{"id":"https://openalex.org/W4391305309","doi":"https://doi.org/10.1109/tii.2024.3353913","title":"GreedyGD: Enhanced Generalized Deduplication for Direct Analytics in IoT","display_name":"GreedyGD: Enhanced Generalized Deduplication for Direct Analytics in IoT","publication_year":2024,"publication_date":"2024-01-29","ids":{"openalex":"https://openalex.org/W4391305309","doi":"https://doi.org/10.1109/tii.2024.3353913"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2024.3353913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3353913","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/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":true,"raw_author_name":"Aaron Hurst","raw_affiliation_strings":["DIGIT Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110828662","display_name":"Daniel E. Lucani","orcid":null},"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 Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","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 Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT Centre and the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103233839"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":3.3421,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92214349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"20","issue":"4","first_page":"6954","last_page":"6962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996399998664856,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8955796957015991},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.830970287322998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7723509669303894},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6874822378158569},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6744999885559082},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6646578311920166},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.5492210984230042},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.4758588671684265},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42101728916168213},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3499869108200073},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32704734802246094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2728565037250519},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.16335809230804443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11853387951850891}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8955796957015991},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.830970287322998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723509669303894},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6874822378158569},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6744999885559082},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6646578311920166},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.5492210984230042},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.4758588671684265},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42101728916168213},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3499869108200073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32704734802246094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2728565037250519},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.16335809230804443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11853387951850891}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tii.2024.3353913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3353913","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/a6aa9d99-899e-45f0-ac0b-952449bf6080","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/a6aa9d99-899e-45f0-ac0b-952449bf6080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hurst, A, Lucani R\u00f6tter, D E & Zhang, Q 2024, 'GreedyGD: Enhanced Generalized Deduplication for Direct Analytics in IoT', IEEE Transactions on Industrial Informatics, vol. 20, no. 4, pp. 6954-6962. https://doi.org/10.1109/TII.2024.3353913","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W105287674","https://openalex.org/W1592493173","https://openalex.org/W1743861851","https://openalex.org/W1977556410","https://openalex.org/W2024171325","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2161488606","https://openalex.org/W2204310803","https://openalex.org/W2296760620","https://openalex.org/W2395370972","https://openalex.org/W2751531235","https://openalex.org/W2768475350","https://openalex.org/W2811266402","https://openalex.org/W2886377182","https://openalex.org/W2910070523","https://openalex.org/W2921514674","https://openalex.org/W2993853848","https://openalex.org/W3010302802","https://openalex.org/W3044766408","https://openalex.org/W3047599943","https://openalex.org/W3098592065","https://openalex.org/W3162385334","https://openalex.org/W3179083294","https://openalex.org/W4210817337","https://openalex.org/W4226425434","https://openalex.org/W6635549040","https://openalex.org/W6683504902","https://openalex.org/W6780883385","https://openalex.org/W6940864310"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2032414556","https://openalex.org/W2169871401","https://openalex.org/W2057878850"],"abstract_inverted_index":{"The":[0],"exponential":[1],"growth":[2],"of":[3,9],"data":[4,15,38,84,91,130],"generated":[5],"by":[6],"the":[7],"Internet":[8],"Things":[10],"presents":[11],"significant":[12],"challenges":[13],"for":[14],"communication,":[16],"storage,":[17],"and":[18,40,97,120,123],"analytics.":[19],"Consequently,":[20],"organizations":[21],"often":[22],"face":[23],"high":[24,63],"costs":[25],"when":[26],"attempting":[27],"to":[28,101,132],"leverage":[29],"their":[30],"own":[31],"data.":[32,74],"Novel":[33],"techniques":[34],"that":[35,61,87],"holistically":[36],"optimize":[37],"storage":[39],"analytics":[41,125],"in":[42],"IoT":[43],"systems":[44],"are":[45],"therefore":[46],"required.":[47],"One":[48],"promising":[49],"approach":[50],"is":[51,56],"generalized":[52],"deduplication":[53],"(GD),":[54],"which":[55],"a":[57,81,114],"lossless":[58],"compression":[59,64,85,96],"technique":[60],"delivers":[62],"while":[65,126],"also":[66],"enabling":[67],"low-cost":[68],"random":[69],"access":[70],"directly":[71],"on":[72,107],"compressed":[73],"In":[75],"this":[76],"article,":[77],"we":[78],"introduce":[79],"GreedyGD,":[80],"novel":[82],"GD":[83,103,134],"algorithm":[86],"offers":[88],"reliable,":[89],"efficient":[90],"analytics,":[92],"along":[93],"with":[94],"more":[95,118,121],"faster":[98],"runtime":[99],"compared":[100,131],"previous":[102,133],"compressors.":[104,135],"Evaluating":[105],"GreedyGD":[106],"18":[108],"real-world":[109],"datasets":[110],"revealed":[111],"excellent":[112],"performance:":[113],"11.2\u00d7":[115],"speed-up,":[116],"1.6\u00d7":[117],"compression,":[119],"accurate":[122],"reliable":[124],"using":[127],"4\u00d7":[128],"less":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}