{"id":"https://openalex.org/W2145126350","doi":"https://doi.org/10.1109/aqtr.2014.6857838","title":"A new text clustering method based on Huffman encoding algorithm","display_name":"A new text clustering method based on Huffman encoding algorithm","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2145126350","doi":"https://doi.org/10.1109/aqtr.2014.6857838","mag":"2145126350"},"language":"en","primary_location":{"id":"doi:10.1109/aqtr.2014.6857838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aqtr.2014.6857838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Automation, Quality and Testing, Robotics","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/A5083026097","display_name":"Maria Muntean","orcid":"https://orcid.org/0000-0003-3928-7216"},"institutions":[{"id":"https://openalex.org/I4210140223","display_name":"1 Decembrie 1918 University","ror":"https://ror.org/04577k168","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210140223"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Maria Muntean","raw_affiliation_strings":["Science and Engineering Department, \u201c1 Decembrie 1918\u201d University of Alba Iulia, Alba Iulia, Romania","Sci. & Eng. Dept., Univ. of Alba Iulia, Alba Iulia, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Engineering Department, \u201c1 Decembrie 1918\u201d University of Alba Iulia, Alba Iulia, Romania","institution_ids":["https://openalex.org/I4210140223"]},{"raw_affiliation_string":"Sci. & Eng. Dept., Univ. of Alba Iulia, Alba Iulia, Romania","institution_ids":["https://openalex.org/I4210140223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011105446","display_name":"Lucia C\u00e3bulea","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140223","display_name":"1 Decembrie 1918 University","ror":"https://ror.org/04577k168","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210140223"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lucia Cabulea","raw_affiliation_strings":["Science and Engineering Department, \u201c1 Decembrie 1918\u201d University of Alba Iulia, Alba Iulia, Romania","Sci. & Eng. Dept., Univ. of Alba Iulia, Alba Iulia, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Engineering Department, \u201c1 Decembrie 1918\u201d University of Alba Iulia, Alba Iulia, Romania","institution_ids":["https://openalex.org/I4210140223"]},{"raw_affiliation_string":"Sci. & Eng. Dept., Univ. of Alba Iulia, Alba Iulia, Romania","institution_ids":["https://openalex.org/I4210140223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045151955","display_name":"Honoriu Vslean","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Honoriu Vslean","raw_affiliation_strings":["Autom. Dept., Tech. Univ. of Cluj Napoca, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autom. Dept., Tech. Univ. of Cluj Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8846,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76345682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1160","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9915000200271606,"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":0.9908000230789185,"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/huffman-coding","display_name":"Huffman coding","score":0.824112594127655},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7980331182479858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787789702415466},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6539576053619385},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5528653264045715},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5055222511291504},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4900926351547241},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4885293245315552},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4805889129638672},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.47529304027557373},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4595246911048889},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.41471412777900696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4062996208667755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3894311189651489},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.2582096457481384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23855748772621155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1285739541053772}],"concepts":[{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.824112594127655},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7980331182479858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787789702415466},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6539576053619385},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5528653264045715},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5055222511291504},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4900926351547241},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4885293245315552},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4805889129638672},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.47529304027557373},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4595246911048889},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.41471412777900696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4062996208667755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3894311189651489},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2582096457481384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23855748772621155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1285739541053772},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aqtr.2014.6857838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aqtr.2014.6857838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Automation, Quality and Testing, Robotics","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":11,"referenced_works":["https://openalex.org/W1566796406","https://openalex.org/W2043255484","https://openalex.org/W2071416419","https://openalex.org/W2107306087","https://openalex.org/W2141518341","https://openalex.org/W2150015221","https://openalex.org/W2154615166","https://openalex.org/W2188010542","https://openalex.org/W2992984260","https://openalex.org/W3120740533","https://openalex.org/W6687398598"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W3144143113","https://openalex.org/W2892323093","https://openalex.org/W4306940721","https://openalex.org/W2181939267","https://openalex.org/W2117838073","https://openalex.org/W2491448268","https://openalex.org/W2160785859","https://openalex.org/W3174322327","https://openalex.org/W2394193399"],"abstract_inverted_index":{"Clustering":[0],"of":[1,15,36,53,71,80,115,169],"text":[2,37,72],"data":[3,8,38],"is":[4,39,138],"a":[5,13,63,81,125,154,164],"widely":[6],"studied":[7],"mining":[9],"problem":[10],"and":[11,23,30,87,122],"has":[12,146],"number":[14],"applications":[16],"such":[17],"as":[18,91],"spam":[19],"detection,":[20],"document":[21],"organization":[22],"indexing,":[24],"IP-address":[25],"streams,":[26,29],"credit-card":[27],"transaction":[28],"so":[31,48],"on.":[32],"However,":[33],"the":[34,45,51,68,77,94,99,104,109,116,130,141,167],"clustering":[35,69,127,156],"still":[40],"in":[41,93,151],"early":[42],"stage,":[43],"because":[44,150],"research":[46],"focused":[47],"far":[49],"on":[50],"case":[52],"quantitative":[54],"or":[55,161],"categorical":[56],"data.":[57,73],"In":[58,98],"this":[59,152],"paper":[60],"we":[61,102,123],"propose":[62],"new":[64],"method":[65,75,111,137,157],"for":[66],"improving":[67],"accuracy":[70,128],"Our":[74],"encodes":[76],"string":[78,148],"values":[79],"dataset":[82,117,142],"using":[83],"Huffman":[84],"encoding":[85],"algorithm,":[86],"declares":[88],"these":[89],"attributes":[90],"integer":[92],"cluster":[95,105],"evaluation":[96],"phase.":[97],"experimental":[100],"part,":[101],"compared":[103],"label":[106],"assigned":[107],"by":[108],"proposed":[110],"to":[112,143],"each":[113],"instance":[114],"with":[118,133,163],"its":[119],"real":[120],"category,":[121],"obtained":[124],"better":[126],"than":[129],"one":[131],"found":[132],"traditional":[134,155],"methods.":[135],"This":[136],"useful":[139],"when":[140],"be":[144],"clustered":[145],"only":[147],"attributes,":[149],"case,":[153],"does":[158],"not":[159],"recognize,":[160],"recognize":[162],"low":[165],"accuracy,":[166],"category":[168],"instances.":[170]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}