{"id":"https://openalex.org/W2344005651","doi":"https://doi.org/10.1109/tcc.2016.2527646","title":"EPAS: A Sampling Based Similarity Identification Algorithm for the Cloud","display_name":"EPAS: A Sampling Based Similarity Identification Algorithm for the Cloud","publication_year":2016,"publication_date":"2016-02-10","ids":{"openalex":"https://openalex.org/W2344005651","doi":"https://doi.org/10.1109/tcc.2016.2527646","mag":"2344005651"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2016.2527646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2016.2527646","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Cloud Computing","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/A5013906386","display_name":"Yongtao Zhou","orcid":"https://orcid.org/0000-0001-7714-3796"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Zhou","raw_affiliation_strings":["Department of Computer Science, Jinan University, Guangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Jinan University, Guangzhou, P.R. China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073135288","display_name":"Yuhui Deng","orcid":"https://orcid.org/0000-0002-1522-8943"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Deng","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067533020","display_name":"Junjie Xie","orcid":"https://orcid.org/0000-0002-8784-0031"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Xie","raw_affiliation_strings":["Department of Computer Science, Jinan University, Guangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Jinan University, Guangzhou, P.R. China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049154222","display_name":"Laurence T. Yang","orcid":"https://orcid.org/0000-0002-7986-4244"},"institutions":[{"id":"https://openalex.org/I197191942","display_name":"St. Francis Xavier University","ror":"https://ror.org/01wcaxs37","country_code":"CA","type":"education","lineage":["https://openalex.org/I197191942"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laurence T. Yang","raw_affiliation_strings":["Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7986-4244","affiliations":[{"raw_affiliation_string":"Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada","institution_ids":["https://openalex.org/I197191942"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80587469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"3","first_page":"720","last_page":"733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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":0.9980999827384949,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8057500123977661},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6399147510528564},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5826911926269531},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5733116865158081},{"id":"https://openalex.org/keywords/file-size","display_name":"File size","score":0.5621814131736755},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46888917684555054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43581873178482056},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41763073205947876},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32138848304748535},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1959177851676941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1023721992969513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057500123977661},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6399147510528564},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5826911926269531},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5733116865158081},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.5621814131736755},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46888917684555054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43581873178482056},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41763073205947876},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32138848304748535},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1959177851676941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1023721992969513},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcc.2016.2527646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2016.2527646","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Cloud Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3420821451","display_name":null,"funder_award_id":"2013B090200021","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"},{"id":"https://openalex.org/G6616790087","display_name":null,"funder_award_id":"CARCH201401","funder_id":"https://openalex.org/F4320335561","funder_display_name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320335561","display_name":"Institute of Computing Technology, Chinese Academy of