{"id":"https://openalex.org/W3015166974","doi":"https://doi.org/10.1587/transinf.2019iip0017","title":"Improving Seeded k-Means Clustering with Deviation- and Entropy-Based Term Weightings","display_name":"Improving Seeded k-Means Clustering with Deviation- and Entropy-Based Term Weightings","publication_year":2020,"publication_date":"2020-03-31","ids":{"openalex":"https://openalex.org/W3015166974","doi":"https://doi.org/10.1587/transinf.2019iip0017","mag":"3015166974"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019iip0017","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019iip0017","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/4/E103.D_2019IIP0017/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/4/E103.D_2019IIP0017/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069218608","display_name":"Uraiwan Buatoom","orcid":"https://orcid.org/0000-0002-5807-0947"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]},{"id":"https://openalex.org/I316699675","display_name":"Hodges University","ror":"https://ror.org/00s8h5d08","country_code":"US","type":"education","lineage":["https://openalex.org/I316699675"]}],"countries":["TH","US"],"is_corresponding":false,"raw_author_name":"Uraiwan BUATOOM","raw_affiliation_strings":["School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University","institution_ids":["https://openalex.org/I108108428","https://openalex.org/I316699675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068885712","display_name":"Waree Kongprawechnon","orcid":"https://orcid.org/0000-0002-2057-6352"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]},{"id":"https://openalex.org/I316699675","display_name":"Hodges University","ror":"https://ror.org/00s8h5d08","country_code":"US","type":"education","lineage":["https://openalex.org/I316699675"]}],"countries":["TH","US"],"is_corresponding":false,"raw_author_name":"Waree KONGPRAWECHNON","raw_affiliation_strings":["School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University","institution_ids":["https://openalex.org/I108108428","https://openalex.org/I316699675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083358892","display_name":"Thanaruk Theeramunkong","orcid":"https://orcid.org/0000-0003-0744-4213"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]},{"id":"https://openalex.org/I316699675","display_name":"Hodges University","ror":"https://ror.org/00s8h5d08","country_code":"US","type":"education","lineage":["https://openalex.org/I316699675"]},{"id":"https://openalex.org/I4210132449","display_name":"The Royal College Of Anesthesiologists Of Thailand","ror":"https://ror.org/03e4r0p06","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210132449"]},{"id":"https://openalex.org/I4387154341","display_name":"Office of the Royal Society","ror":"https://ror.org/04v9gtz82","country_code":null,"type":"government","lineage":["https://openalex.org/I4387154341"]}],"countries":["TH","US"],"is_corresponding":false,"raw_author_name":"Thanaruk THEERAMUNKONG","raw_affiliation_strings":["School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University","The Royal Society of Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Computer, and Communication Technology (ICT), Sirindhorn International Institute of Technology, Thammasat University","institution_ids":["https://openalex.org/I108108428","https://openalex.org/I316699675"]},{"raw_affiliation_string":"The Royal Society of Thailand","institution_ids":["https://openalex.org/I4210132449","https://openalex.org/I4387154341"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2681,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65003995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E103.D","issue":"4","first_page":"748","last_page":"758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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":0.9890999794006348,"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":0.7659691572189331},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6831392049789429},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.6008090376853943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5870729684829712},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5623267292976379},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4226084351539612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40864336490631104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3975295126438141},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38385263085365295},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24735519289970398},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0884341299533844}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7659691572189331},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6831392049789429},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.6008090376853943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