{"id":"https://openalex.org/W2575776434","doi":"https://doi.org/10.1109/ccaa.2016.7813695","title":"Observations on factors affecting performance of MapReduce based Apriori on Hadoop cluster","display_name":"Observations on factors affecting performance of MapReduce based Apriori on Hadoop cluster","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2575776434","doi":"https://doi.org/10.1109/ccaa.2016.7813695","mag":"2575776434"},"language":"en","primary_location":{"id":"doi:10.1109/ccaa.2016.7813695","doi":"https://doi.org/10.1109/ccaa.2016.7813695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccaa.2016.7813695","pdf_url":null,"source":{"id":"https://openalex.org/S4306423450","display_name":"International Conference on Computing, Communication and Automation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Computing, Communication and Automation (ICCCA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1701.05982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011296934","display_name":"Sudhakar Singh","orcid":"https://orcid.org/0000-0002-0710-924X","observed_orcids":["https://orcid.org/0000-0002-0710-924X"]},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudhakar Singh","raw_affiliation_strings":["Department of Computer Science, Institute of Science, BHU, Varanasi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Institute of Science, BHU, Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083646550","display_name":"Rakhi Garg","orcid":"https://orcid.org/0000-0003-0083-5465","observed_orcids":["https://orcid.org/0000-0003-0083-5465"]},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rakhi Garg","raw_affiliation_strings":["Department of Computer Science, Institute of Science, BHU, Varanasi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Institute of Science, BHU, Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081133318","display_name":"Pramod Kumar Mishra","orcid":"https://orcid.org/0000-0003-3957-1161","observed_orcids":["https://orcid.org/0000-0003-3957-1161"]},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. K. Mishra","raw_affiliation_strings":["Department of Computer Science, Institute of Science, BHU, Varanasi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Institute of Science, BHU, Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8492,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75534968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"128","issue":null,"first_page":"87","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8848000168800354,"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":0.8848000168800354,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.10740000009536743,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0012000000569969416,"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/apriori-algorithm","display_name":"Apriori algorithm","score":0.8840000033378601},{"id":"https://openalex.org/keywords/mapreduce","display_name":"MapReduce","score":0.9070000052452087},{"id":"https://openalex.org/keywords/hadoop-cluster","display_name":"Hadoop cluster","score":0.7760000228881836},{"id":"https://openalex.org/keywords/frequent-itemset-mining","display_name":"frequent itemset mining","score":0.996999979019165},{"id":"https://openalex.org/keywords/execution-time","display_name":"execution time","score":0.4259999990463257},{"id":"https://openalex.org/keywords/data-structures","display_name":"data structures","score":0.8820000290870667},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"speculative execution","score":0.9580000042915344},{"id":"https://openalex.org/keywords/data-locality","display_name":"data locality","score":0.9959999918937683},{"id":"https://openalex.org/keywords/parallelism-control","display_name":"parallelism control","score":0.8769999742507935},{"id":"https://openalex.org/keywords/heterogeneous-clusters","display_name":"heterogeneous clusters","score":0.7789999842643738},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.5379999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789225816726685},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7729381322860718},{"id":"https://openalex.org/C81440476","wikidata":"https://www.wikidata.org/wiki/Q513511","display_name":"Apriori algorithm","level":3,"score":0.7199350595474243},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6721184253692627},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6649853587150574},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5945960879325867},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5605648756027222},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5423799753189087},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5386860370635986},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.532680094242096},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4917481243610382},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.40807127952575684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39736050367355347},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35738682746887207},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23910880088806152},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07828009128570557},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ccaa.2016.7813695","doi":"https://doi.org/10.1109/ccaa.2016.7813695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccaa.2016.7813695","pdf_url":null,"source":{"id":"https://openalex.org/S4306423450","display_name":"International