{"id":"https://openalex.org/W4394748744","doi":"https://doi.org/10.1080/10618600.2024.2341896","title":"Data Nuggets: A Method for Reducing Big Data While Preserving Data Structure","display_name":"Data Nuggets: A Method for Reducing Big Data While Preserving Data Structure","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394748744","doi":"https://doi.org/10.1080/10618600.2024.2341896"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2024.2341896","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2341896","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","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/A5024904681","display_name":"Traymon Beavers","orcid":"https://orcid.org/0000-0002-7549-6587"},"institutions":[{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]},{"id":"https://openalex.org/I4210151386","display_name":"Janssen (United States)","ror":"https://ror.org/05af73403","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I4210151386"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Traymon E. Beavers","raw_affiliation_strings":["Janssen R&D","Janssen R&D, Spring House, PA"],"raw_orcid":"https://orcid.org/0000-0002-7549-6587","affiliations":[{"raw_affiliation_string":"Janssen R&D","institution_ids":["https://openalex.org/I137982388"]},{"raw_affiliation_string":"Janssen R&D, Spring House, PA","institution_ids":["https://openalex.org/I4210151386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622643","display_name":"Ge Cheng","orcid":"https://orcid.org/0000-0002-4342-8029"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Ge Cheng","raw_affiliation_strings":["Department of Statistics, Rutgers University","Department of Statistics, Rutgers University, New Brunswick, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Department of Statistics, Rutgers University, New Brunswick, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033556826","display_name":"Yajie Duan","orcid":"https://orcid.org/0000-0001-5833-9056"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Yajie Duan","raw_affiliation_strings":["Department of Statistics, Rutgers University","Department of Statistics, Rutgers University, New Brunswick, NJ"],"raw_orcid":"https://orcid.org/0000-0001-5833-9056","affiliations":[{"raw_affiliation_string":"Department of Statistics, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Department of Statistics, Rutgers University, New Brunswick, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432250","display_name":"Javier Cabrera","orcid":"https://orcid.org/0009-0000-9771-0786"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Javier Cabrera","raw_affiliation_strings":["Department of Statistics, Rutgers University","Department of Statistics, Rutgers University, New Brunswick, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Department of Statistics, Rutgers University, New Brunswick, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086074256","display_name":"Mariusz Lubomirski","orcid":null},"institutions":[{"id":"https://openalex.org/I1320553840","display_name":"Amgen (United States)","ror":"https://ror.org/03g03ge92","country_code":"US","type":"company","lineage":["https://openalex.org/I1320553840"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariusz Lubomirski","raw_affiliation_strings":["Amgen Pharmaceutical","Amgen Pharmaceutical, Thousand Oaks, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amgen Pharmaceutical","institution_ids":["https://openalex.org/I1320553840"]},{"raw_affiliation_string":"Amgen Pharmaceutical, Thousand Oaks, CA","institution_ids":["https://openalex.org/I1320553840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045560880","display_name":"Dhammika Amaratunga","orcid":"https://orcid.org/0000-0001-8293-5042"},"institutions":[{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]},{"id":"https://openalex.org/I4210151386","display_name":"Janssen (United States)","ror":"https://ror.org/05af73403","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I4210151386"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Dhammika Amaratunga","raw_affiliation_strings":["Janssen R&D","Janssen R&D, Spring House, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Janssen R&D","institution_ids":["https://openalex.org/I137982388"]},{"raw_affiliation_string":"Janssen R&D, Spring House, PA","institution_ids":["https://openalex.org/I4210151386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076427525","display_name":"Jeffrey E. Teigler","orcid":null},"institutions":[{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]},{"id":"https://openalex.org/I4210151386","display_name":"Janssen (United States)","ror":"https://ror.org/05af73403","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I4210151386"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Jeffrey E. Teigler","raw_affiliation_strings":["Janssen R&D","Janssen R&D, Spring House, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Janssen R&D","institution_ids":["https://openalex.org/I137982388"]},{"raw_affiliation_string":"Janssen R&D, Spring