{"id":"https://openalex.org/W4210817337","doi":"https://doi.org/10.1109/globecom46510.2021.9685589","title":"Direct Analytics of Generalized Deduplication Compressed IoT Data","display_name":"Direct Analytics of Generalized Deduplication Compressed IoT Data","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4210817337","doi":"https://doi.org/10.1109/globecom46510.2021.9685589"},"language":"en","primary_location":{"id":"doi:10.1109/globecom46510.2021.9685589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom46510.2021.9685589","pdf_url":null,"source":{"id":"https://openalex.org/S4363607714","display_name":"2021 IEEE Global Communications Conference (GLOBECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103233839","display_name":"Aaron Hurst","orcid":"https://orcid.org/0000-0002-9683-7774"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Aaron Hurst","raw_affiliation_strings":["DIGIT, Aarhus University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIGIT, Aarhus University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360194","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0001-5303-9804"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["DIGIT, Aarhus University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIGIT, Aarhus University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110828662","display_name":"Daniel E. Lucani","orcid":"https://orcid.org/0000-0001-5325-8863"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel E. Lucani","raw_affiliation_strings":["DIGIT, Aarhus University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIGIT, Aarhus University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104360871","display_name":"Ira Assent","orcid":"https://orcid.org/0000-0002-1091-9948"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ira Assent","raw_affiliation_strings":["DIGIT, Aarhus University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIGIT, Aarhus University,Department of Computer Science","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":1.0227,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78411229,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.983299970626831,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.983299970626831,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9084030389785767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8338141441345215},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.7955126166343689},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6812576651573181},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6484774351119995},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.6209881901741028},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.5381883382797241},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5371042490005493},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5202656984329224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5052538514137268},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.45261555910110474},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4444800019264221},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.44074100255966187},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32850146293640137},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21731576323509216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10141852498054504},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09628593921661377},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08352795243263245}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9084030389785767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338141441345215},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.7955126166343689},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6812576651573181},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6484774351119995},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.6209881901741028},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.5381883382797241},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5371042490005493},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5202656984329224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5052538514137268},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.45261555910110474},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4444800019264221},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.44074100255966187},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32850146293640137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21731576323509216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10141852498054504},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09628593921661377},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08352795243263245},{"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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globecom46510.2021.9685589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom46510.2021.9685589","pdf_url":null,"source":{"id":"https://openalex.org/S4363607714","display_name":"2021 IEEE Global Communications Conference (GLOBECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/8236b60f-f9d7-48df-9f85-2a910a948303","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/8236b60f-f9d7-48df-9f85-2a910a948303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hurst, A, Zhang, Q, Lucani R\u00f6tter, D E & Assent, I 2021, Direct Analytics of Generalized Deduplication Compressed IoT Data. in 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings. IEEE, IEEE Global Communications Conference (GLOBECOM), IEEE Conference and Exhibition on Global Telecommunications, Madrid, Spain, 07/12/2021. https://doi.org/10.1109/GLOBECOM46510.2021.9685589","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1996881001","https://openalex.org/W2047612536","https://openalex.org/W2395370972","https://openalex.org/W2537240387","https://openalex.org/W2747704798","https://openalex.org/W2778613407","https://openalex.org/W2806161436","https://openalex.org/W2886377182","https://openalex.org/W2891503716","https://openalex.org/W2891870102","https://openalex.org/W2958089299","https://openalex.org/W2963235000","https://openalex.org/W3000117384","https://openalex.org/W3010302802","https://openalex.org/W3013367821","https://openalex.org/W3031675169","https://openalex.org/W3034838735","https://openalex.org/W3047599943","https://openalex.org/W3081642083","https://openalex.org/W3098592065","https://openalex.org/W3120740533","https://openalex.org/W3125626969","https://openalex.org/W3147010956","https://openalex.org/W3162385334","https://openalex.org/W4233996382","https://openalex.org/W6765537425","https://openalex.org/W6779357891","https://openalex.org/W6792985385"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2032334472","https://openalex.org/W4383897877","https://openalex.org/W3008013744","https://openalex.org/W2884042376","https://openalex.org/W2615141153","https://openalex.org/W2077135008","https://openalex.org/W223870977","https://openalex.org/W2739791894"],"abstract_inverted_index":{"Given":[0],"the":[1,9,21,39,55,65,68,82,103,118],"ever":[2],"increasing":[3],"volume":[4],"of":[5,11,23,50,67,120],"data":[6,13,24,52,63,96,104],"generated":[7],"by":[8,73],"Internet":[10],"Things,":[12],"compression":[14,58,121],"plays":[15],"an":[16],"essential":[17],"role":[18],"in":[19,126],"reducing":[20],"cost":[22],"transmission":[25],"and":[26,38,97,122],"storage.":[27],"However,":[28,85],"it":[29,86,112],"also":[30],"introduces":[31],"a":[32],"barrier,":[33],"namely":[34],"decompression,":[35],"between":[36],"users":[37],"data-driven":[40],"insights":[41],"they":[42],"require.":[43],"We":[44],"propose":[45],"methods":[46],"for":[47],"direct":[48],"analytics":[49,79,125],"compressed":[51],"based":[53],"on":[54],"Generalized":[56],"Deduplication":[57],"algorithm.":[59],"When":[60],"applied":[61],"to":[62,78,115],"clustering,":[64],"accuracy":[66],"best":[69],"performing":[70],"method":[71],"differs":[72],"merely":[74],"1-5%":[75],"when":[76],"compared":[77],"performed":[80],"upon":[81],"uncompressed":[83],"data.":[84],"runs":[87],"four":[88],"times":[89],"faster,":[90],"accesses":[91],"only":[92],"14%":[93],"as":[94],"much":[95],"requires":[98],"significantly":[99],"less":[100],"storage":[101],"since":[102],"is":[105,113],"always":[106],"compressed.":[107],"These":[108],"results":[109],"show":[110],"that":[111],"possible":[114],"simultaneously":[116],"reap":[117],"benefits":[119],"accurate,":[123],"high-speed":[124],"many":[127],"applications.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}