{"id":"https://openalex.org/W2170365184","doi":"https://doi.org/10.1109/dmo.2009.5341896","title":"Building a new taxonomy for data discretization techniques","display_name":"Building a new taxonomy for data discretization techniques","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2170365184","doi":"https://doi.org/10.1109/dmo.2009.5341896","mag":"2170365184"},"language":"en","primary_location":{"id":"doi:10.1109/dmo.2009.5341896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dmo.2009.5341896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 2nd Conference on Data Mining and Optimization","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/A5042883130","display_name":"Azuraliza Abu Bakar","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Azuraliza Abu Bakar","raw_affiliation_strings":["Data Mining & Optimization Research Group, University Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining & Optimization Research Group, University Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074274712","display_name":"Zulaiha Ali Othman","orcid":"https://orcid.org/0000-0002-4238-5266"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Zulaiha Ali Othman","raw_affiliation_strings":["Data Mining & Optimization Research Group, University Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining & Optimization Research Group, University Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nor Liyana Mohd Shuib","orcid":null},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Nor Liyana Mohd Shuib","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, University Malaya, MALAYSIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, University Malaya, MALAYSIA","institution_ids":["https://openalex.org/I1323252656"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6586,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95548408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.991599977016449,"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/data-mining","display_name":"Data mining","score":0.7786805629730225},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.7780965566635132},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7593967318534851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.71793532371521},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7100816369056702},{"id":"https://openalex.org/keywords/data-reduction","display_name":"Data reduction","score":0.5319885015487671},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4996500015258789},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.47858548164367676},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.455625057220459},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4532105624675751},{"id":"https://openalex.org/keywords/discretization-of-continuous-features","display_name":"Discretization of continuous features","score":0.4158622622489929},{"id":"https://openalex.org/keywords/discretization-error","display_name":"Discretization error","score":0.2731953263282776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2725890278816223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20253774523735046},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1448918879032135},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12641039490699768}],"concepts":[{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7786805629730225},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7780965566635132},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7593967318534851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71793532371521},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7100816369056702},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.5319885015487671},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4996500015258789},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.47858548164367676},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.455625057220459},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4532105624675751},{"id":"https://openalex.org/C105427703","wikidata":"https://www.wikidata.org/wiki/Q665193","display_name":"Discretization of continuous features","level":4,"score":0.4158622622489929},{"id":"https://openalex.org/C126148662","wikidata":"https://www.wikidata.org/wiki/Q3890355","display_name":"Discretization error","level":3,"score":0.2731953263282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2725890278816223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20253774523735046},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1448918879032135},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12641039490699768},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dmo.2009.5341896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dmo.2009.5341896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 2nd Conference on Data Mining and