{"id":"https://openalex.org/W4391093875","doi":"https://doi.org/10.1109/bigdata59044.2023.10386695","title":"Feature Selection on Big Data using Masked Sparse Bottleneck Centroid-Encoder","display_name":"Feature Selection on Big Data using Masked Sparse Bottleneck Centroid-Encoder","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093875","doi":"https://doi.org/10.1109/bigdata59044.2023.10386695"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5063172366","display_name":"Tomojit Ghosh","orcid":"https://orcid.org/0000-0001-6875-3840"},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tomojit Ghosh","raw_affiliation_strings":["University of Tennessee,Department of Computer Science & Engineering,Chattanooga,USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee,Department of Computer Science & Engineering,Chattanooga,USA","institution_ids":["https://openalex.org/I177097968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008589258","display_name":"M. Kirby","orcid":"https://orcid.org/0000-0002-5234-6308"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Kirby","raw_affiliation_strings":["Colorado State University,Department of Mathematics,Fort Collins,USA","Department of Mathematics, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Colorado State University,Department of Mathematics,Fort Collins,USA","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Department of Mathematics, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063172366"],"corresponding_institution_ids":["https://openalex.org/I177097968"],"apc_list":null,"apc_paid":null,"fwci":1.2238,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84012221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9904999732971191,"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/T10862","display_name":"AI in cancer detection","score":0.9904999732971191,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9897000193595886,"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":0.9797000288963318,"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/centroid","display_name":"Centroid","score":0.7689412832260132},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6447043418884277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6387078762054443},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6359723210334778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6009467244148254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4901624619960785},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4591197073459625},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45214563608169556},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43978846073150635},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4102820158004761}],"concepts":[{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.7689412832260132},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6447043418884277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6387078762054443},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6359723210334778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009467244148254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4901624619960785},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4591197073459625},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45214563608169556},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43978846073150635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4102820158004761},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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":62,"referenced_works":["https://openalex.org/W113475142","https://openalex.org/W1577822803","https://openalex.org/W1661405579","https://openalex.org/W1964042173","https://openalex.org/W1971881316","https://openalex.org/W2018998004","https://openalex.org/W2020925091","https://openalex.org/W2022020282","https://openalex.org/W2031735032","https://openalex.org/W2059667789","https://openalex.org/W2098515060","https://openalex.org/W2100495367","https://openalex.org/W2114391324","https://openalex.org/W2118526609","https://openalex.org/W2118561568","https://openalex.org/W2119883478","https://openalex.org/W2122825543","https://openalex.org/W2125621954","https://openalex.org/W2135046866","https://openalex.org/W2136922672","https://openalex.org/W2143426320","https://openalex.org/W2152195021","https://openalex.org/W2161893150","https://openalex.org/W2253