{"id":"https://openalex.org/W2776754263","doi":"https://doi.org/10.1186/s40537-017-0109-0","title":"A clustering algorithm for multivariate data streams with correlated components","display_name":"A clustering algorithm for multivariate data streams with correlated components","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2776754263","doi":"https://doi.org/10.1186/s40537-017-0109-0","mag":"2776754263"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-017-0109-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0109-0","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0109-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0109-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Giacomo Aletti","orcid":null},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giacomo Aletti","raw_affiliation_strings":["Department of Environmental Science and Policy & ADAMSS Center, Universit\u00e0 degli Studi di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Science and Policy & ADAMSS Center, Universit\u00e0 degli Studi di Milano, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alessandra Micheletti","orcid":"https://orcid.org/0000-0002-5369-5657"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandra Micheletti","raw_affiliation_strings":["Department of Environmental Science and Policy & ADAMSS Center, Universit\u00e0 degli Studi di Milano, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5369-5657","affiliations":[{"raw_affiliation_string":"Department of Environmental Science and Policy & ADAMSS Center, Universit\u00e0 degli Studi di Milano, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189158943"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":1.1915,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85152784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8216000199317932,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8216000199317932,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.03449999913573265,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.01759999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7278000116348267},{"id":"https://openalex.org/keywords/mahalanobis-distance","display_name":"Mahalanobis distance","score":0.6568999886512756},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5235000252723694},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.45010000467300415},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.41620001196861267},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.38350000977516174},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.3833000063896179},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7278000116348267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895999908447266},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5231000185012817},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.28940001130104065},{"id":"https://openalex.org/C137250428","wikidata":"https://www.wikidata.org/wiki/Q5178897","display_name":"Covariance function","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2669000029563904},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.26579999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-017-0109-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0109-0","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0109-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1707.01199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01199","pdf_url":"https://arxiv.org/pdf/1707.01199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:air.unimi.it:2434/541307","is_oa":true,"landing_page_url":"http://hdl.handle.net/2434/541307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:1809cfc236b4453b80c6936f045fb67c","is_oa":false,"landing_page_url":"https://doaj.org/article/1809cfc236b4453b80c6936f045fb67c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 4, Iss 1, Pp 1-20 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-017-0109-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0109-0","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0109-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2776754263.pdf","grobid_xml":"https://content.openalex.org/works/W2776754263.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1493454437","https://openalex.org/W1594924988","https://openalex.org/W1827518550","https://openalex.org/W1990974373","https://openalex.org/W2011430131","https://openalex.org/W2032783896","https://openalex.org/W2056921971","https://openalex.org/W2118250025","https://openalex.org/W2126626732","https://openalex.org/W2505774719","https://openalex.org/W4230065791","https://openalex.org/W4231029117","https://openalex.org/W4235539094","https://openalex.org/W4300601563"],"related_works":[],"abstract_inverted_index":{"Common":[0],"clustering":[1,53],"algorithms":[2,29,54,68],"require":[3],"multiple":[4],"scans":[5],"of":[6,39,74,91,95,108,177,183,218],"all":[7],"the":[8,32,37,86,105,109,114,129,195,199,206,210,215,221],"data":[9,21,41,79,143,146,180,184,207],"to":[10,30,36,55,141,193,209],"achieve":[11],"convergence,":[12],"and":[13,88,120,150,197],"this":[14,126],"is":[15,127,191],"prohibitive":[16],"when":[17],"large":[18,56],"databases,":[19],"with":[20,145,154,187],"arriving":[22],"in":[23,44,51,66,131,175],"streams,":[24,144],"must":[25],"be":[26],"processed.":[27],"Some":[28],"extend":[31],"popular":[33],"K-means":[34],"method":[35],"analysis":[38],"streaming":[40],"are":[42,118,161],"present":[43],"literature":[45],"since":[46],"1998":[47],"(Bradley":[48],"et":[49,64],"al.":[50,65],"Scaling":[52],"databases.":[57],"In:":[58,72],"KDD.":[59],"p.":[60,81],"9\u201315,":[61],"1998;":[62],"O\u2019Callaghan":[63],"Streaming-data":[67],"for":[69,205],"high-quality":[70],"clustering.":[71],"Proceedings":[73],"IEEE":[75],"international":[76],"conference":[77],"on":[78,85],"engineering.":[80],"685,":[82],"2001),":[83],"based":[84],"memorization":[87],"recursive":[89],"update":[90],"a":[92,138,178],"small":[93,188],"number":[94,217],"summary":[96],"statistics,":[97],"but":[98],"they":[99],"either":[100],"don\u2019t":[101],"take":[102],"into":[103],"account":[104],"specific":[106],"variability":[107],"clusters,":[110],"or":[111,182],"assume":[112],"that":[113,202],"random":[115],"vectors":[116],"which":[117,169],"processed":[119],"grouped":[121],"have":[122],"uncorrelated":[123],"components.":[124],"Unfortunately":[125],"not":[128],"case":[130],"many":[132],"practical":[133],"situations.":[134],"We":[135,212],"here":[136],"propose":[137],"new":[139],"algorithm":[140],"process":[142],"having":[147,185],"correlated":[148],"components":[149,186],"coming":[151],"from":[152,220],"clusters":[153,219],"different":[155],"covariance":[156,159],"matrices.":[157],"Such":[158],"matrices":[160,196],"estimated":[162],"via":[163],"an":[164],"optimal":[165],"double":[166],"shrinkage":[167],"method,":[168],"provides":[170],"positive":[171],"definite":[172],"estimates":[173],"even":[174],"presence":[176],"few":[179],"points,":[181],"variance.":[189],"This":[190],"needed":[192],"invert":[194],"compute":[198],"Mahalanobis":[200],"distances":[201],"we":[203],"use":[204],"assignment":[208],"clusters.":[211],"also":[213],"estimate":[214],"total":[216],"data.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2018-01-05T00:00:00"}