Optimization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W22040276","https://openalex.org/W22933393","https://openalex.org/W67858951","https://openalex.org/W69783631","https://openalex.org/W90901292","https://openalex.org/W105178432","https://openalex.org/W136154127","https://openalex.org/W136455924","https://openalex.org/W208128215","https://openalex.org/W235630032","https://openalex.org/W639511938","https://openalex.org/W1482410484","https://openalex.org/W1486465383","https://openalex.org/W1493199116","https://openalex.org/W1494166964","https://openalex.org/W1513366687","https://openalex.org/W1527997375","https://openalex.org/W1530010412","https://openalex.org/W1545814848","https://openalex.org/W1554309553","https://openalex.org/W1572027721","https://openalex.org/W1585743408","https://openalex.org/W1597910678","https://openalex.org/W1602306524","https://openalex.org/W1602944711","https://openalex.org/W1608815176","https://openalex.org/W1610099415","https://openalex.org/W1678889691","https://openalex.org/W1679913846","https://openalex.org/W1742152372","https://openalex.org/W1810531667","https://openalex.org/W1861764418","https://openalex.org/W1902572552","https://openalex.org/W1961147827","https://openalex.org/W2000613518","https://openalex.org/W2020546735","https://openalex.org/W2023995721","https://openalex.org/W2049092228","https://openalex.org/W2054658115","https://openalex.org/W2082131185","https://openalex.org/W2086460959","https://openalex.org/W2095945735","https://openalex.org/W2098699182","https://openalex.org/W2101110573","https://openalex.org/W2105646650","https://openalex.org/W2109293916","https://openalex.org/W2110883665","https://openalex.org/W2112122409","https://openalex.org/W2113001205","https://openalex.org/W2118716686","https://openalex.org/W2130517087","https://openalex.org/W2133008226","https://openalex.org/W2133121564","https://openalex.org/W2135511047","https://openalex.org/W2140190241","https://openalex.org/W2145912932","https://openalex.org/W2146424733","https://openalex.org/W2149706766","https://openalex.org/W2159191485","https://openalex.org/W2160170937","https://openalex.org/W2160671582","https://openalex.org/W2161919332","https://openalex.org/W2166169924","https://openalex.org/W2185734222","https://openalex.org/W2340020088","https://openalex.org/W2483832347","https://openalex.org/W2570343052","https://openalex.org/W4236137412","https://openalex.org/W4255833381","https://openalex.org/W4285719527","https://openalex.org/W6600913515","https://openalex.org/W6602774077","https://openalex.org/W6602840736","https://openalex.org/W6603663993","https://openalex.org/W6604371904","https://openalex.org/W6609041395","https://openalex.org/W6620733711","https://openalex.org/W6628803227","https://openalex.org/W6629593171","https://openalex.org/W6630540995","https://openalex.org/W6631458826","https://openalex.org/W6635046684","https://openalex.org/W6635821875","https://openalex.org/W6636478343","https://openalex.org/W6639105084","https://openalex.org/W6639652276","https://openalex.org/W6641082943","https://openalex.org/W6674301760","https://openalex.org/W6676746716","https://openalex.org/W6676923212","https://openalex.org/W6679813549","https://openalex.org/W6684235423"],"related_works":["https://openalex.org/W3202554610","https://openalex.org/W138569904","https://openalex.org/W2186437798","https://openalex.org/W2020045149","https://openalex.org/W2618163531","https://openalex.org/W2548532473","https://openalex.org/W2376367779","https://openalex.org/W176219849","https://openalex.org/W2897583753","https://openalex.org/W3021414116"],"abstract_inverted_index":{"Data":[0,89,110],"preprocessing":[1,45,87],"is":[2,10,178,202],"an":[3,125],"important":[4,85],"step":[5,46,68],"in":[6,18,22,66,116,141],"data":[7,34,58,70,78,81,86,94,102,122,137,152],"mining.":[8],"It":[9,28],"used":[11],"to":[12,24,53,207],"resolve":[13],"various":[14,49],"types":[15],"of":[16,30,48,69,100,106,121,128,135,143,151,185,198],"problem":[17],"a":[19,57,104,113,182],"large":[20],"dataset":[21],"order":[23,52],"produce":[25],"quality":[26,55],"data.":[27],"consists":[29,47],"four":[31,149],"steps,":[32],"namely,":[33],"cleaning,":[35],"integration,":[36],"reduction":[37,79,90],"and":[38,158,162,165,168,172,195],"transformation.":[39],"The":[40,176],"literature":[41],"shows":[42],"that":[43],"each":[44],"techniques.":[50,175,188],"In":[51,72],"develop":[54],"data,":[56],"miner":[59],"must":[60],"decide":[61],"the":[62,93,98,118,133,136,196,199,209],"most":[63],"appropriate":[64,126],"techniques":[65,192],"every":[67],"preprocessing.":[71],"this":[73],"study,":[74],"we":[75],"focus":[76],"on":[77,181,205],"particularly":[80,140],"discretization":[82,111,153,187,200],"as":[83,155],"one":[84],"step.":[88],"involves":[91],"reducing":[92,97,117],"distribution":[95],"by":[96],"range":[99,105],"continuous":[101],"into":[103],"values":[107,130],"or":[108],"categories.":[109],"plays":[112],"major":[114],"role":[115],"attribute":[119],"intervals":[120],"values.":[123],"Finding":[124],"number":[127],"discrete":[129],"will":[131],"improve":[132],"performance":[134],"mining":[138],"modelling,":[139],"terms":[142],"classification":[144],"accuracy.":[145],"This":[146],"paper":[147],"proposes":[148],"levels":[150],"taxonomy":[154,177,211],"follows:":[156],"hierarchical":[157],"non-hierarchical;":[159],"splitting,":[160],"merging":[161],"combination;":[163],"supervised":[164],"unsupervised":[166],"combinations;":[167],"binning,":[169],"statistic,":[170],"entropy":[171],"other":[173],"related":[174],"developed":[179],"based":[180],"detailed":[183],"review":[184],"previous":[186],"More":[189],"than":[190],"fifty":[191],"are":[193,212],"investigated,":[194],"structure":[197],"approach":[201],"outlined.":[203],"Guidelines":[204],"how":[206],"use":[208],"proposed":[210],"also":[213],"discussed.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}