{"id":"https://openalex.org/W2570457402","doi":"https://doi.org/10.1109/icsai.2016.7811097","title":"Comparative studies of sampling for analytics on massive data","display_name":"Comparative studies of sampling for analytics on massive data","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2570457402","doi":"https://doi.org/10.1109/icsai.2016.7811097","mag":"2570457402"},"language":"en","primary_location":{"id":"doi:10.1109/icsai.2016.7811097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2016.7811097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 3rd International Conference on Systems and Informatics (ICSAI)","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/A5100342962","display_name":"Xuan Zhang","orcid":"https://orcid.org/0009-0000-8760-4381"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zhang","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2016","issue":null,"first_page":"1002","last_page":"1007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.8483721017837524},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8259161710739136},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6326780319213867},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5948078036308289},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5866183638572693},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.5284050703048706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5218633413314819},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.47138553857803345},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46881675720214844},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.4511779546737671},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4175224304199219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483721017837524},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8259161710739136},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6326780319213867},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5948078036308289},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5866183638572693},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.5284050703048706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5218633413314819},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47138553857803345},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46881675720214844},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.4511779546737671},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4175224304199219},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsai.2016.7811097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2016.7811097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 3rd International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"},{"id":"mag:2751207196","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201702241071910759","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W983082260","https://openalex.org/W1485084946","https://openalex.org/W1911008668","https://openalex.org/W1971459440","https://openalex.org/W2024562752","https://openalex.org/W2036461974","https://openalex.org/W2037701287","https://openalex.org/W2049400253","https://openalex.org/W2055748525","https://openalex.org/W2091632079","https://openalex.org/W2099378941","https://openalex.org/W2099601885","https://openalex.org/W2103012681","https://openalex.org/W2103212156","https://openalex.org/W2110363867","https://openalex.org/W2117897510","https://openalex.org/W2119885577","https://openalex.org/W2130010548","https://openalex.org/W2131975293","https://openalex.org/W2138474206","https://openalex.org/W2139276812","https://openalex.org/W2140565974","https://openalex.org/W2146774335","https://openalex.org/W2152029707","https://openalex.org/W2166619657","https://openalex.org/W2169982181","https://openalex.org/W2293019624","https://openalex.org/W2296677182","https://openalex.org/W2327088997","https://openalex.org/W3125634603","https://openalex.org/W4231580960","https://openalex.org/W4233413206","https://openalex.org/W4238584892","https://openalex.org/W4242587584","https://openalex.org/W4285719527","https://openalex.org/W4299827484","https://openalex.org/W6675146241","https://openalex.org/W6679815717","https://openalex.org/W6680704885","https://openalex.org/W6680922791"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W4245701730","https://openalex.org/W2511794504","https://openalex.org/W2911648135","https://openalex.org/W3092201768","https://openalex.org/W2886451445","https://openalex.org/W3108449883","https://openalex.org/W2551093110","https://openalex.org/W2796632413"],"abstract_inverted_index":{"Groupwise":[0],"analytics":[1,34],"on":[2,43],"big":[3,37,116],"data":[4,38,46,76,97,108,134,137],"have":[5],"been":[6],"widely":[7],"used":[8],"in":[9,19],"statistics,":[10],"computer":[11],"science,":[12],"parallel":[13],"computing":[14],"and":[15,118,122],"many":[16],"other":[17],"fields":[18],"recent":[20],"years.":[21],"At":[22],"The":[23],"same":[24],"time,":[25,51],"Aggregation":[26],"queries":[27,42,114],"is":[28,60,67],"one":[29],"of":[30,55,75,88,96,101,124],"the":[31,40,44,52,57,82,99,120,128,132],"most":[32],"important":[33],"techniques.":[35],"In":[36],"eras,":[39],"aggregation":[41,113],"ever-increasing":[45],"volumes":[47],"will":[48,105],"consumes":[49],"much":[50],"traditional":[53],"methods":[54],"traversing":[56],"entire":[58],"dataset":[59],"not":[61],"acceptable":[62],"to":[63,77,131],"users.":[64],"Data":[65],"sampling":[66,109],"a":[68,73,86,93,139,143],"technique":[69,83,129],"that":[70],"only":[71],"process":[72],"part":[74],"get":[78],"an":[79],"approximate":[80,112],"result,":[81],"can":[84],"save":[85],"lot":[87],"time":[89],"when":[90],"dealing":[91],"with":[92,98],"vast":[94],"amount":[95],"sacrifice":[100],"accuracy.":[102],"This":[103],"paper":[104],"introduce":[106],"several":[107],"algorithms":[110],"for":[111,115],"data,":[117],"analyze":[119],"shortcomings":[121],"advantages":[123],"each":[125],"methods.":[126],"Including":[127],"apply":[130],"sparse":[133],"which":[135],"meaning":[136],"has":[138],"limited":[140],"population":[141],"but":[142],"wide":[144],"range.":[145]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}