{"id":"https://openalex.org/W3146677438","doi":"https://doi.org/10.4018/ijitwe.2021040103","title":"Towards Efficient Big Data Storage With MapReduce Deduplication System","display_name":"Towards Efficient Big Data Storage With MapReduce Deduplication System","publication_year":2021,"publication_date":"2021-03-29","ids":{"openalex":"https://openalex.org/W3146677438","doi":"https://doi.org/10.4018/ijitwe.2021040103","mag":"3146677438"},"language":"en","primary_location":{"id":"doi:10.4018/ijitwe.2021040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijitwe.2021040103","pdf_url":null,"source":{"id":"https://openalex.org/S152329874","display_name":"International Journal of Information Technology and Web Engineering","issn_l":"1554-1045","issn":["1554-1045","1554-1053"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology and Web Engineering","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/A5057472354","display_name":"C. Vijesh Joe","orcid":"https://orcid.org/0000-0003-4671-9339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijesh Joe","raw_affiliation_strings":["VV College of Engineering, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VV College of Engineering, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047894504","display_name":"Jennifer S. Raj","orcid":"https://orcid.org/0000-0001-7195-9647"},"institutions":[{"id":"https://openalex.org/I4387154320","display_name":"Gnanamani College of Technology","ror":"https://ror.org/0366mhr44","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387154320"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jennifer S. Raj","raw_affiliation_strings":["Gnanamani College of Technology, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gnanamani College of Technology, India","institution_ids":["https://openalex.org/I4387154320"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029999345","display_name":"S. Smys","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smys S.","raw_affiliation_strings":["RVS Technical Campus, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RVS Technical Campus, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04770199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"2","first_page":"45","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9944000244140625,"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":0.9944000244140625,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9926000237464905,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9093070030212402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.865624189376831},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5640754699707031},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48377344012260437},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4250364601612091},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4199898838996887},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34707212448120117},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2631518244743347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12446179986000061}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9093070030212402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.865624189376831},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5640754699707031},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48377344012260437},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4250364601612091},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4199898838996887},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34707212448120117},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2631518244743347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12446179986000061},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4018/ijitwe.2021040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijitwe.2021040103","pdf_url":null,"source":{"id":"https://openalex.org/S152329874","display_name":"International Journal of Information Technology and Web Engineering","issn_l":"1554-1045","issn":["1554-1045","1554-1053"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology and Web Engineering","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jitwe0:v:16:y:2021:i:2:p:45-57","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJITWE.2021040103","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2010150514","https://openalex.org/W2149140091","https://openalex.org/W2321942028","https://openalex.org/W2401572102","https://openalex.org/W2481696877","https://openalex.org/W2487200295","https://openalex.org/W2511565759","https://openalex.org/W2556483642","https://openalex.org/W2587323806","https://openalex.org/W2590387313","https://openalex.org/W2756289758","https://openalex.org/W2786554768","https://openalex.org/W2792322951","https://openalex.org/W2805733941","https://openalex.org/W2957219408","https://openalex.org/W2958391490","https://openalex.org/W2975055736","https://openalex.org/W3014193728","https://openalex.org/W3185336819"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W1982579475"],"abstract_inverted_index":{"In":[0,111],"the":[1,30,44,59,89,97,121,139,145,160,165],"big":[2],"data":[3,11],"era,":[4],"there":[5],"is":[6,24,50,58,88,108,147],"a":[7,19],"high":[8,54],"requirement":[9],"for":[10,85],"storage":[12,31],"and":[13,22,33,104,116,135,152,167],"processing.":[14],"The":[15,74,142,155],"conventional":[16],"approach":[17,27,62],"faces":[18],"great":[20],"challenge,":[21],"de-duplication":[23,48,128,136],"an":[25],"excellent":[26],"to":[28,42,52,65,95],"reduce":[29],"space":[32],"computational":[34],"time.":[35,73,123,169],"Many":[36],"existing":[37],"approaches":[38],"take":[39],"much":[40],"time":[41,137],"pinpoint":[43],"similar":[45],"data.":[46],"MapReduce":[47,57],"system":[49,76,146,162],"proposed":[51,75,161],"attain":[53],"duplication":[55],"ratio.":[56],"parallel":[60],"processing":[61,168],"that":[63,159],"helps":[64],"process":[66],"large":[67],"number":[68],"of":[69,144],"files":[70],"in":[71],"less":[72],"uses":[77],"two":[78,80],"threshold":[79],"divisor":[81],"with":[82],"switch":[83],"algorithm":[84],"chunking.":[86],"Switch":[87],"average":[90],"parameter":[91],"used":[92,109],"by":[93,149],"TTTD-S":[94],"minimize":[96],"chunk":[98,133],"size":[99,125],"variance.":[100],"Hashing":[101],"using":[102],"SHA-3":[103],"fractal":[105,112],"tree":[106],"indexing":[107],"here.":[110],"index":[113],"tree,":[114],"read":[115],"write":[117],"takes":[118],"place":[119],"at":[120],"same":[122],"Data":[124],"after":[126],"de-duplication,":[127],"ratio,":[129],"throughput,":[130],"hash":[131],"time,":[132,134],"are":[138],"parameters":[140],"used.":[141],"performance":[143],"tested":[148],"college":[150],"scorecard":[151],"ZCTA":[153],"dataset.":[154],"experimental":[156],"results":[157],"show":[158],"can":[163],"lessen":[164],"duplicity":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
