{"id":"https://openalex.org/W3195971125","doi":"https://doi.org/10.1109/access.2021.3104357","title":"A Deep-Learned Embedding Technique for Categorical Features Encoding","display_name":"A Deep-Learned Embedding Technique for Categorical Features Encoding","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3195971125","doi":"https://doi.org/10.1109/access.2021.3104357","mag":"3195971125"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3104357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3104357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09512057.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09512057.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055369143","display_name":"Mwamba Kasongo Dahouda","orcid":"https://orcid.org/0000-0003-0376-683X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mwamba Kasongo Dahouda","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0376-683X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040592322","display_name":"Inwhee Joe","orcid":"https://orcid.org/0000-0002-8435-0395"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inwhee Joe","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8435-0395","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":21.5719,"has_fulltext":true,"cited_by_count":284,"citation_normalized_percentile":{"value":0.99579546,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"114381","last_page":"114391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9962000250816345,"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/encoding","display_name":"Encoding (memory)","score":0.7678995132446289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274901866912842},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6647048592567444},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.631405234336853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240174531936646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3943285048007965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19306686520576477}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7678995132446289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274901866912842},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6647048592567444},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.631405234336853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240174531936646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3943285048007965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19306686520576477}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3104357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3104357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09512057.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ea4f54fbd4ee4fc28489b168449a0955","is_oa":true,"landing_page_url":"https://doaj.org/article/ea4f54fbd4ee4fc28489b168449a0955","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 114381-114391 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3104357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3104357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09512057.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1514347133","display_name":null,"funder_award_id":"2020-0-00107","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G3411130480","display_name":null,"funder_award_id":"2020-0-00107","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195971125.pdf","grobid_xml":"https://content.openalex.org/works/W3195971125.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1556996173","https://openalex.org/W1614298861","https://openalex.org/W1990836268","https://openalex.org/W1994292711","https://openalex.org/W2056795330","https://openalex.org/W2070996757","https://openalex.org/W2131774270","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2159401492","https://openalex.org/W2239420864","https://openalex.org/W2250539671","https://openalex.org/W2274880506","https://openalex.org/W2427606719","https://openalex.org/W2464785945","https://openalex.org/W2493916176","https://openalex.org/W2558531213","https://openalex.org/W2742947407","https://openalex.org/W2754843079","https://openalex.org/W2765449478","https://openalex.org/W2769358515","https://openalex.org/W2784353464","https://openalex.org/W2824731080","https://openalex.org/W2884001105","https://openalex.org/W2912165583","https://openalex.org/W2923551741","https://openalex.org/W2945836425","https://openalex.org/W2950577311","https://openalex.org/W2952230511","https://openalex.org/W2954052001","https://openalex.org/W2962902328","https://openalex.org/W2962987875","https://openalex.org/W2964093505","https://openalex.org/W2998704965","https://openalex.org/W3014054623","https://openalex.org/W3014479773","https://openalex.org/W3020873385","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6636510571","https://openalex.org/W6668178708","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6683738474","https://openalex.org/W6717731741","https://openalex.org/W6719736774","https://openalex.org/W6723250868","https://openalex.org/W6744142555","https://openalex.org/W6745750740","https://openalex.org/W6753568494","https://openalex.org/W6760712844","https://openalex.org/W6763026624","https://openalex.org/W6764439227"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W4390437797","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Many":[0],"machine":[1,81],"learning":[2,8,82,157],"algorithms":[3,27],"and":[4,58,77,116,140,231],"almost":[5],"all":[6,162],"deep":[7],"architectures":[9],"are":[10,56,122,184],"incapable":[11],"of":[12,60,119,163,180,206,210,216],"processing":[13],"plain":[14],"texts":[15],"in":[16,31,65,213],"their":[17,23],"raw":[18],"form.":[19],"This":[20,84],"means":[21],"that":[22,135,192],"input":[24],"to":[25,33,43,69,112,146,160,170],"the":[26,117,120,164,168,178,193,214,217,224],"must":[28],"be":[29],"numerical":[30,49],"order":[32],"solve":[34],"classification":[35],"or":[36],"regression":[37],"problems.":[38],"Hence,":[39],"it":[40],"is":[41,100,110,158],"necessary":[42],"encode":[44],"these":[45],"categorical":[46,92,96,105,138,149,165,199],"variables":[47],"into":[48],"values":[50],"using":[51],"encoding":[52,64,94],"techniques.":[53],"Categorical":[54],"features":[55,93,106,234],"common":[57],"often":[59],"high":[61,71],"cardinality.":[62],"One-hot":[63],"such":[66],"circumstances":[67],"leads":[68],"very":[70],"dimensional":[72],"vector":[73,121],"representations,":[74],"raising":[75],"memory":[76,220,230],"computability":[78],"concerns":[79],"for":[80,91,104,186,198],"models.":[83],"paper":[85],"proposes":[86],"a":[87,101,113,126,132,151,202],"deep-learned":[88,195,225],"embedding":[89,196,226],"technique":[90,99,197,227],"on":[95],"datasets.":[97],"Our":[98],"distributed":[102],"representation":[103],"where":[107],"each":[108,148],"category":[109],"mapped":[111],"distinct":[114],"vector,":[115],"properties":[118],"learned":[123],"while":[124],"training":[125],"neural":[127],"network.":[128],"First,":[129],"we":[130,142],"create":[131],"data":[133,150,166,200],"vocabulary":[134,169],"includes":[136],"only":[137],"data,":[139],"then":[141],"use":[143],"word":[144,171],"tokenization":[145],"make":[147],"single":[152],"word.":[153],"After":[154],"that,":[155],"feature":[156],"introduced":[159],"map":[161],"from":[167],"vectors.":[172],"Three":[173],"different":[174],"datasets":[175],"provided":[176],"by":[177],"University":[179],"California":[181],"Irvine":[182],"(UCI)":[183],"used":[185],"training.":[187],"The":[188],"experimental":[189],"results":[190],"show":[191],"proposed":[194],"provides":[201],"higher":[203],"F1":[204],"score":[205],"89%":[207],"than":[208,235],"71%":[209],"one-hot":[211,236],"encoding,":[212],"case":[215],"Long":[218],"short-term":[219],"(LSTM)":[221],"model.":[222],"Moreover,":[223],"uses":[228],"less":[229],"generates":[232],"fewer":[233],"encoding.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":33},{"year":2025,"cited_by_count":94},{"year":2024,"cited_by_count":90},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}