5870729684829712},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5623267292976379},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4226084351539612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40864336490631104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3975295126438141},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38385263085365295},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24735519289970398},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0884341299533844},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019iip0017","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019iip0017","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/4/E103.D_2019IIP0017/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019iip0017","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019iip0017","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/4/E103.D_2019IIP0017/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G6570415265","display_name":null,"funder_award_id":"RTA6280015","funder_id":"https://openalex.org/F4320323439","funder_display_name":"Thammasat University"},{"id":"https://openalex.org/G8145318707","display_name":null,"funder_award_id":"RTA6280015","funder_id":"https://openalex.org/F4320322614","funder_display_name":"Thailand Research Fund"}],"funders":[{"id":"https://openalex.org/F4320322614","display_name":"Thailand Research Fund","ror":"https://ror.org/03gd1bh37"},{"id":"https://openalex.org/F4320322683","display_name":"Burapha University","ror":"https://ror.org/01ff74m36"},{"id":"https://openalex.org/F4320323439","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20"},{"id":"https://openalex.org/F4320326788","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015166974.pdf","grobid_xml":"https://content.openalex.org/works/W3015166974.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W45904873","https://openalex.org/W202303397","https://openalex.org/W1596382552","https://openalex.org/W1963816080","https://openalex.org/W1969128289","https://openalex.org/W1973837973","https://openalex.org/W1984589212","https://openalex.org/W1992944354","https://openalex.org/W2000950075","https://openalex.org/W2007193508","https://openalex.org/W2007499122","https://openalex.org/W2031115546","https://openalex.org/W2088994381","https://openalex.org/W2096100960","https://openalex.org/W2102524069","https://openalex.org/W2104500038","https://openalex.org/W2105543877","https://openalex.org/W2134089414","https://openalex.org/W2139956879","https://openalex.org/W2144211451","https://openalex.org/W2153291472","https://openalex.org/W2165933018","https://openalex.org/W2293570855","https://openalex.org/W2340234190","https://openalex.org/W2467221854","https://openalex.org/W2558197696","https://openalex.org/W2598930435","https://openalex.org/W2607931573","https://openalex.org/W2735051402","https://openalex.org/W2772114629","https://openalex.org/W2912725653","https://openalex.org/W2963910295","https://openalex.org/W3000444237"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2108418243","https://openalex.org/W2127804977","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W2040545019","https://openalex.org/W3046039077","https://openalex.org/W2056801006"],"abstract_inverted_index":{"The":[0,113],"outcome":[1],"of":[2,97,128],"document":[3],"clustering":[4,81,133],"depends":[5],"on":[6],"the":[7,33,80,84,86,95,117,121,132],"scheme":[8],"used":[9,91],"to":[10,14,25,29,31,74],"assign":[11],"a":[12,18,41,54,125],"weight":[13],"each":[15],"term":[16,65],"in":[17,64,78],"document.":[19],"While":[20],"recent":[21],"works":[22],"have":[23],"tried":[24],"use":[26],"distributions":[27,130],"related":[28],"class":[30],"enhance":[32],"discrimination":[34],"ability.":[35],"It":[36],"is":[37,48,90],"worth":[38],"exploring":[39],"whether":[40],"deviation":[42],"approach":[43,47],"or":[44],"an":[45],"entropy":[46],"more":[49],"effective.":[50],"This":[51],"paper":[52],"presents":[53],"comparison":[55],"between":[56],"deviation-based":[57,118],"distribution":[58,61,119],"and":[59,94,100,108,124],"entropy-based":[60,122],"as":[62],"constraints":[63],"weighting.":[66],"In":[67,83],"addition,":[68],"their":[69],"potential":[70],"combinations":[71],"are":[72,103],"investigated":[73],"find":[75],"optimal":[76],"solutions":[77],"guiding":[79],"process.":[82],"experiments,":[85],"seeded":[87],"k-means":[88],"method":[89],"for":[92],"clustering,":[93],"performances":[96],"deviation-based,":[98],"entropy-based,":[99],"hybrid":[101],"approaches,":[102],"analyzed":[104],"using":[105],"two":[106],"English":[107],"one":[109],"Thai":[110],"text":[111],"datasets.":[112],"result":[114],"showed":[115],"that":[116],"outperformed":[120],"distribution,":[123],"suitable":[126],"combination":[127],"these":[129],"increases":[131],"accuracy":[134],"by":[135],"10%.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