Sciences","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W26020480","https://openalex.org/W38366299","https://openalex.org/W99339045","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1034059622","https://openalex.org/W1969126835","https://openalex.org/W1975868314","https://openalex.org/W1988625252","https://openalex.org/W1996771666","https://openalex.org/W1997657677","https://openalex.org/W2001700730","https://openalex.org/W2004286258","https://openalex.org/W2004902747","https://openalex.org/W2012833704","https://openalex.org/W2031725441","https://openalex.org/W2056980397","https://openalex.org/W2059788796","https://openalex.org/W2067545467","https://openalex.org/W2069003154","https://openalex.org/W2075108022","https://openalex.org/W2081193615","https://openalex.org/W2091903458","https://openalex.org/W2109943392","https://openalex.org/W2110322986","https://openalex.org/W2119565742","https://openalex.org/W2123767107","https://openalex.org/W2132069633","https://openalex.org/W2132399973","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2147755199","https://openalex.org/W2151930506","https://openalex.org/W2152565070","https://openalex.org/W2160127232","https://openalex.org/W2170123632","https://openalex.org/W2173213060","https://openalex.org/W2281363974","https://openalex.org/W2998583855","https://openalex.org/W4230940751","https://openalex.org/W4245678615","https://openalex.org/W6601033703","https://openalex.org/W6601562713","https://openalex.org/W6604069196","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6695688771"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W3150465815","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W1997222214","https://openalex.org/W2560439919","https://openalex.org/W4389340727","https://openalex.org/W2802581102","https://openalex.org/W4205786897"],"abstract_inverted_index":{"The":[0,69,136],"explosive":[1],"growth":[2,107],"of":[3,89,108,119,138,148,156,163,204,253,272,292,303],"data":[4,10,18,51,109,126,196],"brings":[5],"new":[6],"challenges":[7],"to":[8,21,40,79,128,169,182,208,223,237,248],"the":[9,29,41,81,102,106,130,153,170,187,199,202,205,210,215,225,232,238,250,261,265,307],"storage":[11],"and":[12,61,72,92,95,112,142,201,230,276,288],"management":[13],"in":[14,24,28,50,114,270],"cloud":[15,188],"environment.":[16],"These":[17],"usually":[19],"have":[20],"be":[22],"processed":[23],"a":[25,37,46,115,145,161,245,282],"timely":[26],"fashion":[27],"cloud.":[30,308],"Thus,":[31],"any":[32],"increased":[33],"latency":[34],"may":[35],"cause":[36],"massive":[38],"loss":[39],"enterprises.":[42],"Similarity":[43],"detection":[44,234,295],"plays":[45],"very":[47],"important":[48],"role":[49],"management.":[52],"Many":[53],"typical":[54],"algorithms":[55,74,269],"such":[56],"as":[57,132],"Shingle,":[58,70],"Simhash,":[59],"Traits":[60,73],"Traditional":[62],"Sampling":[63,179],"Algorithm":[64],"(TSA)":[65],"are":[66],"extensively":[67],"used.":[68],"Simhash":[71],"read":[75],"entire":[76,121],"source":[77,149],"file":[78,157,184,191,207],"calculate":[80,129],"corresponding":[82],"similarity":[83,133,164,185,226,254,294,304],"characteristic":[84],"value,":[85],"thus":[86],"requiring":[87],"lots":[88],"CPU":[90,275],"cycles":[91],"memory":[93,277],"space":[94],"incurring":[96],"tremendous":[97],"disk":[98],"accesses.":[99],"In":[100],"addition,":[101],"overhead":[103,137,252],"increases":[104],"with":[105],"set":[110],"volume":[111],"results":[113,258],"long":[116],"delay.":[117],"Instead":[118],"reading":[120],"file,":[122],"TSA":[123,139],"samples":[124,195],"some":[125],"blocks":[127,197],"fingerprints":[131],"characteristics":[134],"value.":[135],"is":[140,166,221,299],"fixed":[141],"negligible.":[143],"However,":[144],"slight":[146,171],"modification":[147],"files":[150,229],"will":[151],"trigger":[152],"bit":[154],"positions":[155],"content":[158],"shifting.":[159],"Therefore,":[160,297],"failure":[162],"identification":[165,305],"inevitable":[167],"due":[168],"modifications.":[172,216],"This":[173],"paper":[174,243],"proposes":[175],"an":[176,218,300],"Enhanced":[177],"Position-Aware":[178],"algorithm":[180,247],"(EPAS)":[181],"identify":[183],"for":[186,306],"by":[189,214],"modulo":[190],"length.":[192],"EPAS":[193,262,280],"concurrently":[194],"from":[198],"head":[200],"tail":[203],"modulated":[206],"avoid":[209],"position":[211],"shift":[212],"incurred":[213],"Meanwhile,":[217],"improved":[219],"metric":[220],"proposed":[222],"measure":[224],"between":[227,286],"different":[228],"make":[231],"possible":[233],"probability":[235],"close":[236],"actual":[239],"probability.":[240],"Furthermore,":[241],"this":[242],"describes":[244],"query":[246],"reduce":[249],"time":[251,273],"detection.":[255],"Our":[256],"experimental":[257],"demonstrate":[259],"that":[260,291],"significantly":[263],"outperforms":[264],"existing":[266],"well":[267],"known":[268],"terms":[271],"overhead,":[274],"occupation.":[278],"Moreover,":[279],"makes":[281],"more":[283],"preferable":[284],"tradeoff":[285],"precision":[287],"recall":[289],"than":[290],"other":[293],"algorithms.":[296],"it":[298],"effective":[301],"approach":[302]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
