{"id":"https://openalex.org/W2063512404","doi":"https://doi.org/10.14778/2078324.2078327","title":"Building wavelet histograms on large data in MapReduce","display_name":"Building wavelet histograms on large data in MapReduce","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2063512404","doi":"https://doi.org/10.14778/2078324.2078327","mag":"2063512404"},"language":"en","primary_location":{"id":"doi:10.14778/2078324.2078327","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078324.2078327","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5064482744","display_name":"Jeffrey Jestes","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Jestes","raw_affiliation_strings":["University of Utah Salt Lake City, Utah","University of Utah, Salt Lake City , Utah,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City , Utah,","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009196125","display_name":"Ke Yi","orcid":"https://orcid.org/0000-0002-2178-3716"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yi","raw_affiliation_strings":["HKUST, Hong Kong, China","[HKUST, Hong Kong, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"[HKUST, Hong Kong, China]","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feifei Li","raw_affiliation_strings":["University of Utah Salt Lake City, Utah","University of Utah, Salt Lake City , Utah,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City , Utah,","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9033,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96381798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"5","issue":"2","first_page":"109","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9897000193595886,"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":0.9897000193595886,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.8119742274284363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8104674816131592},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7394791841506958},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7095381021499634},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6282095909118652},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5249412059783936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21148157119750977},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1644171178340912},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1444213092327118}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8119742274284363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104674816131592},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7394791841506958},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7095381021499634},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6282095909118652},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5249412059783936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21148157119750977},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1644171178340912},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1444213092327118}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.14778/2078324.2078327","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078324.2078327","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.227.5948","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.227.5948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vldb.org/pvldb/vol5/p109_jeffreyjestes_vldb2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.3064","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.3064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utah.edu/%7Elifeifei/papers/mrhistogram.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.601","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utah.edu/~lifeifei/papers/mrhistogram.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.747.991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.747.991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1110.6649.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-57434","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-57434","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1483763945","https://openalex.org/W1488441684","https://openalex.org/W1489255272","https://openalex.org/W1544095808","https://openalex.org/W1822348499","https://openalex.org/W1976597724","https://openalex.org/W2010279913","https://openalex.org/W2018989507","https://openalex.org/W2021850646","https://openalex.org/W2029538739","https://openalex.org/W2035543557","https://openalex.org/W2052331661","https://openalex.org/W2064379477","https://openalex.org/W2075620950","https://openalex.org/W2088698696","https://openalex.org/W2089419727","https://openalex.org/W2098935637","https://openalex.org/W2106163100","https://openalex.org/W2106834095","https://openalex.org/W2110086534","https://openalex.org/W2110557355","https://openalex.org/W2114303224","https://openalex.org/W2116400826","https://openalex.org/W2119400430","https://openalex.org/W2122465391","https://openalex.org/W2122731071","https://openalex.org/W2125775320","https://openalex.org/W2131126403","https://openalex.org/W2135417552","https://openalex.org/W2142031898","https://openalex.org/W2146635036","https://openalex.org/W2151930506","https://openalex.org/W2153511931","https://openalex.org/W2162139064","https://openalex.org/W2171903035","https://openalex.org/W2666600683","https://openalex.org/W2912802084","https://openalex.org/W4238284510","https://openalex.org/W6629296720","https://openalex.org/W6638337754","https://openalex.org/W6654966671","https://openalex.org/W6663908676","https://openalex.org/W6677022862","https://openalex.org/W6682829892","https://openalex.org/W6758383543","https://openalex.org/W7072006003"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W3151146928"],"abstract_inverted_index":{"MapReduce":[0,23,110],"is":[1,32,55],"becoming":[2],"the":[3,52,58,68,82,85],"de":[4],"facto":[5],"framework":[6],"for":[7,48,105,122],"storing":[8],"and":[9,19,46,51,92,102,125,129,141,161],"processing":[10],"massive":[11],"data,":[12,50],"due":[13],"to":[14,42,109,143,165],"its":[15],"excellent":[16],"scalability,":[17],"reliability,":[18],"elasticity.":[20],"In":[21,63],"many":[22],"applications,":[24],"obtaining":[25],"a":[26,151],"compact":[27],"accurate":[28],"summary":[29],"of":[30,57,70,84,99,155,167,175],"data":[31,36],"essential.":[33],"Among":[34],"various":[35],"summarization":[37],"tools,":[38],"histograms":[39,73,108,128],"have":[40],"proven":[41],"be":[43],"particularly":[44],"important":[45],"useful":[47],"summarizing":[49],"wavelet":[53,72,107,127],"histogram":[54],"one":[56],"most":[59],"widely":[60],"used":[61],"histograms.":[62],"this":[64],"paper,":[65],"we":[66,118],"investigate":[67],"problem":[69],"building":[71,106],"efficiently":[74],"on":[75],"large":[76,159],"datasets":[77],"in":[78,133,139,150],"MapReduce.":[79,134],"We":[80,95,135],"measure":[81],"efficiency":[83],"algorithms":[86,121],"by":[87,180],"both":[88],"end-to-end":[89],"running":[90],"time":[91],"communication":[93],"cost.":[94],"demonstrate":[96],"straightforward":[97],"adaptations":[98],"existing":[100],"exact":[101,124],"approximate":[103,126],"methods":[104],"clusters":[111],"are":[112],"highly":[113],"inefficient.":[114],"To":[115],"that":[116],"end,":[117],"design":[119],"new":[120,182],"computing":[123],"discuss":[130],"their":[131],"implementation":[132],"illustrate":[136],"our":[137,181],"techniques":[138],"Hadoop,":[140],"compare":[142],"baseline":[144],"solutions":[145],"with":[146],"extensive":[147],"experiments":[148],"performed":[149],"heterogeneous":[152],"Hadoop":[153],"cluster":[154],"16":[156],"nodes,":[157],"using":[158],"real":[160],"synthetic":[162],"datasets,":[163],"up":[164],"hundreds":[166],"gigabytes.":[168],"The":[169],"results":[170],"suggest":[171],"significant":[172],"(often":[173],"orders":[174],"magnitude)":[176],"performance":[177],"improvement":[178],"achieved":[179],"algorithms.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}