{"id":"https://openalex.org/W4320024295","doi":"https://doi.org/10.1109/bigdata55660.2022.10020450","title":"Approximation of the expectation-maximization algorithm for Gaussian mixture models on big data","display_name":"Approximation of the expectation-maximization algorithm for Gaussian mixture models on big data","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024295","doi":"https://doi.org/10.1109/bigdata55660.2022.10020450"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5073580921","display_name":"Mateusz Przyborowski","orcid":"https://orcid.org/0000-0002-7721-8433"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Mateusz Przyborowski","raw_affiliation_strings":["University of Warsaw QED Software,Institute of Informatics,Warsaw,Poland","Institute of Informatics, University of Warsaw QED Software, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"University of Warsaw QED Software,Institute of Informatics,Warsaw,Poland","institution_ids":["https://openalex.org/I4654613"]},{"raw_affiliation_string":"Institute of Informatics, University of Warsaw QED Software, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057541763","display_name":"Dominik \u015al\u0229zak","orcid":"https://orcid.org/0000-0003-2453-4974"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dominik Slezak","raw_affiliation_strings":["University of Warsaw QED Software,Institute of Informatics,Warsaw,Poland","Institute of Informatics, University of Warsaw QED Software, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"University of Warsaw QED Software,Institute of Informatics,Warsaw,Poland","institution_ids":["https://openalex.org/I4654613"]},{"raw_affiliation_string":"Institute of Informatics, University of Warsaw QED Software, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073580921"],"corresponding_institution_ids":["https://openalex.org/I4654613"],"apc_list":null,"apc_paid":null,"fwci":0.7276,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72457445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6256","last_page":"6260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9991000294685364,"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":0.9991000294685364,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.996999979019165,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9950000047683716,"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/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.8015526533126831},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.7038391828536987},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6682562232017517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6153889894485474},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5092121362686157},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4959648549556732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4531521797180176},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4397461712360382},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43961039185523987},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43763643503189087},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4364212453365326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3337574601173401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27939608693122864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2576327919960022},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2324260175228119},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14421331882476807}],"concepts":[{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.8015526533126831},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.7038391828536987},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6682562232017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6153889894485474},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5092121362686157},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4959648549556732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4531521797180176},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4397461712360382},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43961039185523987},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43763643503189087},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4364212453365326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3337574601173401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27939608693122864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2576327919960022},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2324260175228119},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14421331882476807},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2009086942","https://openalex.org/W2115415549","https://openalex.org/W2117853077","https://openalex.org/W2124369546","https://openalex.org/W2150606601","https://openalex.org/W2165880886","https://openalex.org/W2168530812","https://openalex.org/W2490662969","https://openalex.org/W2498094064","https://openalex.org/W2627006445","https://openalex.org/W2786672974","https://openalex.org/W3120740533","https://openalex.org/W4300412342","https://openalex.org/W6748816842"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W805531662","https://openalex.org/W2077224612","https://openalex.org/W84255947","https://openalex.org/W2153481672","https://openalex.org/W4312864369","https://openalex.org/W2014842417","https://openalex.org/W2891133681","https://openalex.org/W1853799209"],"abstract_inverted_index":{"Gaussian":[0],"mixture":[1],"models":[2,36],"are":[3,86],"a":[4],"very":[5],"useful":[6],"tool":[7],"for":[8,37],"modeling":[9],"data":[10],"distribution.":[11],"While":[12],"estimating":[13],"parameters":[14],"using":[15],"the":[16,38,51,60,69,83],"expectation-maximization":[17,52,70],"algorithm,":[18],"this":[19,44],"approach":[20,85],"does":[21],"not":[22],"scale":[23],"well":[24],"with":[25,82],"big":[26],"datasets,":[27],"especially":[28],"if":[29],"it":[30],"is":[31],"necessary":[32],"to":[33],"prepare":[34],"many":[35],"proper":[39],"selection":[40],"of":[41,50,59],"metaparameters.":[42],"In":[43],"article":[45],"we":[46],"present":[47],"an":[48],"approximation":[49],"algorithm":[53],"obtained":[54],"by":[55],"merging":[56],"crucial":[57],"subsets":[58],"dataset,":[61],"that":[62],"differ":[63],"slightly":[64],"in":[65],"their":[66],"effect":[67],"on":[68],"loss":[71],"function,":[72],"into":[73],"information":[74],"granules.":[75],"Furthermore,":[76],"application":[77],"examples":[78],"comparing":[79],"new":[80],"method":[81],"classical":[84],"shown.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}