{"id":"https://openalex.org/W2795067252","doi":"https://doi.org/10.1145/3190645.3190705","title":"A comparative study of mapreduce and hive based on the design of the information gain algorithm for analytical workloads","display_name":"A comparative study of mapreduce and hive based on the design of the information gain algorithm for analytical workloads","publication_year":2018,"publication_date":"2018-03-29","ids":{"openalex":"https://openalex.org/W2795067252","doi":"https://doi.org/10.1145/3190645.3190705","mag":"2795067252"},"language":"en","primary_location":{"id":"doi:10.1145/3190645.3190705","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3190645.3190705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACMSE 2018 Conference","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/A5038428882","display_name":"Sikha Bagui","orcid":"https://orcid.org/0000-0002-1886-4582"},"institutions":[{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sikha Bagui","raw_affiliation_strings":["The University of West Florida"],"affiliations":[{"raw_affiliation_string":"The University of West Florida","institution_ids":["https://openalex.org/I83683471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003128110","display_name":"Sharon K. John","orcid":null},"institutions":[{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharon K. John","raw_affiliation_strings":["The University of West Florida"],"affiliations":[{"raw_affiliation_string":"The University of West Florida","institution_ids":["https://openalex.org/I83683471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037812317","display_name":"John P. Baggs","orcid":null},"institutions":[{"id":"https://openalex.org/I83683471","display_name":"University of West Florida","ror":"https://ror.org/002w4zy91","country_code":"US","type":"education","lineage":["https://openalex.org/I83683471"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John P. Baggs","raw_affiliation_strings":["The University of West Florida"],"affiliations":[{"raw_affiliation_string":"The University of West Florida","institution_ids":["https://openalex.org/I83683471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038428882"],"corresponding_institution_ids":["https://openalex.org/I83683471"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03228071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9955000281333923,"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":0.9955000281333923,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.8850533962249756},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.709421694278717},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.633315920829773},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5712313055992126},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5622295141220093},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5332780480384827},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5099042654037476},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43275973200798035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4061431884765625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33052587509155273},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29927998781204224},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15859255194664001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8850533962249756},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.709421694278717},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.633315920829773},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5712313055992126},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5622295141220093},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5332780480384827},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5099042654037476},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43275973200798035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4061431884765625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33052587509155273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29927998781204224},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15859255194664001},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1145/3190645.3190705","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3190645.3190705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACMSE 2018 Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1684737195"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2046172023","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W2972896947","https://openalex.org/W85300993"],"abstract_inverted_index":{"Information":[0,198],"Gain":[1,199],"(IG)":[2],"or":[3],"the":[4,41,46,64,124,135,145,180,185,211],"Kullback":[5],"Leibler":[6],"algorithm":[7,11],"is":[8,13,79,116,182],"a":[9,163],"statistical":[10],"that":[12,77,215],"employed":[14],"to":[15,21,44,93,97,118,122,228],"extract":[16],"useful":[17],"features":[18],"from":[19,184],"datasets":[20],"eliminate":[22],"redundant":[23],"and":[24,50,85,104,143,154,193,213,220,226],"valueless":[25],"features.":[26],"Applying":[27],"this":[28,111],"feature":[29],"selection":[30],"technique":[31],"paves":[32],"way":[33],"for":[34,59,82,140,149,176,232],"sophisticated":[35],"analysis":[36],"on":[37,152,200,210],"Big":[38,112],"Data,":[39],"requiring":[40],"underlying":[42],"framework":[43,142],"handle":[45],"data":[47,83,172],"complexity,":[48],"volume":[49],"velocity.":[51],"The":[52],"Hadoop":[53,141],"ecosystem":[54],"comes":[55],"in":[56,137],"handy,":[57],"enabling":[58],"seamless":[60],"distributed":[61],"computing":[62,65],"leveraging":[63],"potential":[66],"of":[67,126,147,187,197],"many":[68],"commercial":[69],"machines.":[70],"Previous":[71],"research":[72],"studies":[73],"[1,":[74],"2]":[75],"indicate":[76],"Hive":[78,153],"best":[80],"suited":[81],"warehousing":[84],"ETL":[86],"(Extract,":[87],"Transform,":[88],"Load)":[89],"workloads.":[90,178],"We":[91],"aim":[92],"extend":[94],"Hive's":[95],"capability":[96],"analyze":[98],"how":[99],"it":[100,115],"suits":[101],"analytical":[102,150,177],"algorithms":[103,120],"compare":[105],"its":[106],"performance":[107],"with":[108],"MapReduce.":[109,155],"In":[110],"Data":[113],"era,":[114],"essential":[117],"design":[119],"efficiently":[121],"reap":[123],"benefits":[125,212],"parallelization":[127],"over":[128,162],"existing":[129],"frameworks.":[130],"This":[131],"study":[132],"will":[133,206,223],"showcase":[134],"efficacy":[136],"designing":[138],"IG":[139,148],"discuss":[144],"implementation":[146,196],"workload":[151],"Inherently":[156],"both":[157,201],"these":[158,202],"components":[159,205,231],"are":[160],"built":[161],"shared":[164],"nothing":[165],"architecture":[166],"which":[167],"prevents":[168],"contention":[169],"issues":[170],"increasing":[171],"parallelism,":[173],"thus":[174],"best-fitting":[175],"Hence,":[179],"programmer":[181],"relieved":[183],"overhead":[186],"maintaining":[188],"structures":[189],"like":[190],"indexes,":[191],"caches":[192],"partitions.":[194],"Assessing":[195],"parallel":[203],"processing":[204],"certainly":[207],"provide":[208],"insights":[209],"downsides":[214],"each":[216],"component":[217],"should":[218],"offer":[219],"at":[221],"large":[222],"enable":[224],"researchers":[225],"developers":[227],"employ":[229],"appropriate":[230],"suitable":[233],"tasks.":[234]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}