{"id":"https://openalex.org/W4254239782","doi":"https://doi.org/10.1109/ipdps.2006.1639315","title":"Design and analysis of a multi-dimensional data sampling service for large scale data analysis applications","display_name":"Design and analysis of a multi-dimensional data sampling service for large scale data analysis applications","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W4254239782","doi":"https://doi.org/10.1109/ipdps.2006.1639315"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"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":"Xi Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055193073","display_name":"T. Kurc","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":"T. Kurc","raw_affiliation_strings":["Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068734352","display_name":"J. 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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100430876"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.636,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71683597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9 pp.","last_page":"9 pp."},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9984999895095825,"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":0.8262729644775391},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7784428000450134},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6473126411437988},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.633970320224762},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6162887811660767},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5843716859817505},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5321838855743408},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47926661372184753},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4334307909011841},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37381577491760254},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26468566060066223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08599817752838135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262729644775391},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7784428000450134},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6473126411437988},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.633970320224762},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6162887811660767},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5843716859817505},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5321838855743408},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47926661372184753},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4334307909011841},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37381577491760254},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26468566060066223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08599817752838135},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2006.1639315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1529669441","https://openalex.org/W1548168538","https://openalex.org/W1595687138","https://openalex.org/W1892999956","https://openalex.org/W1979605853","https://openalex.org/W1994326354","https://openalex.org/W1997020216","https://openalex.org/W2015190123","https://openalex.org/W2022942700","https://openalex.org/W2041989747","https://openalex.org/W2119885577","https://openalex.org/W2151367350","https://openalex.org/W2158242568","https://openalex.org/W2159772324","https://openalex.org/W2160741692","https://openalex.org/W2170212104","https://openalex.org/W4292023222","https://openalex.org/W4300068876","https://openalex.org/W6682964993","https://openalex.org/W6685090917"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2022275305","https://openalex.org/W2389214306","https://openalex.org/W2369125128","https://openalex.org/W2571250724"],"abstract_inverted_index":{"Sampling":[0],"is":[1,70],"a":[2,24,42,85,92],"widely":[3],"used":[4],"technique":[5],"to":[6,54,106,121],"increase":[7],"efficiency":[8,127],"in":[9,52],"database":[10],"and":[11,128],"data":[12,62],"mining":[13],"applications":[14],"operating":[15],"on":[16,35,41,73],"large":[17,37,82],"dataset.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"present":[23],"scalable":[25],"sampling":[26],"implementation":[27,69],"that":[28,116],"supports":[29],"efficient,":[30],"multi-dimensional":[31],"spatio-temporal":[32,95],"sample":[33],"generation":[34],"dynamic,":[36],"scale":[38],"datasets":[39,83],"stored":[40],"storage":[43],"cluster":[44],"The":[45,112],"proposed":[46],"algorithm":[47],"leverages":[48],"Hilbert":[49],"space-filling":[50],"curves":[51],"order":[53,59,123],"provide":[55],"an":[56,122],"approximate":[57],"linear":[58],"of":[60,75,101,124],"multidimensional":[61],"while":[63],"maintaining":[64],"spatial":[65],"locality.":[66],"This":[67],"new":[68],"then":[71],"bootstrapped":[72],"top":[74],"our":[76,102,117],"previous":[77],"implementation,":[78],"which":[79],"efficiently":[80],"samples":[81],"along":[84],"single":[86],"dimension":[87],"(e.g.,":[88],"time),":[89],"thereby":[90],"realizing":[91],"service":[93],"for":[94],"sampling.":[96],"We":[97],"evaluate":[98],"the":[99,107],"performance":[100],"approach":[103,118],"comparing":[104],"it":[105],"popular":[108],"R-tree":[109],"based":[110],"technique.":[111],"experimental":[113],"results":[114],"show":[115],"achieves":[119],"up":[120],"magnitude":[125],"higher":[126],"scalability":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}