{"id":"https://openalex.org/W2566782973","doi":"https://doi.org/10.1109/dsaa.2016.40","title":"EM*: An EM Algorithm for Big Data","display_name":"EM*: An EM Algorithm for Big Data","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2566782973","doi":"https://doi.org/10.1109/dsaa.2016.40","mag":"2566782973"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa.2016.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2016.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","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/A5070970331","display_name":"Hasan Kurban","orcid":"https://orcid.org/0000-0003-3142-2866"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hasan Kurban","raw_affiliation_strings":["Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","Computer Science Department, Indiana University Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Computer Science Department, Indiana University Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090584378","display_name":"Mark Jenne","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Jenne","raw_affiliation_strings":["Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","Computer Science Department, Indiana University Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Computer Science Department, Indiana University Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081672389","display_name":"Mehmet Dalk\u0131l\u0131\u00e7","orcid":"https://orcid.org/0000-0002-0776-7365"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet M. Dalkilic","raw_affiliation_strings":["Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","Computer Science Department, Indiana University Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Indiana Univ., Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Computer Science Department, Indiana University Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070970331"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":2.5708,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9217224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9990000128746033,"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":0.9990000128746033,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9961000084877014,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.7425708770751953},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6533010005950928},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.6387729644775391},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5564271211624146},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49043509364128113},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4217776358127594},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3616141676902771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25529056787490845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14967003464698792},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.12905371189117432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425708770751953},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6533010005950928},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.6387729644775391},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5564271211624146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49043509364128113},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4217776358127594},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3616141676902771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25529056787490845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14967003464698792},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.12905371189117432},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa.2016.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2016.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","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":40,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W613321770","https://openalex.org/W1967639437","https://openalex.org/W1984536199","https://openalex.org/W1985690171","https://openalex.org/W2006685053","https://openalex.org/W2024476015","https://openalex.org/W2026450968","https://openalex.org/W2030391296","https://openalex.org/W2049633694","https://openalex.org/W2053742104","https://openalex.org/W2072634211","https://openalex.org/W2090692107","https://openalex.org/W2091276705","https://openalex.org/W2100923606","https://openalex.org/W2103139809","https://openalex.org/W2108399535","https://openalex.org/W2117853077","https://openalex.org/W2118254160","https://openalex.org/W2134199473","https://openalex.org/W2142827986","https://openalex.org/W2152977846","https://openalex.org/W2154986869","https://openalex.org/W2345596855","https://openalex.org/W2566096797","https://openalex.org/W2567948266","https://openalex.org/W3106301435","https://openalex.org/W3120740533","https://openalex.org/W3129711340","https://openalex.org/W3165241807","https://openalex.org/W4230773251","https://openalex.org/W4237209138","https://openalex.org/W4241310355","https://openalex.org/W4245883374","https://openalex.org/W4251782677","https://openalex.org/W4293311141","https://openalex.org/W6606145560","https://openalex.org/W6679743023","https://openalex.org/W6796017329","https://openalex.org/W7037644959"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W4200136508","https://openalex.org/W1556040568"],"abstract_inverted_index":{"Existing":[0],"data":[1,30,35,65,73,80,91,118],"mining":[2],"techniques,":[3],"more":[4,94],"particularly":[5],"iterative":[6],"learning":[7],"algorithms,":[8],"become":[9],"overwhelmed":[10],"with":[11,123],"big":[12],"data.":[13],"While":[14],"parallelism":[15],"is":[16,57,93,131],"an":[17],"obvious":[18],"and,":[19],"usually,":[20],"necessary":[21],"strategy,":[22],"we":[23],"observe":[24],"that":[25,67,74,81,92,127],"both":[26],"(1)":[27,71],"continually":[28],"revisiting":[29],"and":[31,84,116],"(2)":[32,85],"visiting":[33],"all":[34],"are":[36],"two":[37],"of":[38],"the":[39,87,90],"most":[40],"prominent":[41],"problems":[42],"especially":[43],"for":[44,52],"iterative,":[45],"unsupervised":[46],"algorithms":[47],"like":[48],"Expectation":[49],"Maximization":[50],"algorithm":[51,108,111],"clustering":[53],"(EM-T).":[54],"Our":[55],"strategy":[56],"to":[58,70,76,96],"embed":[59],"EM-T":[60,110],"into":[61],"a":[62],"non-linear":[63],"hierarchical":[64],"structure(heap)":[66],"allows":[68],"us":[69],"separate":[72],"needs":[75],"be":[77],"revisited":[78],"from":[79],"does":[82],"not":[83],"narrow":[86],"iteration":[88],"toward":[89],"difficult":[95],"cluster.":[97],"We":[98,104,120],"call":[99],"this":[100],"extended":[101],"EM-T,":[102],"EM*.":[103],"show":[105],"our":[106],"EM*":[107,130],"outperform":[109],"over":[112],"large":[113],"real":[114],"world":[115],"synthetic":[117],"sets.":[119],"lastly":[121],"conclude":[122],"some":[124],"theoretic":[125],"underpinnings":[126],"explain":[128],"why":[129],"successful.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}