{"id":"https://openalex.org/W2038827046","doi":"https://doi.org/10.1145/2371316.2371349","title":"Efficient dataset size reduction by finding homogeneous clusters","display_name":"Efficient dataset size reduction by finding homogeneous clusters","publication_year":2012,"publication_date":"2012-09-16","ids":{"openalex":"https://openalex.org/W2038827046","doi":"https://doi.org/10.1145/2371316.2371349","mag":"2038827046"},"language":"en","primary_location":{"id":"doi:10.1145/2371316.2371349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2371316.2371349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth Balkan Conference in Informatics","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/A5043003448","display_name":"Stefanos Ougiaroglou","orcid":"https://orcid.org/0000-0003-1094-2520"},"institutions":[{"id":"https://openalex.org/I192756129","display_name":"University of Macedonia","ror":"https://ror.org/05fg6gr82","country_code":"GR","type":"education","lineage":["https://openalex.org/I192756129"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stefanos Ougiaroglou","raw_affiliation_strings":["University of Mecedonia, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mecedonia, Thessaloniki, Greece","institution_ids":["https://openalex.org/I192756129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089769845","display_name":"Georgios Evangelidis","orcid":"https://orcid.org/0000-0003-1639-2152"},"institutions":[{"id":"https://openalex.org/I192756129","display_name":"University of Macedonia","ror":"https://ror.org/05fg6gr82","country_code":"GR","type":"education","lineage":["https://openalex.org/I192756129"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Evangelidis","raw_affiliation_strings":["University of Mecedonia, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mecedonia, Thessaloniki, Greece","institution_ids":["https://openalex.org/I192756129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192756129"],"apc_list":null,"apc_paid":null,"fwci":4.4307,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94327927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T10057","display_name":"Face and Expression Recognition","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9922000169754028,"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":0.7704408168792725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7327291369438171},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6845060586929321},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.6732800006866455},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.622287392616272},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6049692630767822},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.571384072303772},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5401789546012878},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4932059645652771},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.48540934920310974},{"id":"https://openalex.org/keywords/data-reduction","display_name":"Data reduction","score":0.4847426116466522},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4592689275741577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45133334398269653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43787774443626404},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4159421920776367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33299845457077026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1302950382232666}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7704408168792725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7327291369438171},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6845060586929321},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.6732800006866455},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.622287392616272},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6049692630767822},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.571384072303772},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5401789546012878},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4932059645652771},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.48540934920310974},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.4847426116466522},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4592689275741577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45133334398269653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43787774443626404},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4159421920776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33299845457077026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1302950382232666},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2371316.2371349","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2371316.2371349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth Balkan Conference in Informatics","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":25,"referenced_works":["https://openalex.org/W1497953515","https://openalex.org/W1523590985","https://openalex.org/W1535540078","https://openalex.org/W1610836425","https://openalex.org/W1967001541","https://openalex.org/W1983734765","https://openalex.org/W1994410331","https://openalex.org/W2011762057","https://openalex.org/W2014403077","https://openalex.org/W2019762723","https://openalex.org/W2068514419","https://openalex.org/W2092617083","https://openalex.org/W2098631313","https://openalex.org/W2098935086","https://openalex.org/W2104715395","https://openalex.org/W2107686700","https://openalex.org/W2122496402","https://openalex.org/W2127218421","https://openalex.org/W2147169507","https://openalex.org/W2150800840","https://openalex.org/W2151537585","https://openalex.org/W2158724449","https://openalex.org/W2162583212","https://openalex.org/W2182722412","https://openalex.org/W4253298852"],"related_works":["https://openalex.org/W2150708814","https://openalex.org/W2015128070","https://openalex.org/W2352801741","https://openalex.org/W2126100045","https://openalex.org/W2566086483","https://openalex.org/W4200420744","https://openalex.org/W2377815255","https://openalex.org/W2170365184","https://openalex.org/W2546959060","https://openalex.org/W1968933949"],"abstract_inverted_index":{"Although":[0],"the":[1,8,16,35,85,96,117],"k-Nearest":[2],"Neighbor":[3],"classifier":[4],"is":[5,67,99],"one":[6],"of":[7,81],"most":[9],"widely-used":[10],"classification":[11,57,118],"methods,":[12,110],"it":[13,23,112],"suffers":[14],"from":[15],"high":[17,62],"computational":[18],"cost":[19,50],"and":[20,51,101],"storage":[21,53],"requirements":[22,54],"involves.":[24],"These":[25],"major":[26],"drawbacks":[27],"have":[28],"constituted":[29],"an":[30,41,60],"active":[31],"research":[32],"field":[33],"over":[34],"last":[36],"decades.":[37],"This":[38],"paper":[39],"proposes":[40],"effective":[42],"data":[43],"reduction":[44,104],"algorithm":[45,66,98],"that":[46,75,95],"has":[47],"low":[48],"preprocessing":[49],"reduces":[52],"while":[55,111],"maintaining":[56],"accuracy":[58],"at":[59],"acceptable":[61],"level.":[63],"The":[64,79],"proposed":[65,97],"based":[68,90],"on":[69,91],"a":[70],"fast":[71],"pre-processing":[72],"clustering":[73],"procedure":[74],"creates":[76],"homogeneous":[77],"clusters.":[78],"centroids":[80],"these":[82],"clusters":[83],"constitute":[84],"reduced":[86],"training-set.":[87],"Experimental":[88],"results,":[89],"real-life":[92],"datasets,":[93],"illustrate":[94],"faster":[100],"achieves":[102],"higher":[103],"rates":[105],"than":[106],"three":[107],"known":[108],"existing":[109],"does":[113],"not":[114],"significantly":[115],"reduce":[116],"accuracy.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}