{"id":"https://openalex.org/W2002431676","doi":"https://doi.org/10.1109/bigdata.2013.6691587","title":"Scientific discovery through weighted sampling","display_name":"Scientific discovery through weighted sampling","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2002431676","doi":"https://doi.org/10.1109/bigdata.2013.6691587","mag":"2002431676"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5062962519","display_name":"Lefteris Sidirourgos","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Lefteris Sidirourgos","raw_affiliation_strings":["CWI Amsterdam, Database Architectures, The Netherlands","Database Archit., CWI, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"CWI Amsterdam, Database Architectures, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Database Archit., CWI, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108572275","display_name":"Martin Kersten","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martin Kersten","raw_affiliation_strings":["CWI Amsterdam, Database Architectures, The Netherlands","Database Archit., CWI, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"CWI Amsterdam, Database Architectures, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Database Archit., CWI, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058712681","display_name":"Peter Boncz","orcid":"https://orcid.org/0000-0001-6256-0140"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter Boncz","raw_affiliation_strings":["CWI Amsterdam, Database Architectures, The Netherlands","Database Archit., CWI, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"CWI Amsterdam, Database Architectures, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Database Archit., CWI, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062962519"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":null,"apc_paid":null,"fwci":1.0874,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79481664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"300","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9952999949455261,"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/T11719","display_name":"Data Quality and Management","score":0.9591000080108643,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673729658126831},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.697074294090271},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6317453980445862},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.5620288252830505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4921645522117615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4815542995929718},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47428709268569946},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4624856114387512},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4574863016605377},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.4556141793727875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11542323231697083},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09860488772392273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673729658126831},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.697074294090271},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6317453980445862},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.5620288252830505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4921645522117615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4815542995929718},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47428709268569946},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4624856114387512},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4574863016605377},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.4556141793727875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11542323231697083},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09860488772392273},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2013.6691587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1505808391","https://openalex.org/W1565225458","https://openalex.org/W1581547316","https://openalex.org/W1592355944","https://openalex.org/W1964857063","https://openalex.org/W1992023276","https://openalex.org/W1993482412","https://openalex.org/W2020584928","https://openalex.org/W2037701287","https://openalex.org/W2071989194","https://openalex.org/W2117348908","https://openalex.org/W2173213060","https://openalex.org/W2199389590","https://openalex.org/W2284530523","https://openalex.org/W2620485168","https://openalex.org/W2752908210","https://openalex.org/W4241185933","https://openalex.org/W4250212406","https://openalex.org/W6630164444","https://openalex.org/W6634880912","https://openalex.org/W6635371082","https://openalex.org/W6677704861","https://openalex.org/W6696216207","https://openalex.org/W7043289394"],"related_works":["https://openalex.org/W2038693912","https://openalex.org/W1991602789","https://openalex.org/W1582396021","https://openalex.org/W1988359706","https://openalex.org/W312558119","https://openalex.org/W4210985407","https://openalex.org/W2335441444","https://openalex.org/W138014004","https://openalex.org/W2075598034","https://openalex.org/W2984441180"],"abstract_inverted_index":{"Scientific":[0],"discovery":[1,116],"has":[2],"shifted":[3],"from":[4,26],"being":[5,107],"an":[6,17,93],"exercise":[7],"of":[8,16,19,36,60,132,146,164,175],"theory":[9],"and":[10,38,136,159,172],"computation,":[11],"to":[12,32,55,82,95,113,119,127],"become":[13],"the":[14,61,65,102,114,129,133,144,151],"exploration":[15],"ocean":[18],"observational":[20],"data.":[21],"Scientists":[22],"explore":[23],"data":[24,105,112,124],"originated":[25],"modern":[27],"scientific":[28,53,73,115,134],"instruments":[29],"in":[30],"order":[31],"discover":[33],"interesting":[34],"aspects":[35],"it":[37],"formulate":[39],"their":[40],"hypothesis.":[41,122],"Such":[42],"workloads":[43],"press":[44],"for":[45,78],"new":[46],"database":[47],"functionality.":[48],"We":[49,87,154],"aim":[50],"at":[51],"sampling":[52,91,100],"databases":[54,74],"create":[56],"many":[57],"different":[58,76,162],"impressions":[59],"data,":[62],"on":[63],"which":[64],"scientists":[66],"can":[67,137],"quickly":[68],"evaluate":[69],"exploratory":[70],"queries.":[71],"However,":[72],"introduce":[75],"challenges":[77],"sample":[79],"construction":[80],"compared":[81],"classical":[83],"business":[84],"analytical":[85],"applications.":[86],"propose":[88],"adaptive":[89],"weighted":[90,99,176],"as":[92],"alternative":[94],"uniform":[96],"sampling.":[97,177],"With":[98],"only":[101],"most":[103],"informative":[104],"is":[106,117,125],"sampled,":[108],"thus":[109],"more":[110],"relevant":[111],"available":[118],"examine":[120],"a":[121,141,170],"Relevant":[123],"considered":[126],"be":[128,138],"focal":[130],"points":[131],"search,":[135],"defined":[139],"either":[140],"priori":[142],"with":[143],"use":[145],"functions,":[147],"or":[148],"by":[149],"monitoring":[150],"query":[152,157],"workload.":[153],"study":[155],"such":[156],"workloads,":[158],"we":[160,168],"detail":[161],"families":[163],"weight":[165],"functions.":[166],"Finally,":[167],"give":[169],"quantitative":[171],"qualitative":[173],"evaluation":[174]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}