609413","https://openalex.org/W2293825098","https://openalex.org/W2398336627","https://openalex.org/W2460144244","https://openalex.org/W2475924856","https://openalex.org/W2557913829","https://openalex.org/W2560674852","https://openalex.org/W2600746833","https://openalex.org/W2754603907","https://openalex.org/W2787225914","https://openalex.org/W2798405286","https://openalex.org/W2892911634","https://openalex.org/W2913375711","https://openalex.org/W2951396542","https://openalex.org/W2997674406","https://openalex.org/W2998216295","https://openalex.org/W3002587223","https://openalex.org/W3004752032","https://openalex.org/W3095195132","https://openalex.org/W3105513009","https://openalex.org/W3105524694","https://openalex.org/W4239510810","https://openalex.org/W4246623349","https://openalex.org/W4251163770","https://openalex.org/W4287864083","https://openalex.org/W4289236186","https://openalex.org/W4294541532","https://openalex.org/W4295897369","https://openalex.org/W4394657409","https://openalex.org/W6631190155","https://openalex.org/W6636914306","https://openalex.org/W6682496738","https://openalex.org/W6730796357","https://openalex.org/W6743704092","https://openalex.org/W6759872529","https://openalex.org/W6773814093","https://openalex.org/W6773837021","https://openalex.org/W6864595823","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W3013299381"],"abstract_inverted_index":{"We":[0,157,181],"introduce":[1],"a":[2,64,69],"nonlinear":[3],"model,":[4],"Masked":[5],"Sparse":[6],"Bottleneck":[7],"Centroid-Encoder":[8],"(MSBCE),":[9],"for":[10],"determining":[11],"the":[12,32,36,46,55,73,78,83,86,105,109,114,119,123,126,132,136,196,211,244],"features":[13,27,93,121,134,186],"that":[14,184],"discriminate":[15],"between":[16],"two":[17,219],"or":[18],"more":[19],"classes.":[20],"The":[21,61,139,236],"algorithm":[22,140],"aims":[23],"to":[24,49,72,130,143,161,255],"extract":[25],"discriminatory":[26],"in":[28,35,45],"groups":[29],"while":[30],"reconstructing":[31],"class":[33,59,101,137],"centroids":[34,102,110],"ambient":[37],"space":[38],"and":[39,53,111,153,179,226,231],"simultaneously":[40],"use":[41],"additional":[42],"penalty":[43],"terms":[44],"bottleneck":[47],"layer":[48,66],"decrease":[50],"within-class":[51],"scatter":[52],"increase":[54],"separation":[56],"of":[57,85,108,113,135,243,247],"different":[58,162],"centroids.":[60,138],"model":[62],"has":[63],"sparsity-promoting":[65],"(SPL)":[67],"with":[68,77,228],"one-to-one":[70],"connection":[71],"input":[74,95],"layer.":[75],"Along":[76],"primary":[79],"objective,":[80],"we":[81,99],"minimize":[82],"$l_{2,1}$-norm":[84],"sparse":[87,115],"layer,":[88,116],"which":[89,239],"filters":[90],"out":[91],"unnecessary":[92],"from":[94,122,205],"data.":[96,156],"During":[97],"training,":[98],"update":[100],"by":[103],"taking":[104],"Hadamard":[106],"product":[107],"weights":[112],"thus":[117],"masking":[118],"irrelevant":[120],"target.":[124],"Therefore":[125],"proposed":[127],"method":[128,160],"learns":[129],"reconstruct":[131],"critical":[133],"is":[141,210,216],"applied":[142],"various":[144],"real-world":[145],"data":[146,223],"sets,":[147,199,224],"including":[148,167],"high-dimensional":[149],"biological,":[150],"image,":[151],"speech,":[152],"accelerometer":[154],"sensor":[155],"compared":[158,254],"our":[159],"state-of-the-art":[163,202,207],"feature":[164,214],"selection":[165,215],"techniques,":[166],"supervised":[168],"Concrete":[169],"Autoencoders":[170],"(SCAE),":[171],"Feature":[172],"Selection":[173],"Networks":[174],"(FsNet),":[175],"Stochastic":[176],"Gates":[177],"(STG),":[178],"LassoNet.":[180],"empirically":[182],"showed":[183],"MSBCE":[185],"often":[187],"produced":[188],"better":[189],"classification":[190],"accuracy":[191],"than":[192],"other":[193],"methods":[194],"on":[195,218],"sequester":[197],"test":[198],"setting":[200],"new":[201],"results.":[203],"Apart":[204],"achieving":[206],"results,":[208],"this":[209],"first":[212],"time":[213],"done":[217],"high-energy":[220],"particle":[221],"physics":[222],"SUSY":[225],"HIGGS,":[227],"4.5":[229],"million":[230,233],"10":[232],"samples,":[234],"respectively.":[235],"selected":[237],"features,":[238],"are":[240],"only":[241],"25-30%":[242],"total":[245],"number":[246],"variables,":[248],"attained":[249],"almost":[250],"similar":[251],"prediction":[252],"rates":[253],"all":[256],"features.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}