House, PA","institution_ids":["https://openalex.org/I4210151386"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101432250"],"corresponding_institution_ids":["https://openalex.org/I102322142","https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":1.2119,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81575611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":"1","first_page":"330","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9825000166893005,"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":0.9825000166893005,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7718431353569031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983776688575745},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6217405200004578},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.6092547178268433},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.605968713760376},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5133189558982849},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.45611071586608887},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44797438383102417},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4413042962551117},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.41280800104141235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2807141840457916}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7718431353569031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983776688575745},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6217405200004578},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.6092547178268433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.605968713760376},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5133189558982849},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.45611071586608887},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44797438383102417},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4413042962551117},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.41280800104141235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2807141840457916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10618600.2024.2341896","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2341896","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4672630110","display_name":null,"funder_award_id":"R01-HL150065","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W79970639","https://openalex.org/W1540089290","https://openalex.org/W1596717185","https://openalex.org/W1977556410","https://openalex.org/W1979540296","https://openalex.org/W2037178322","https://openalex.org/W2042383323","https://openalex.org/W2044842931","https://openalex.org/W2045964207","https://openalex.org/W2067563600","https://openalex.org/W2082612735","https://openalex.org/W2083252561","https://openalex.org/W2127218421","https://openalex.org/W2141245797","https://openalex.org/W2150593711","https://openalex.org/W2188049077","https://openalex.org/W2250495309","https://openalex.org/W2299467264","https://openalex.org/W2546803629","https://openalex.org/W2582743722","https://openalex.org/W2950017555","https://openalex.org/W3108892885","https://openalex.org/W3134769245","https://openalex.org/W4206341000","https://openalex.org/W4231029117","https://openalex.org/W4238414465","https://openalex.org/W4249187532","https://openalex.org/W4254687493","https://openalex.org/W6644682428"],"related_works":["https://openalex.org/W2579148721","https://openalex.org/W4387893611","https://openalex.org/W2347335694","https://openalex.org/W2091056927","https://openalex.org/W2067407580","https://openalex.org/W4317486777","https://openalex.org/W4389669152","https://openalex.org/W2038514069","https://openalex.org/W1967233468","https://openalex.org/W2009181529"],"abstract_inverted_index":{"Big":[0],"data,":[1,128],"with":[2],"N\u00d7P":[3],"dimension":[4],"where":[5],"N":[6],"is":[7,77,90,101],"extremely":[8],"large,":[9],"has":[10],"created":[11],"new":[12,108],"challenges":[13],"for":[14,38,198,203],"data":[15,56,138,167,177],"analysis,":[16],"particularly":[17,97],"in":[18,155],"the":[19,74,85,92,95,99,111,163,166,174],"realm":[20],"of":[21,25,66,94,113,125,127,165,176,183],"creating":[22],"meaningful":[23],"clusters":[24],"data.":[26],"Clustering":[27],"techniques,":[28],"such":[29,148],"as":[30,149],"K-means":[31,196],"or":[32,60],"hierarchical":[33],"clustering":[34,75,154,197],"are":[35,48,140,206],"popular":[36],"methods":[37,47,147],"performing":[39],"exploratory":[40,181],"analysis":[41,152,182],"on":[42],"large":[43,119],"datasets.":[44],"Unfortunately,":[45],"these":[46],"not":[49,102],"always":[50],"possible":[51],"to":[52,54,58,79,179],"apply":[53,173],"big":[55],"due":[57],"memory":[59],"time":[61],"constraints":[62],"generated":[63],"by":[64],"calculations":[65],"order":[67],"P*N(N\u22121)2.":[68],"To":[69],"circumvent":[70],"this":[71,204],"problem,":[72],"typically":[73],"technique":[76],"applied":[78],"a":[80,88,107,118,122,131,156,184],"random":[81],"sample":[82],"drawn":[83],"from":[84],"dataset;":[86],"however,":[87],"weakness":[89],"that":[91,145],"structure":[93],"dataset,":[96],"at":[98],"edges,":[100],"necessarily":[103],"maintained.":[104],"We":[105,161],"propose":[106],"solution":[109],"through":[110],"concept":[112],"\u201cdata":[114],"nuggets\u201d,":[115],"which":[116],"reduces":[117],"dataset":[120,187],"into":[121,143],"small":[123],"collection":[124],"nuggets":[126,139,168,178],"each":[129],"containing":[130,188],"center,":[132],"weight,":[133],"and":[134,153,172,195],"scale":[135],"parameter.":[136],"The":[137],"then":[141],"input":[142],"algorithms":[144],"compute":[146],"principal":[150],"components":[151],"more":[157],"computationally":[158],"efficient":[159],"manner.":[160],"show":[162],"consistency":[164],"based":[169],"covariance":[170],"estimator":[171],"methodology":[175],"perform":[180],"flow":[185],"cytometry":[186],"over":[189],"one":[190],"million":[191],"observations":[192],"using":[193],"PCA":[194],"weighted":[199],"observations.":[200],"Supplementary":[201],"materials":[202],"article":[205],"available":[207],"online.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}