{"id":"https://openalex.org/W2094228100","doi":"https://doi.org/10.1109/bibe.2008.4696683","title":"Normalized EM algorithm for tumor clustering using gene expression data","display_name":"Normalized EM algorithm for tumor clustering using gene expression data","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2094228100","doi":"https://doi.org/10.1109/bibe.2008.4696683","mag":"2094228100"},"language":"en","primary_location":{"id":"doi:10.1109/bibe.2008.4696683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2008.4696683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on BioInformatics and BioEngineering","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/A5101813009","display_name":"Phuong Nguyen","orcid":"https://orcid.org/0000-0002-3752-8699"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Nguyen Minh Phuong","raw_affiliation_strings":["The School of Electrical Engineering and Telecommunications, University of New South Wales, Kensington, NSW, Australia","Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Kensington, NSW"],"affiliations":[{"raw_affiliation_string":"The School of Electrical Engineering and Telecommunications, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Kensington, NSW","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000403961","display_name":"Nguy\u1ec5n Xu\u00e2n Vinh","orcid":"https://orcid.org/0000-0002-7275-750X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nguyen Xuan Vinh","raw_affiliation_strings":["The School of Electrical Engineering and Telecommunications, University of New South Wales, Kensington, NSW, Australia","Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Kensington, NSW"],"affiliations":[{"raw_affiliation_string":"The School of Electrical Engineering and Telecommunications, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Kensington, NSW","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101813009"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.1347,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.54609179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9988999962806702,"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":0.9962999820709229,"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":0.8758037090301514},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.697700023651123},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.6827142238616943},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.6754370927810669},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.6298397779464722},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.596522867679596},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5805703401565552},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.5791800618171692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5140103101730347},{"id":"https://openalex.org/keywords/hypersphere","display_name":"Hypersphere","score":0.5005917549133301},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4953285753726959},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4722558557987213},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.46784624457359314},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44730374217033386},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.41484376788139343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38356396555900574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37142136693000793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37126240134239197},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20031329989433289},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10136571526527405}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8758037090301514},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.697700023651123},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.6827142238616943},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.6754370927810669},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.6298397779464722},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.596522867679596},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5805703401565552},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.5791800618171692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5140103101730347},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.5005917549133301},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4953285753726959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4722558557987213},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.46784624457359314},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44730374217033386},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.41484376788139343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38356396555900574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37142136693000793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37126240134239197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20031329989433289},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10136571526527405},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe.2008.4696683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2008.4696683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on BioInformatics and BioEngineering","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":37,"referenced_works":["https://openalex.org/W1769049279","https://openalex.org/W1790954942","https://openalex.org/W1970156673","https://openalex.org/W2069271664","https://openalex.org/W2087684630","https://openalex.org/W2096788288","https://openalex.org/W2108728387","https://openalex.org/W2109014721","https://openalex.org/W2109363337","https://openalex.org/W2109970232","https://openalex.org/W2124704116","https://openalex.org/W2127284416","https://openalex.org/W2130494035","https://openalex.org/W2133241531","https://openalex.org/W2135000328","https://openalex.org/W2135187880","https://openalex.org/W2136097953","https://openalex.org/W2138218344","https://openalex.org/W2141729166","https://openalex.org/W2142460132","https://openalex.org/W2145001205","https://openalex.org/W2146646206","https://openalex.org/W2148694408","https://openalex.org/W2150926065","https://openalex.org/W2152012752","https://openalex.org/W2155612034","https://openalex.org/W2161893150","https://openalex.org/W2165011536","https://openalex.org/W2168811230","https://openalex.org/W2496323672","https://openalex.org/W4246697467","https://openalex.org/W4247420482","https://openalex.org/W6637940469","https://openalex.org/W6681208759","https://openalex.org/W6682124274","https://openalex.org/W6776535907","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2362911195","https://openalex.org/W1981651077","https://openalex.org/W2794209582","https://openalex.org/W2567087402","https://openalex.org/W2163563073","https://openalex.org/W2610598280","https://openalex.org/W4381747237","https://openalex.org/W1987613674","https://openalex.org/W2803938633","https://openalex.org/W2330550450"],"abstract_inverted_index":{"Most":[0],"of":[1,66,86,194,202,208,212,222],"the":[2,18,34,55,64,72,112,134,144,160,164,187,192,200,209,213,219,223],"proposed":[3],"clustering":[4,20,28,52,78,140,168,189],"approaches":[5],"are":[6,83],"heuristic":[7],"in":[8,47,186,225],"nature.":[9],"As":[10],"a":[11,23,104],"result,":[12],"it":[13],"is":[14,118,131,163,171,196,230],"difficult":[15],"to":[16,39,100,110,173,218],"interpret":[17],"obtained":[19],"outcomes":[21],"from":[22,33,59],"statistical":[24,42,228],"standpoint.":[25],"Mixture":[26],"model-based":[27,56,154,167],"has":[29],"received":[30],"much":[31,197],"attention":[32],"gene":[35],"expression":[36],"community":[37],"due":[38],"its":[40,45,125,226],"sound":[41],"background":[43],"and":[44,156],"flexibility":[46],"data":[48,93,184],"modeling.":[49],"However,":[50],"current":[51],"algorithms":[53,68,141],"following":[54],"framework":[57],"suffer":[58],"two":[60,113],"serious":[61],"drawbacks.":[62],"First,":[63],"performance":[65,135],"these":[67],"critically":[69],"depends":[70],"on":[71],"starting":[73],"values":[74],"for":[75,124,151],"their":[76],"iterative":[77,127],"procedures.":[79],"And":[80],"second,":[81],"they":[82],"not":[84],"capable":[85],"working":[87,177],"directly":[88,178],"with":[89,121,137,179,216],"very":[90,180],"high":[91,181],"dimensional":[92,182],"sets":[94,185],"whose":[95],"dimension":[96],"might":[97],"be":[98,174],"up":[99],"thousands.":[101],"We":[102],"propose":[103],"novel":[105],"normalized":[106,116,161,214],"Expectation-Maximization":[107],"(EM)":[108],"algorithm":[109,150,169],"tackle":[111],"challenges.":[114],"The":[115],"EM":[117,126,146,149,162,215],"stable":[119,175],"even":[120],"random":[122],"initializations":[123],"procedure.":[128],"Its":[129],"stability":[130],"demonstrated":[132],"through":[133],"comparison":[136],"other":[138],"related":[139],"such":[142],"as":[143],"unnormalized":[145],"(The":[147],"conventional":[148],"Gaussian":[152],"mixture":[153,166],"clustering)":[155],"spherical":[157],"k-means.":[158],"Furthermore,":[159],"first":[165],"that":[170],"shown":[172],"when":[176],"microarray":[183],"sample":[188],"problem,":[190],"where":[191],"number":[193,201],"genes":[195],"larger":[198],"than":[199],"samples.":[203],"Besides,":[204],"an":[205],"interesting":[206],"property":[207],"convergence":[210],"speed":[211],"respect":[217],"squared":[220],"radius":[221],"hypersphere":[224],"corresponding":[227],"model":[229],"uncovered.":[231]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}