{"id":"https://openalex.org/W2160741692","doi":"https://doi.org/10.1145/1088149.1088162","title":"Design of a next generation sampling service for large scale data analysis applications","display_name":"Design of a next generation sampling service for large scale data analysis applications","publication_year":2005,"publication_date":"2005-06-20","ids":{"openalex":"https://openalex.org/W2160741692","doi":"https://doi.org/10.1145/1088149.1088162","mag":"2160741692"},"language":"en","primary_location":{"id":"doi:10.1145/1088149.1088162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088149.1088162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th annual international conference on Supercomputing","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/A5101758548","display_name":"Huamin Wang","orcid":"https://orcid.org/0000-0002-8153-2337"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"H. Wang","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755351","display_name":"Srinivasan Parthasarathy","orcid":"https://orcid.org/0000-0002-6062-6449"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Parthasarathy","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043552468","display_name":"Amol Ghoting","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Ghoting","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059512590","display_name":"Shirish Tatikonda","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Tatikonda","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068014041","display_name":"Gregory Buehrer","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Buehrer","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037383891","display_name":"Tahsin Kur\u00e7","orcid":"https://orcid.org/0000-0001-9237-4306"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Kurc","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109212347","display_name":"Joel Saltz","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Saltz","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101758548"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.0943,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83072304,"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":"91","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8748459219932556},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6926543116569519},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.570315420627594},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5264109969139099},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.522862434387207},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47357046604156494},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4504358768463135},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.41958943009376526},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4123949706554413},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33633533120155334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748459219932556},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6926543116569519},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.570315420627594},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5264109969139099},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.522862434387207},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47357046604156494},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4504358768463135},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.41958943009376526},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4123949706554413},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33633533120155334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1088149.1088162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088149.1088162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.252","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~ghoting/papers/wang-ics05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1483679765","https://openalex.org/W1489843519","https://openalex.org/W1529669441","https://openalex.org/W1540405939","https://openalex.org/W1548168538","https://openalex.org/W1555576437","https://openalex.org/W1582211363","https://openalex.org/W1595687138","https://openalex.org/W1597561788","https://openalex.org/W1601142477","https://openalex.org/W1605688901","https://openalex.org/W1788554450","https://openalex.org/W1847303236","https://openalex.org/W1968526517","https://openalex.org/W1994326354","https://openalex.org/W1997020216","https://openalex.org/W2001474264","https://openalex.org/W2022942700","https://openalex.org/W2041989747","https://openalex.org/W2056985101","https://openalex.org/W2068411009","https://openalex.org/W2090683636","https://openalex.org/W2091122332","https://openalex.org/W2098634622","https://openalex.org/W2110298485","https://openalex.org/W2119885577","https://openalex.org/W2125412267","https://openalex.org/W2138860061","https://openalex.org/W2140190241","https://openalex.org/W2147191819","https://openalex.org/W2147864479","https://openalex.org/W2151367350","https://openalex.org/W2158242568","https://openalex.org/W2166333076","https://openalex.org/W2752885492","https://openalex.org/W4285719527","https://openalex.org/W6628973722","https://openalex.org/W6632919194","https://openalex.org/W6676560735","https://openalex.org/W6678833645","https://openalex.org/W6680704940"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W156620619","https://openalex.org/W2616249226","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W2997844990","https://openalex.org/W1598221548","https://openalex.org/W2081850291","https://openalex.org/W1963695443"],"abstract_inverted_index":{"Advances":[0],"in":[1,9,59,104,126],"data":[2,14,21,36,64,74,110,156,178],"collection":[3],"and":[4,11,20,193,200,213],"storage":[5],"technologies":[6],"have":[7],"resulted":[8],"large":[10],"dynamically":[12],"growing":[13],"sets":[15,37],"at":[16],"many":[17],"organizations.":[18],"Database":[19],"mining":[22,75,179],"researchers":[23],"often":[24,46,57],"use":[25],"sampling":[26,80,202],"with":[27,38,123,154,224],"great":[28],"effect":[29],"to":[30,41,216],"scale":[31],"up":[32,215],"performance":[33],"on":[34],"these":[35],"small":[39],"cost":[40,49,55,85,124],"accuracy.":[42],"However,":[43],"existing":[44],"techniques":[45],"ignore":[47],"the":[48,60,63,67,92,105,127,130],"of":[50,62,94,107,129,138,219],"computing":[51],"a":[52,102,108,116,174,190],"sample.":[53,131],"This":[54],"is":[56,70],"linear":[58,125],"size":[61,128],"set,":[65],"not":[66],"sample,":[68],"which":[69,196],"expensive.":[71],"Furthermore,":[72],"for":[73,150,168,177],"applications":[76],"that":[77,119,162,206],"leverage":[78],"progressive":[79,201],"or":[81],"bootstrapping-based":[82],"techniques,":[83],"this":[84,98,139],"can":[86],"be":[87],"prohibitive,":[88],"since":[89],"they":[90],"require":[91],"generation":[93,122],"multiple":[95],"samples.To":[96],"address":[97],"problem,":[99],"we":[100,114],"present":[101,134],"solution":[103,142],"context":[106],"state-of-the-art":[109],"analysis":[111,194],"center.":[112],"Specifically,":[113],"propose":[115],"scalable":[117],"service":[118,176],"supports":[120,163],"sample":[121],"We":[132,158,181,204],"then":[133,182],"an":[135,160,217],"efficient":[136],"parallelization":[137],"service.":[140],"Our":[141],"leverages":[143],"high":[144],"speed":[145],"interconnects":[146],"(e.g.":[147],"Myrinet,":[148],"Infini-band)":[149],"parallel":[151],"I/O":[152],"operations":[153],"pipelined":[155],"transfers.":[157],"export":[159],"interface":[161],"both":[164,198],"ad-hoc":[165],"SQL-like":[166],"querying":[167],"database":[169,199],"applications,":[170],"as":[171,173],"well":[172],"stand-alone":[175],"applications.":[180],"evaluate":[183],"our":[184,207],"work":[185],"using":[186],"queries":[187],"abstracted":[188],"from":[189],"network":[191],"monitoring":[192],"application,":[195],"uses":[197],"queries.":[203],"demonstrate":[205],"implementation":[208],"achieves":[209],"good":[210],"load":[211],"balance":[212],"realizes":[214],"order":[218],"magnitude":[220],"speedup":[221],"when":[222],"compared":[223],"extant":[225],"approaches.":[226]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}