{"id":"https://openalex.org/W4405935600","doi":"https://doi.org/10.1109/tai.2024.3524370","title":"A Stratified Seed Selection Algorithm for $K$-Means Clustering on Big Data","display_name":"A Stratified Seed Selection Algorithm for $K$-Means Clustering on Big Data","publication_year":2024,"publication_date":"2024-12-31","ids":{"openalex":"https://openalex.org/W4405935600","doi":"https://doi.org/10.1109/tai.2024.3524370"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3524370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3524370","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Artificial Intelligence","raw_type":"journal-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/A5017375468","display_name":"Namita Bajpai","orcid":"https://orcid.org/0000-0002-5817-5407"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Namita Bajpai","raw_affiliation_strings":["Department of Artificial Intelligence, Indian Institute of Technology, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-5817-5407","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062553068","display_name":"Jiaul H. Paik","orcid":"https://orcid.org/0000-0003-1550-3586"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jiaul H. Paik","raw_affiliation_strings":["Department of Artificial Intelligence, Indian Institute of Technology, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0003-1550-3586","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024219981","display_name":"Sudeshna Sarkar","orcid":"https://orcid.org/0000-0003-3439-4282"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeshna Sarkar","raw_affiliation_strings":["Department of Computer Science, Indian Institute of Technology, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0003-3439-4282","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.2401,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66876173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"6","issue":"5","first_page":"1334","last_page":"1344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8490999937057495,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8490999937057495,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.7407000064849854,"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/T13535","display_name":"Wireless Sensor Networks and IoT","score":0.6955999732017517,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6840869784355164},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6192079782485962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5462027788162231},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4112253785133362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.365171879529953},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3560665547847748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2658242881298065}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6840869784355164},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6192079782485962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5462027788162231},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4112253785133362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.365171879529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3560665547847748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2658242881298065}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3524370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3524370","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2011430131","https://openalex.org/W2051224630","https://openalex.org/W2071821878","https://openalex.org/W2074408893","https://openalex.org/W2138779671","https://openalex.org/W2142838865","https://openalex.org/W2150879893","https://openalex.org/W2767123504","https://openalex.org/W2798965501","https://openalex.org/W2803398131","https://openalex.org/W2805169807","https://openalex.org/W2973255091","https://openalex.org/W2989341113","https://openalex.org/W2997272341","https://openalex.org/W3124214789","https://openalex.org/W3161186311","https://openalex.org/W3181104647","https://openalex.org/W4213251304","https://openalex.org/W4213412693","https://openalex.org/W4313442728","https://openalex.org/W4321125004","https://openalex.org/W4408359828","https://openalex.org/W6668990524","https://openalex.org/W6675435373","https://openalex.org/W6678914141","https://openalex.org/W6686821501","https://openalex.org/W6743384090","https://openalex.org/W6767436834","https://openalex.org/W6772289248"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4405901645","https://openalex.org/W4394895745","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2051487156","https://openalex.org/W2910064364"],"abstract_inverted_index":{"In$k$-means":[0],"clustering,":[1],"the":[2,9,12,38,43,71,78,81,86,92,116,122,127],"selection":[3,33],"of":[4,11,42,73,83,91,100,115,129,144,153],"initial":[5],"seeds":[6,45],"significantly":[7],"influences":[8],"quality":[10,39,62,72],"resulting":[13],"clusters.":[14],"Moreover,":[15],"clustering":[16],"large-sized":[17],"data":[18,146],"introduces":[19],"an":[20],"additional":[21],"challenge":[22],"for":[23],"seed":[24,32,61,75],"selection.":[25],"We":[26],"propose":[27,58],"a":[28,47,59,74,112,134,142,151],"novel":[29,60],"and":[30,40,89,156],"scalable":[31,105],"approach":[34,64,69],"by":[35,76,160],"jointly":[36],"modeling":[37],"diversity":[41],"potential":[44],"through":[46],"principled":[48],"probabilistic":[49],"stochastic":[50],"point":[51],"process.":[52],"To":[53],"this":[54],"end,":[55],"we":[56,107,120],"also":[57],"estimation":[63],"on":[65,111,141],"large":[66],"data.":[67],"Our":[68],"quantifies":[70],"measuring":[77],"divergence":[79],"between":[80,85],"distribution":[82],"similarity":[84],"closest":[87],"neighbors":[88,95],"that":[90,148],"randomly":[93],"chosen":[94],"from":[96],"exhaustive":[97],"stratified":[98],"batches":[99],"samples.":[101],"Unlike":[102],"many":[103],"existing":[104],"approaches,":[106],"do":[108],"not":[109],"rely":[110],"small":[113],"sample":[114],"original":[117],"data;":[118],"instead,":[119],"use":[121],"entire":[123],"data,":[124],"thereby":[125],"minimizing":[126],"chance":[128],"leaving":[130],"out":[131],"information":[132],"about":[133],"potentially":[135],"high-quality":[136],"seed.":[137],"The":[138],"extensive":[139],"evaluation":[140],"set":[143],"benchmark":[145],"shows":[147],"it":[149],"outperforms":[150],"number":[152],"strong,":[154],"well-known,":[155],"recent":[157],"algorithms":[158],"measured":[159],"three":[161],"standard":[162],"metrics.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-01-01T00:00:00"}