{"id":"https://openalex.org/W2011106265","doi":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","title":"Data Deduplication Cluster Based on Similarity-Locality Approach","display_name":"Data Deduplication Cluster Based on Similarity-Locality Approach","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W2011106265","doi":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","mag":"2011106265"},"language":"en","primary_location":{"id":"doi:10.1109/greencom-ithings-cpscom.2013.409","doi":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","pdf_url":null,"source":{"id":"https://openalex.org/S7407087538","display_name":"IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2011106265"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5100432039","display_name":"Xingyu Zhang","orcid":"https://orcid.org/0000-0003-2195-8544","observed_orcids":["https://orcid.org/0000-0003-2195-8544"]},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Zhang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091790870","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0003-3612-7989","observed_orcids":["https://orcid.org/0000-0003-3612-7989"]},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"2168","last_page":"2172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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":0.9970999956130981,"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/T11719","display_name":"Data Quality and Management","score":0.00139999995008111,"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/T11269","display_name":"Algorithms and Data Compression","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.9319999814033508},{"id":"https://openalex.org/keywords/block-level-deduplication","display_name":"block-level deduplication","score":0.9319999814033508},{"id":"https://openalex.org/keywords/data-routing","display_name":"data routing","score":0.9660000205039978},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9440000057220459},{"id":"https://openalex.org/keywords/data-backup","display_name":"data backup","score":0.6079999804496765},{"id":"https://openalex.org/keywords/storage-systems","display_name":"storage systems","score":0.5},{"id":"https://openalex.org/keywords/big-data-storage","display_name":"big data storage","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9778570532798767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629359006881714},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8083047866821289},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7190163135528564},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.612309455871582},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5684455037117004},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46527525782585144},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3823358118534088},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3781033754348755},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2743481397628784},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/greencom-ithings-cpscom.2013.409","doi":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/greencom-ithings-cpscom.2013.409","pdf_url":null,"source":{"id":"https://openalex.org/S7407087538","display_name":"IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W69510097","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1494137514","https://openalex.org/W1521407587","https://openalex.org/W1541467180","https://openalex.org/W1929726975","https://openalex.org/W1965992593","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1978971465","https://openalex.org/W1986313415","https://openalex.org/W2000777721","https://openalex.org/W2003696547","https://openalex.org/W2083139410","https://openalex.org/W2123845384","https://openalex.org/W2128593562","https://openalex.org/W2146889157","https://openalex.org/W2147407897","https://openalex.org/W2281363974","https://openalex.org/W2536989464"],"related_works":["https://openalex.org/W26020480","https://openalex.org/W1965992593","https://openalex.org/W2086416962","https://openalex.org/W2124632914","https://openalex.org/W2903888361","https://openalex.org/W2003696547","https://openalex.org/W1997349095","https://openalex.org/W2402599890","https://openalex.org/W4385287483","https://openalex.org/W4364379626"],"abstract_inverted_index":{"Human":[0],"beings":[1],"have":[2,82],"entered":[3],"the":[4,9,29,85,91,117,121,124,143,148,151],"big":[5],"data":[6,11,16,30,54,92,136],"era,":[7],"and":[8,41,56,90,142],"growing":[10],"bring":[12],"huge":[13],"challenges":[14],"for":[15,53,100],"storage.":[17],"Existing":[18],"deduplication":[19,31,46,62,74,118],"methods":[20],"do":[21],"not":[22],"work":[23],"adequately":[24],"in":[25,50,104],"many":[26],"situations.":[27],"Recently,":[28],"cluster":[32,47,63,75],"has":[33,153],"become":[34],"an":[35],"important":[36],"need":[37],"of":[38,109],"most":[39],"commercial":[40],"research":[42],"backup":[43,55],"systems.":[44],"Data":[45],"becomes":[48,76],"popular":[49],"storage":[51],"system":[52,140,152],"archiving.":[57],"Many":[58],"researchers":[59],"focus":[60],"on":[61],"by":[64],"which":[65],"to":[66,81,116,132],"reduce":[67],"more":[68,134],"redundant":[69],"data.":[70],"Especially":[71],"block":[72],"level":[73],"popular.":[77],"It":[78],"is":[79,98,114,130],"concerned":[80],"two":[83],"challenges:":[84],"chunk-lookup":[86,101],"disk":[87,102],"bottleneck":[88,103],"problem":[89],"routing":[93],"problem.":[94],"A":[95],"new":[96],"solution":[97],"proposed":[99],"our":[105],"paper.":[106],"The":[107,139],"Approach":[108],"combining":[110],"similarity":[111],"with":[112],"locality":[113],"applied":[115],"cluster.":[119],"At":[120],"same":[122],"time,":[123],"bloom":[125],"filter":[126],"algorithm":[127],"storing":[128],"fingerprint":[129],"used":[131],"find":[133],"duplicate":[135],"between":[137],"nodes.":[138],"architecture":[141],"details":[144],"are":[145],"provided.":[146],"Finally,":[147],"experiment":[149],"shows":[150],"a":[154],"good":[155],"performance.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}