{"id":"https://openalex.org/W4384935487","doi":"https://doi.org/10.1186/s40537-023-00798-1","title":"Big data: an optimized approach for cluster initialization","display_name":"Big data: an optimized approach for cluster initialization","publication_year":2023,"publication_date":"2023-07-20","ids":{"openalex":"https://openalex.org/W4384935487","doi":"https://doi.org/10.1186/s40537-023-00798-1"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-023-00798-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00798-1","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00798-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00798-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101574199","display_name":"Marina Gul","orcid":"https://orcid.org/0000-0002-3259-198X"},"institutions":[{"id":"https://openalex.org/I68288478","display_name":"Sukkur IBA University","ror":"https://ror.org/03e5jvk98","country_code":"PK","type":"education","lineage":["https://openalex.org/I68288478"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Marina Gul","raw_affiliation_strings":["Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-3259-198X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan","institution_ids":["https://openalex.org/I68288478"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053255220","display_name":"M. Abdul Rehman","orcid":"https://orcid.org/0000-0001-7412-8531"},"institutions":[{"id":"https://openalex.org/I68288478","display_name":"Sukkur IBA University","ror":"https://ror.org/03e5jvk98","country_code":"PK","type":"education","lineage":["https://openalex.org/I68288478"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"M. Abdul Rehman","raw_affiliation_strings":["Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan"],"raw_orcid":"https://orcid.org/0000-0001-7412-8531","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan","institution_ids":["https://openalex.org/I68288478"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053255220"],"corresponding_institution_ids":["https://openalex.org/I68288478"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":3.2393,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93475139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8867303729057312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8046965599060059},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7596632242202759},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6534003615379333},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6004068851470947},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5206338763237},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.47740522027015686},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.47070619463920593},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46528974175453186},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4609236717224121},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43027758598327637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18882447481155396}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8867303729057312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046965599060059},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7596632242202759},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6534003615379333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6004068851470947},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5206338763237},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.47740522027015686},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.47070619463920593},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46528974175453186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4609236717224121},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43027758598327637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18882447481155396},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-023-00798-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00798-1","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00798-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f57a567d15e34bd49da172ef004824bb","is_oa":true,"landing_page_url":"https://doaj.org/article/f57a567d15e34bd49da172ef004824bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 10, Iss 1, Pp 1-19 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-023-00798-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00798-1","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00798-1","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4384935487.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1585610988","https://openalex.org/W1981276685","https://openalex.org/W2008981950","https://openalex.org/W2011430131","https://openalex.org/W2016381774","https://openalex.org/W2029698681","https://openalex.org/W2036216970","https://openalex.org/W2049633694","https://openalex.org/W2069564486","https://openalex.org/W2086959852","https://openalex.org/W2108399535","https://openalex.org/W2116762767","https://openalex.org/W2142458924","https://openalex.org/W2142827986","https://openalex.org/W2150593711","https://openalex.org/W2324662912","https://openalex.org/W2753555091","https://openalex.org/W2787220232","https://openalex.org/W2789548662","https://openalex.org/W2790613489","https://openalex.org/W2794846143","https://openalex.org/W2841402245","https://openalex.org/W2926997109","https://openalex.org/W2940320374","https://openalex.org/W2964087164","https://openalex.org/W2999988112","https://openalex.org/W3012123778","https://openalex.org/W3019913914","https://openalex.org/W3100095447","https://openalex.org/W3107196492","https://openalex.org/W3112135300","https://openalex.org/W3155492258","https://openalex.org/W3160252920","https://openalex.org/W3199046788","https://openalex.org/W4241252752","https://openalex.org/W4292941874","https://openalex.org/W4293558809","https://openalex.org/W4316019788","https://openalex.org/W6636657728"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"Abstract":[0],"The":[1,82],"k-means,":[2],"one":[3],"of":[4,45,142,148],"the":[5,43,129,136,140],"most":[6],"widely":[7],"used":[8],"clustering":[9,77],"algorithm,":[10,67],"is":[11,31],"not":[12],"only":[13],"faster":[14],"in":[15,113],"computation":[16],"but":[17],"also":[18],"produces":[19],"comparatively":[20],"better":[21,76,92],"clusters.":[22],"However,":[23],"it":[24,30,52],"has":[25],"two":[26],"major":[27],"downsides,":[28],"first":[29,84],"sensitive":[32],"to":[33,57,135],"initialize":[34],"k":[35,107],"value":[36],"and":[37,65,122],"secondly,":[38],"especially":[39],"for":[40,75],"larger":[41],"datasets,":[42],"number":[44,147],"iterations":[46],"could":[47],"be":[48],"very":[49],"large,":[50],"making":[51],"computationally":[53],"hard.":[54],"In":[55],"order":[56],"address":[58],"these":[59],"issues,":[60],"we":[61],"proposed":[62,130],"a":[63,114],"scalable":[64],"cost-effective":[66],"called":[68],"R-k-means,":[69],"which":[70],"provides":[71],"an":[72],"optimized":[73],"solution":[74],"large":[78],"scale":[79],"high-dimensional":[80],"datasets.":[81,124],"algorithm":[83],"selects":[85],"O(R)":[86],"initial":[87,93,108],"points":[88,101],"then":[89,103],"reselect":[90],"O(l)":[91],"points,":[94],"using":[95,119],"distance":[96],"probability":[97],"from":[98],"dataset.":[99],"These":[100],"are":[102],"again":[104],"clustered":[105],"into":[106],"points.":[109],"An":[110],"empirical":[111],"study":[112],"controlled":[115],"environment":[116],"was":[117],"conducted":[118],"both":[120],"simulated":[121],"real":[123],"Experimental":[125],"results":[126],"showed":[127],"that":[128],"approach":[131],"outperformed":[132],"as":[133],"compared":[134],"previous":[137],"approaches":[138],"when":[139],"size":[141],"data":[143],"increases":[144],"with":[145],"increasing":[146],"dimensions.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}