{"id":"https://openalex.org/W2030663295","doi":"https://doi.org/10.1109/cidm.2014.7008701","title":"Scaling a neyman-pearson subset selection approach via heuristics for mining massive data","display_name":"Scaling a neyman-pearson subset selection approach via heuristics for mining massive data","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2030663295","doi":"https://doi.org/10.1109/cidm.2014.7008701","mag":"2030663295"},"language":"en","primary_location":{"id":"doi:10.1109/cidm.2014.7008701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2014.7008701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079638101","display_name":"Gregory Ditzler","orcid":"https://orcid.org/0000-0001-6890-0935"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Ditzler","raw_affiliation_strings":["Drexel University, Philadelphia, PA 19104 USA","Drexel University, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA 19104 USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Drexel University, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020997623","display_name":"Matthew Austen","orcid":null},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Austen","raw_affiliation_strings":["Rowan University, Glassboro, NJ 08028 USA","Rowan University, Glassboro, NJ 08028, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rowan University, Glassboro, NJ 08028 USA","institution_ids":["https://openalex.org/I44265643"]},{"raw_affiliation_string":"Rowan University, Glassboro, NJ 08028, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Rosen","raw_affiliation_strings":["Drexel University, Philadelphia, PA 19104 USA","Drexel University, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA 19104 USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Drexel University, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025314990","display_name":"Robi Polikar","orcid":"https://orcid.org/0000-0002-2739-4228"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robi Polikar","raw_affiliation_strings":["Rowan University, Glassboro, NJ 08028 USA","Rowan University, Glassboro, NJ 08028, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rowan University, Glassboro, NJ 08028 USA","institution_ids":["https://openalex.org/I44265643"]},{"raw_affiliation_string":"Rowan University, Glassboro, NJ 08028, USA","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9988999962806702,"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":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973999857902527,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.991100013256073,"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/feature-selection","display_name":"Feature selection","score":0.8140078783035278},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7329744696617126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6400160193443298},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6017313599586487},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5541868209838867},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5488616824150085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49764660000801086},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4617955684661865},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44347238540649414}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.8140078783035278},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7329744696617126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6400160193443298},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6017313599586487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5541868209838867},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5488616824150085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49764660000801086},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4617955684661865},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44347238540649414},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cidm.2014.7008701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2014.7008701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.728.1406","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.728.1406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.engr.arizona.edu/%7Editzler/publications/cidm2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W138217685","https://openalex.org/W144440563","https://openalex.org/W149574399","https://openalex.org/W1506934790","https://openalex.org/W1518574222","https://openalex.org/W1520252399","https://openalex.org/W1569512666","https://openalex.org/W1583700199","https://openalex.org/W1619226191","https://openalex.org/W1661871015","https://openalex.org/W1811186957","https://openalex.org/W1875482710","https://openalex.org/W1922017469","https://openalex.org/W1964042173","https://openalex.org/W1976802195","https://openalex.org/W1995196655","https://openalex.org/W2017337590","https://openalex.org/W2035575256","https://openalex.org/W2043772506","https://openalex.org/W2101826491","https://openalex.org/W2115247131","https://openalex.org/W2119387367","https://openalex.org/W2120173366","https://openalex.org/W2122825543","https://openalex.org/W2128059732","https://openalex.org/W2135046866","https://openalex.org/W2141552007","https://openalex.org/W2143426320","https://openalex.org/W2156504490","https://openalex.org/W2156909104","https://openalex.org/W2159175617","https://openalex.org/W2169673611","https://openalex.org/W2998216295","https://openalex.org/W4205699531","https://openalex.org/W4230674625","https://openalex.org/W4239875977","https://openalex.org/W4285719527","https://openalex.org/W6605609575","https://openalex.org/W6605866200","https://openalex.org/W6606090912","https://openalex.org/W6636914306","https://openalex.org/W6639467292","https://openalex.org/W6649221059","https://openalex.org/W6675201423","https://openalex.org/W6677040099","https://openalex.org/W6680979241","https://openalex.org/W6682686508","https://openalex.org/W6684950209","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Feature":[0,26],"subset":[1,54,76,102,117],"selection":[2,27,55,72,103,118,124,148,160,169],"is":[3,28,42,56,90],"an":[4,113],"important":[5],"step":[6],"towards":[7],"producing":[8],"a":[9,81,92,99,121,157,167,210],"classifier":[10,24],"that":[11,64,137],"relies":[12],"only":[13],"on":[14,34,98,132,207],"relevant":[15],"features,":[16],"while":[17],"keeping":[18],"the":[19,23,35,44,62,75,133,145,174,177,182,202],"computational":[20],"complexity":[21],"of":[22,37,135,156,176,209],"low.":[25],"also":[29],"used":[30,57],"in":[31,49],"making":[32],"inferences":[33,60],"importance":[36],"attributes,":[38],"even":[39],"when":[40],"classification":[41],"not":[43],"ultimate":[45],"goal.":[46],"For":[47],"example,":[48],"bioinformatics":[50],"and":[51,126,185],"genomics":[52],"feature":[53,71,116,159],"to":[58,78,88,105,115,144,205],"make":[59],"between":[61],"variables":[63,87],"best":[65],"describe":[66],"multiple":[67],"populations.":[68],"Unfortunately,":[69],"many":[70,86],"algorithms":[73],"require":[74],"size":[77],"be":[79,106,142],"specified":[80],"priori,":[82],"but":[83],"knowing":[84],"how":[85],"select":[89],"typically":[91],"nontrivial":[93],"task.":[94],"Other":[95],"approaches":[96],"rely":[97],"specific":[100],"variable":[101,123,147],"framework":[104],"used.":[107],"In":[108],"this":[109],"work,":[110],"we":[111,172,200],"examine":[112,173,186],"approach":[114,128,179],"works":[119],"with":[120],"generic":[122,146],"algorithm,":[125],"our":[127,153],"provides":[129],"statistical":[130],"inference":[131],"number":[134],"features":[136],"are":[138],"relevant,":[139],"which":[140,164],"may":[141],"unknown":[143],"algorithm.":[149,170],"This":[150],"work":[151],"extends":[152],"previous":[154],"implementation":[155],"Neyman-Pearson":[158],"(NPFS)":[161],"hypothesis":[162,183],"test,":[163,184],"acts":[165],"as":[166],"meta-subset":[168],"Specifically,":[171],"conservativeness":[175],"NPFS":[178],"by":[180],"biasing":[181],"other":[187],"heuristics":[188],"for":[189],"NPFS.":[190],"We":[191],"include":[192],"results":[193],"from":[194],"carefully":[195],"designed":[196],"synthetic":[197],"datasets.":[198],"Furthermore,":[199],"demonstrate":[201],"NPFS's":[203],"ability":[204],"perform":[206],"data":[208],"massive":[211],"scale.":[212]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}