture-based":[74],"approaches":[75],"also":[76],"prove":[77],"inefficacious":[78],"due":[79],"to":[80,116],"high":[81],"communication":[82,87,152,216],"overhead":[83,181,205],"over":[84,89],"iterations.":[85],"High":[86],"cost":[88,153],"exchange":[91],"both":[92],"locally":[93],"remotely":[95],"further":[96],"aggravates":[97],"situation.":[99],"We":[100],"propose":[101],"a":[102,129,140,161,171],"Communication":[103,180],"Cost":[104],"Effective":[105],"Utility-based":[106],"Pattern":[107],"Mining":[108],"(CEUPM)":[109],"algorithm":[110],"based":[111,166],"Spark":[114,120],"framework":[115],"address":[117],"this":[118,185],"issue.":[119],"accelerates":[121],"iterative":[122],"scanning":[123],"by":[124],"storing":[125],"scanned":[126],"datasets":[127,135,198],"memory":[130,214],"abstraction":[131],"called":[132],"resilient":[133],"distributed":[134],"(RDD).":[136],"RDD":[137],"operations":[138],"need":[139],"redistribution":[141,186],"among":[144],"cluster":[145,178],"nodes":[146],"during":[147,155,184],"processing.":[148],"To":[149],"minimize":[150],"incurred":[154,183],"shuffle":[157,188],"process,":[158],"we":[159],"adopt":[160],"search":[162],"space":[163],"division":[164],"strategy":[165],"parallelism":[169],"fair":[172],"effective":[174],"task":[175],"allocation":[176],"across":[177],"nodes.":[179],"is":[182],"or":[187],"while":[190],"minimizing":[191],"costs.":[192],"Experimental":[193],"results":[194],"four":[196],"real":[197],"demonstrate":[199],"that":[200],"CEUPM":[201],"considerably":[202],"reduces":[203],"shuffling":[204],"outperforms":[207],"other":[208],"existing":[209],"methods":[210],"terms":[212],"usage,":[215],"cost,":[217],"execution":[218],"time,":[219],"scalability.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}