Conference on Computing, Communication and Automation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Computing, Communication and Automation (ICCCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1701.05982","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.05982","pdf_url":"https://arxiv.org/pdf/1701.05982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3153011551","doi":null,"is_oa":true,"landing_page_url":"https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3411204","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SSRN Electronic Journal","raw_type":null},{"id":"doi:10.48550/arxiv.1701.05982","doi":"https://doi.org/10.48550/arxiv.1701.05982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1701.05982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1701.05982","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.05982","pdf_url":"https://arxiv.org/pdf/1701.05982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W33383766","https://openalex.org/W86569730","https://openalex.org/W1484413656","https://openalex.org/W1542978828","https://openalex.org/W1594908600","https://openalex.org/W1861377444","https://openalex.org/W1981162575","https://openalex.org/W1987671078","https://openalex.org/W1992540139","https://openalex.org/W1995797177","https://openalex.org/W1996438407","https://openalex.org/W2004748427","https://openalex.org/W2041325010","https://openalex.org/W2060444451","https://openalex.org/W2087665380","https://openalex.org/W2094836054","https://openalex.org/W2105768086","https://openalex.org/W2119565742","https://openalex.org/W2129714679","https://openalex.org/W2140190241","https://openalex.org/W2140486418","https://openalex.org/W2140838268","https://openalex.org/W2146068062","https://openalex.org/W2148443481","https://openalex.org/W2164604674","https://openalex.org/W2173213060","https://openalex.org/W2254826453","https://openalex.org/W4231139262","https://openalex.org/W6603523508"],"related_works":["https://openalex.org/W2254826453","https://openalex.org/W1995797177","https://openalex.org/W2765714237","https://openalex.org/W2185520150","https://openalex.org/W7097646313","https://openalex.org/W3004324706","https://openalex.org/W4384069289","https://openalex.org/W2761477774","https://openalex.org/W2349740581","https://openalex.org/W2593768537"],"abstract_inverted_index":{"Designing":[0,36],"fast":[1],"and":[2,15,29,44,94,104,116,128,154,168],"scalable":[3],"algorithm":[4,31],"for":[5],"mining":[6],"frequent":[7,33],"itemsets":[8],"is":[9,22,48,192],"always":[10],"being":[11],"a":[12,77,193],"most":[13,26],"eminent":[14],"promising":[16],"problem":[17],"of":[18,24,32,61,79,87,151,189,208],"data":[19,117,126,147,152],"mining.":[20,35],"Apriori":[21,64,90,209],"one":[23],"the":[25,59,84,134,171,203,214],"broadly":[27],"used":[28],"popular":[30],"itemset":[34],"efficient":[37],"algorithms":[38],"on":[39,58,65,70,92],"MapReduce":[40,62,88,206],"framework":[41],"to":[42,101,110],"process":[43],"analyze":[45],"big":[46],"datasets":[47],"contemporary":[49],"research":[50],"nowadays.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,200],"have":[56,75,162,201],"focused":[57],"performance":[60],"based":[63,89],"homogeneous":[66,93],"as":[67,69],"well":[68],"heterogeneous":[71,95],"Hadoop":[72,96],"cluster.":[73],"We":[74,161],"investigated":[76],"number":[78],"factors":[80,108,139,167],"that":[81,122,181],"significantly":[82,212],"affects":[83],"execution":[85,135,197],"time":[86],"running":[91],"Cluster.":[97],"Factors":[98],"are":[99,113,186],"specific":[100,109,184],"both":[102],"algorithmic":[103,111],"non-algorithmic":[105,138],"improvements.":[106],"Considered":[107],"improvements":[112],"filtered":[114,129],"transactions":[115,130],"structures.":[118],"Experimental":[119,178],"results":[120,179],"show":[121,180],"how":[123],"an":[124],"appropriate":[125],"structure":[127],"technique":[131],"drastically":[132],"reduce":[133],"time.":[136,198],"The":[137],"include":[140],"speculative":[141],"execution,":[142],"nodes":[143],"with":[144,157],"poor":[145],"performance,":[146],"locality":[148],"&":[149],"distribution":[150],"blocks,":[153],"parallelism":[155],"control":[156],"input":[158],"split":[159],"size.":[160],"applied":[163],"strategies":[164],"against":[165],"these":[166],"fine":[169],"tuned":[170],"relevant":[172],"parameters":[173,185],"in":[174,196],"our":[175],"particular":[176],"application.":[177],"if":[182],"cluster":[183],"taken":[187],"care":[188],"then":[190],"there":[191],"significant":[194],"reduction":[195],"Also":[199],"discussed":[202],"issues":[204],"regarding":[205],"implementation":[207],"which":[210],"may":[211],"influence":[213],"performance.":[215]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2017-01-26T00:00:00"}