{"id":"https://openalex.org/W2963191517","doi":"https://doi.org/10.1109/tkde.2019.2931014","title":"Bit-oriented Sampling for Aggregation on Big Data","display_name":"Bit-oriented Sampling for Aggregation on Big Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963191517","doi":"https://doi.org/10.1109/tkde.2019.2931014","mag":"2963191517"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2019.2931014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2019.2931014","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5100630087","display_name":"Huan Hu","orcid":"https://orcid.org/0000-0001-5022-0771"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Hu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.156,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58553476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","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/T10317","display_name":"Advanced Database Systems and Queries","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/T12761","display_name":"Data Stream Mining Techniques","score":0.9962999820709229,"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/T11106","display_name":"Data Management and Algorithms","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.818697452545166},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5118018984794617},{"id":"https://openalex.org/keywords/bit","display_name":"Bit (key)","score":0.46950387954711914},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4548715353012085},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2878970503807068},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2015409767627716},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13704124093055725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818697452545166},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5118018984794617},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.46950387954711914},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4548715353012085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2878970503807068},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2015409767627716},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13704124093055725},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2019.2931014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2019.2931014","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4894050043","display_name":null,"funder_award_id":"61832003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G511195426","display_name":"\u5927\u56fe\u6570\u636e\u7ba1\u7406\u4e0e\u5206\u6790\u7684\u57fa\u7840\u7406\u8bba\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61732003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G559540161","display_name":null,"funder_award_id":"U1811461.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W67853643","https://openalex.org/W1523176169","https://openalex.org/W1588594383","https://openalex.org/W1595409123","https://openalex.org/W1967983783","https://openalex.org/W1971459440","https://openalex.org/W2002791618","https://openalex.org/W2005112390","https://openalex.org/W2020147322","https://openalex.org/W2022858489","https://openalex.org/W2022942700","https://openalex.org/W2037701287","https://openalex.org/W2041682101","https://openalex.org/W2066293100","https://openalex.org/W2072534270","https://openalex.org/W2079942837","https://openalex.org/W2103012681","https://openalex.org/W2103212156","https://openalex.org/W2111967617","https://openalex.org/W2112734514","https://openalex.org/W2117897510","https://openalex.org/W2130673381","https://openalex.org/W2137206963","https://openalex.org/W2160770337","https://openalex.org/W2164507334","https://openalex.org/W2167811976","https://openalex.org/W2199389590","https://openalex.org/W2260305637","https://openalex.org/W2272315143","https://openalex.org/W2288076324","https://openalex.org/W2293308125","https://openalex.org/W2295862081","https://openalex.org/W2296677182","https://openalex.org/W2430301697","https://openalex.org/W2436406362","https://openalex.org/W2612337305","https://openalex.org/W2613215397","https://openalex.org/W2613312134","https://openalex.org/W2613577383","https://openalex.org/W2614565221","https://openalex.org/W2732582420","https://openalex.org/W2798499404","https://openalex.org/W2899702797","https://openalex.org/W3147685784","https://openalex.org/W4229903866","https://openalex.org/W4233413206","https://openalex.org/W4250212406","https://openalex.org/W4250981202","https://openalex.org/W4299827484","https://openalex.org/W6602782649","https://openalex.org/W6692524477"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2411923897","https://openalex.org/W2910064364","https://openalex.org/W4255224757"],"abstract_inverted_index":{"The":[0],"efficiency":[1],"of":[2,21,38,43,53,63,76,83,93,105,137,152],"big":[3],"data":[4,54,65],"analysis":[5],"has":[6,80],"become":[7],"a":[8,12,19,36,81,148,178],"bottleneck.":[9],"Aggregation":[10],"is":[11,28,48,88],"fundamental":[13],"analytical":[14],"task.":[15],"It":[16],"usually":[17],"consumes":[18],"lot":[20],"time":[22,34],"so":[23],"that":[24,157,171,191],"sampling":[25,47,77,87,100,108,142,180],"based":[26,78,109,119,143],"aggregation":[27,72,79,153],"often":[29],"used":[30],"to":[31,70],"improve":[32],"response":[33],"at":[35,50,59,90],"loss":[37],"result":[39,176],"accuracy.":[40],"In":[41],"all":[42],"the":[44,51,57,74,91,121,126,135,138,155,167,188],"related":[45],"works,":[46],"conducted":[49,89],"granularity":[52,92],"item.":[55],"Considering":[56],"bits":[58],"different":[60,68],"bit":[61],"positions":[62],"each":[64],"item":[66],"have":[67],"contributions":[69],"an":[71],"result,":[73],"performance":[75],"chance":[82],"being":[84],"improved":[85],"if":[86],"bit.":[94],"Thus,":[95],"this":[96],"paper":[97],"studies":[98],"bit-oriented":[99,106],"for":[101],"aggregation.":[102,144],"Two":[103],"methods":[104,136],"uniform":[107,141],"aggregation,":[110],"i.e.,":[111],"DVBM":[112,145,192],"and":[113,187,193,198],"DVFM,":[114],"are":[115,118,130,184,195],"proposed":[116],"which":[117],"on":[120],"central":[122],"limit":[123],"theorem":[124],"or":[125],"Chebyshev's":[127],"inequality.":[128],"They":[129],"much":[131],"more":[132],"efficient":[133,197],"than":[134],"traditional":[139],"data-oriented":[140],"can":[146],"guarantee":[147],"given":[149],"error":[150],"bound":[151],"with":[154],"assumption":[156],"sample":[158],"variance":[159],"equals":[160],"dataset":[161],"variance.":[162],"By":[163],"contrast,":[164],"DVFM":[165,194],"achieves":[166],"same":[168],"goal":[169],"without":[170],"assumption,":[172],"but":[173],"it":[174],"could":[175],"in":[177],"larger":[179],"size.":[181],"Extensive":[182],"experiments":[183],"carried":[185],"out":[186],"results":[189],"show":[190],"both":[196],"effective.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}