{"id":"https://openalex.org/W2127982206","doi":"https://doi.org/10.1109/icmlc.2012.6359555","title":"LHS: A novel method of information retrieval avoiding an index using linear hashing with key groups in deduplication","display_name":"LHS: A novel method of information retrieval avoiding an index using linear hashing with key groups in deduplication","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2127982206","doi":"https://doi.org/10.1109/icmlc.2012.6359555","mag":"2127982206"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2012.6359555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2012.6359555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Machine Learning and Cybernetics","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/A5108384834","display_name":"Zhike Zhang","orcid":"https://orcid.org/0000-0002-8726-3174"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhike Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071685496","display_name":"Zejun Jiang","orcid":"https://orcid.org/0000-0002-6651-0826"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejun Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842214","display_name":"Zhiqiang Liu","orcid":"https://orcid.org/0000-0002-9238-3496"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Liu","raw_affiliation_strings":["School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110141971","display_name":"Chengzhang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhang Peng","raw_affiliation_strings":["School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnic University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an China, 710072","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108384834"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3546,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65456866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1312","last_page":"1318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"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/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.889795184135437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8477023839950562},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6233291625976562},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6231748461723328},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6056325435638428},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5662094354629517},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.5368258357048035},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5214923620223999},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48019134998321533},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44832295179367065},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38925743103027344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24535930156707764},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10937097668647766}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.889795184135437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477023839950562},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6233291625976562},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6231748461723328},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6056325435638428},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5662094354629517},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.5368258357048035},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5214923620223999},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48019134998321533},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44832295179367065},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38925743103027344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24535930156707764},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10937097668647766},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2012.6359555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2012.6359555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1508926177","https://openalex.org/W1969126835","https://openalex.org/W2099117306","https://openalex.org/W2123767107","https://openalex.org/W6600228218","https://openalex.org/W6602837329","https://openalex.org/W6608138927","https://openalex.org/W6630499100","https://openalex.org/W6674796100"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W1657880117","https://openalex.org/W2107701374","https://openalex.org/W2595172197","https://openalex.org/W2943088381","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2144348063"],"abstract_inverted_index":{"Indexing":[0],"of":[1,16,31,40,49,70,78,80,93,109,128,137,191,225,233],"RAM":[2,47,71,120,154],"is":[3,29,228],"important":[4,34],"to":[5,13,19,53,72,96,124,141,149,155],"information":[6,17,38,110],"retrieval.":[7],"In":[8],"deduplication":[9,41,166,223],"systems,":[10],"we":[11,104,145],"need":[12,67,148,217],"use":[14],"methods":[15,44,65],"retrieval":[18,39,111],"find":[20],"duplicate":[21],"data":[22],"chunks":[23],"quickly.":[24],"Chunk-lookup":[25],"disk":[26,58,176],"bottleneck":[27],"problem":[28],"one":[30,175],"the":[32,37,74,126,134,138,157,165,188,197,202,205,222],"most":[33],"problems":[35],"in":[36,112,119,153,220],"systems.":[42],"Previous":[43],"can":[45,115],"reduce":[46],"usage":[48],"index":[50,56,75,118,152,219],"a":[51,91,106,129,142],"lot":[52],"avoid":[54,116],"reading":[55],"from":[57],"for":[59,76,178],"every":[60,179,182],"chunk":[61,135],"search.":[62],"However,":[63],"these":[64],"still":[66],"several":[68],"TB":[69],"hold":[73],"dozens":[77],"PB":[79],"storage":[81],"space":[82],"utilization.":[83],"We":[84],"design":[85],"Linear":[86,94],"Hashing":[87],"with":[88,169],"Key":[89],"Groups(LHs),":[90],"variation":[92],"Hashing,":[95],"organize":[97],"and":[98,199],"address":[99,127,190],"bins.":[100],"Based":[101],"on":[102],"LHs,":[103,195],"propose":[105],"novel":[107],"method":[108,161,185,214,227],"deduplication,":[113],"which":[114],"an":[117,151,218],"by":[121],"utilizing":[122],"LHs":[123],"compute":[125],"bin.":[130,207],"A":[131],"bin":[132,189,198],"contains":[133],"IDs":[136],"similar":[139],"files":[140],"file.":[143,180],"Then,":[144],"do":[146,156],"not":[147,163,216],"maintain":[150],"same":[158],"thing.":[159],"Our":[160],"does":[162,215],"decrease":[164],"efficiency":[167,224],"compared":[168],"Extreme":[170,234],"Binning,":[171],"when":[172],"it":[173],"needs":[174],"read":[177],"For":[181],"file,":[183],"our":[184,213,226],"firstly":[186],"computes":[187],"this":[192],"file":[193,203],"using":[194],"loads":[196],"then":[200],"deduplicates":[201],"against":[204],"loaded":[206],"Experimental":[208],"results":[209],"show":[210],"that,":[211],"while":[212],"RAM,":[221],"slightly":[229],"better":[230],"than":[231],"that":[232],"Binning.":[235]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
