{"id":"https://openalex.org/W2067027768","doi":"https://doi.org/10.1145/2623330.2623695","title":"Batch discovery of recurring rare classes toward identifying anomalous samples","display_name":"Batch discovery of recurring rare classes toward identifying anomalous samples","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2067027768","doi":"https://doi.org/10.1145/2623330.2623695","mag":"2067027768","pmid":"https://pubmed.ncbi.nlm.nih.gov/36844382"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.indianapolis.iu.edu/bitstreams/3fba99a7-a7ec-4e5c-a2ed-684d8fdb89a2/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067612292","display_name":"Murat D\u00fcndar","orcid":"https://orcid.org/0000-0001-5752-468X"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Dundar","raw_affiliation_strings":["IUPUI, Indianapolis, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IUPUI, Indianapolis, IN, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031733532","display_name":"Halid Ziya Yerebakan","orcid":"https://orcid.org/0000-0003-4735-0289"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Halid Ziya Yerebakan","raw_affiliation_strings":["IUPUI, Indianapolis, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IUPUI, Indianapolis, IN, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034713503","display_name":"Bartek Rajwa","orcid":"https://orcid.org/0000-0001-7540-8236"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bartek Rajwa","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2069,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47606392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2014","issue":null,"first_page":"223","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9997000098228455,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9997000098228455,"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/T10885","display_name":"Gene expression and cancer classification","score":0.968500018119812,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9670000076293945,"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/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.7089838981628418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6679982542991638},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.5425252914428711},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5239063501358032},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5071942806243896},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5041385889053345},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4760061204433441},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.46446412801742554},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4446825087070465},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.43682026863098145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4269687533378601},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42136508226394653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30102306604385376},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.27326691150665283},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.23065954446792603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22812345623970032}],"concepts":[{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.7089838981628418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6679982542991638},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.5425252914428711},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5239063501358032},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5071942806243896},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5041385889053345},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4760061204433441},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.46446412801742554},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4446825087070465},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.43682026863098145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4269687533378601},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42136508226394653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30102306604385376},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.27326691150665283},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.23065954446792603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22812345623970032},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2623330.2623695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmid:36844382","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36844382","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","raw_type":null},{"id":"pmh:oai:scholarworks.indianapolis.iu.edu:1805/36608","is_oa":true,"landing_page_url":"https://hdl.handle.net/1805/36608","pdf_url":"https://scholarworks.indianapolis.iu.edu/bitstreams/3fba99a7-a7ec-4e5c-a2ed-684d8fdb89a2/download","source":{"id":"https://openalex.org/S4306400987","display_name":"IUScholarWorks (Indiana University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I592451","host_organization_name":"Indiana University","host_organization_lineage":["https://openalex.org/I592451"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PMC","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9963292","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9963292","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:scholarworks.indianapolis.iu.edu:1805/36608","is_oa":true,"landing_page_url":"https://hdl.handle.net/1805/36608","pdf_url":"https://scholarworks.indianapolis.iu.edu/bitstreams/3fba99a7-a7ec-4e5c-a2ed-684d8fdb89a2/download","source":{"id":"https://openalex.org/S4306400987","display_name":"IUScholarWorks (Indiana University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I592451","host_organization_name":"Indiana University","host_organization_lineage":["https://openalex.org/I592451"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PMC","raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1099308596","display_name":"Automated spectral data transformations and analysis pipeline for high-throughput","funder_award_id":"5r21eb015707-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4977979725","display_name":null,"funder_award_id":"5R21EB015707","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"},{"id":"https://openalex.org/G5186566204","display_name":"CAREER: Self-adjusting Models as a New Direction in Machine Learning","funder_award_id":"1252648","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6749684980","display_name":null,"funder_award_id":"R21 EB015707","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"},{"id":"https://openalex.org/G7314943721","display_name":null,"funder_award_id":"IIS-1252648","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306799","display_name":"Pharmaceutical Research and Manufacturers of America Foundation","ror":"https://ror.org/01z88k350"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2067027768.pdf","grobid_xml":"https://content.openalex.org/works/W2067027768.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1579271636","https://openalex.org/W1977859620","https://openalex.org/W2014467537","https://openalex.org/W2030962165","https://openalex.org/W2072169887","https://openalex.org/W2083404883","https://openalex.org/W2097446839","https://openalex.org/W2112493011","https://openalex.org/W2118871014","https://openalex.org/W2136327423","https://openalex.org/W2141642784","https://openalex.org/W2158266063","https://openalex.org/W2164903478","https://openalex.org/W2488678869","https://openalex.org/W2604272474","https://openalex.org/W4248463836"],"related_works":["https://openalex.org/W2517377710","https://openalex.org/W2088304067","https://openalex.org/W2939843948","https://openalex.org/W2162057505","https://openalex.org/W2416695473","https://openalex.org/W4385270375","https://openalex.org/W1882901045","https://openalex.org/W1480761103","https://openalex.org/W2060556149","https://openalex.org/W1966862482"],"abstract_inverted_index":{"We":[0,23,53,88,104],"present":[1],"a":[2,13,50,61,73,113],"clustering":[3],"algorithm":[4,138],"for":[5,80,93],"discovering":[6],"rare":[7,121],"yet":[8],"significant":[9],"recurring":[10],"classes":[11,85],"across":[12,56,76,86],"batch":[14],"of":[15,20,32,44,84,108,135],"samples":[16,58,77],"in":[17,49],"the":[18,41,106,109,136,142,145],"presence":[19],"random":[21],"effects.":[22],"model":[24],"each":[25,38],"sample":[26],"data":[27,116],"by":[28,59],"an":[29],"infinite":[30],"mixture":[31],"Dirichlet-process":[33],"Gaussian-mixture":[34],"models":[35],"(DPMs)":[36],"with":[37],"DPM":[39],"representing":[40],"noisy":[42],"realization":[43],"its":[45],"corresponding":[46],"class":[47,102],"distribution":[48],"given":[51],"sample.":[52],"introduce":[54],"dependencies":[55],"multiple":[57],"placing":[60],"global":[62],"Dirichlet":[63],"process":[64],"prior":[65,71],"over":[66],"individual":[67],"DPMs.":[68],"This":[69],"hierarchical":[70],"introduces":[72],"sharing":[74],"mechanism":[75],"and":[78,99,124],"allows":[79],"identifying":[81],"local":[82,97],"realizations":[83],"samples.":[87],"use":[89],"collapsed":[90],"Gibbs":[91],"sampler":[92],"inference":[94],"to":[95],"recover":[96],"DPMs":[98],"identify":[100],"their":[101],"associations.":[103],"demonstrate":[105],"utility":[107],"proposed":[110,137],"algorithm,":[111],"processing":[112],"flow":[114],"cytometry":[115],"set":[117],"containing":[118],"two":[119],"extremely":[120],"cell":[122],"populations,":[123],"report":[125],"results":[126],"that":[127],"significantly":[128],"outperform":[129],"competing":[130],"techniques.":[131],"The":[132],"source":[133],"code":[134],"is":[139],"available":[140],"on":[141],"web":[143],"via":[144],"link:":[146],"http://cs.iupui.edu/~dundar/aspire.htm.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}