{"id":"https://openalex.org/W2003044761","doi":"https://doi.org/10.1109/ic3.2014.6897216","title":"Leveraging hadoop framework to develop duplication detector and analysis using Mapreduce, Hive and Pig","display_name":"Leveraging hadoop framework to develop duplication detector and analysis using Mapreduce, Hive and Pig","publication_year":2014,"publication_date":"2014-08-01","ids":{"openalex":"https://openalex.org/W2003044761","doi":"https://doi.org/10.1109/ic3.2014.6897216","mag":"2003044761"},"language":"en","primary_location":{"id":"doi:10.1109/ic3.2014.6897216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3.2014.6897216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Seventh International Conference on Contemporary Computing (IC3)","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/A5108267422","display_name":"Priyanka Sethi","orcid":null},"institutions":[{"id":"https://openalex.org/I154970844","display_name":"Jaypee Institute of Information Technology","ror":"https://ror.org/05sttyy11","country_code":"IN","type":"education","lineage":["https://openalex.org/I154970844"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyanka Sethi","raw_affiliation_strings":["Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India","Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India-201307"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India","institution_ids":["https://openalex.org/I154970844"]},{"raw_affiliation_string":"Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India-201307","institution_ids":["https://openalex.org/I154970844"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100803556","display_name":"Prakash Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154970844","display_name":"Jaypee Institute of Information Technology","ror":"https://ror.org/05sttyy11","country_code":"IN","type":"education","lineage":["https://openalex.org/I154970844"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prakash Kumar","raw_affiliation_strings":["Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India","Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India-201307"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India","institution_ids":["https://openalex.org/I154970844"]},{"raw_affiliation_string":"Department of Computer Science Engineering and Information Technology, Jaypee Institute of Information Technology, Noida, India-201307","institution_ids":["https://openalex.org/I154970844"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7198,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74450961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"454","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9977999925613403,"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/T11719","display_name":"Data Quality and Management","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9007318019866943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.84578937292099},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.5166087746620178},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.507705807685852},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5050831437110901},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4805731773376465},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.45508626103401184},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4470665752887726},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.44381627440452576},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2900218367576599}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9007318019866943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84578937292099},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.5166087746620178},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.507705807685852},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5050831437110901},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4805731773376465},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.45508626103401184},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4470665752887726},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.44381627440452576},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2900218367576599},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic3.2014.6897216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3.2014.6897216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Seventh International Conference on Contemporary Computing (IC3)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W24740120","https://openalex.org/W66778775","https://openalex.org/W69510097","https://openalex.org/W137089333","https://openalex.org/W174289249","https://openalex.org/W193648907","https://openalex.org/W200233886","https://openalex.org/W230238270","https://openalex.org/W1598064945","https://openalex.org/W1969126835","https://openalex.org/W1974924610","https://openalex.org/W1977797546","https://openalex.org/W1982579475","https://openalex.org/W1986313415","https://openalex.org/W1999984505","https://openalex.org/W2012706015","https://openalex.org/W2030985546","https://openalex.org/W2076793324","https://openalex.org/W2092420848","https://openalex.org/W2107779152","https://openalex.org/W2107782151","https://openalex.org/W2109191804","https://openalex.org/W2119565742","https://openalex.org/W2121133177","https://openalex.org/W2124288146","https://openalex.org/W2125401295","https://openalex.org/W2131894525","https://openalex.org/W2133806194","https://openalex.org/W3147718818","https://openalex.org/W3150003982","https://openalex.org/W6602654064","https://openalex.org/W6602837329","https://openalex.org/W6605588685","https://openalex.org/W6607794886","https://openalex.org/W6608138927","https://openalex.org/W6647052414","https://openalex.org/W6650418438","https://openalex.org/W6676038576"],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W3089119258","https://openalex.org/W3008013744","https://openalex.org/W2884042376","https://openalex.org/W2615141153","https://openalex.org/W2077135008","https://openalex.org/W223870977","https://openalex.org/W2739791894","https://openalex.org/W2351285699"],"abstract_inverted_index":{"The":[0],"burgeoning":[1],"volume":[2],"of":[3,14,17,22,77,87,127],"torrential":[4],"data":[5,38,89,130],"continues":[6],"to":[7,26,33,36,45,55,69,92,101,115],"grow":[8],"exponentially":[9],"in":[10,28,58],"this":[11,20],"very":[12],"age":[13],"the":[15,30,60,75,128,133],"Internet":[16],"Things.":[18],"As":[19],"torrent":[21],"digital":[23],"datasets":[24,144],"continue":[25],"outgrow":[27],"datacenters,":[29],"focus":[31],"needs":[32],"be":[34],"shifted":[35],"stored":[37],"reduction":[39],"methods":[40],"and":[41,64,73,106,117,137,150,155],"that":[42,123,138],"too":[43,139],"pertaining":[44],"NoSQL":[46],"databases":[47],"as":[48],"traditional":[49],"structured":[50],"storage":[51],"systems":[52],"continuously":[53],"tend":[54],"face":[56],"challenges":[57],"providing":[59],"required":[61],"storage,":[62],"throughputs":[63],"computational":[65],"power":[66],"requirements":[67],"necessary":[68],"capture,":[70],"store,":[71],"manage":[72],"analyze":[74],"deluge":[76],"data.":[78],"Deduplication":[79],"systems,":[80],"thus":[81],"designed,":[82],"retain":[83],"a":[84,119],"single":[85],"copy":[86],"redundant":[88],"on":[90],"disk":[91,94],"save":[93],"space,":[95],"but":[96],"what":[97],"if":[98],"we":[99],"want":[100],"keep":[102],"certain":[103],"copies":[104,126],"intentionally":[105],"need":[107],"wishful":[108],"elimination.":[109],"This":[110],"paper":[111],"leverages":[112],"Hadoop":[113],"framework":[114],"design":[116],"develop":[118],"duplication":[120],"detection":[121],"system":[122],"detects":[124],"multiple":[125],"same":[129],"right":[131],"at":[132],"file":[134],"level":[135],"itself":[136],"before":[140],"transmission.":[141],"Thereafter,":[142],"various":[143],"are":[145],"tuned":[146],"for":[147],"better":[148],"performance":[149],"analysed":[151],"using":[152],"MapReduce,":[153],"Hive":[154],"Pig.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}