{"id":"https://openalex.org/W4413188580","doi":"https://doi.org/10.1007/s10586-025-05512-9","title":"Comprehensive evaluation of data preprocessing and visualization techniques for enhanced classification and sampling","display_name":"Comprehensive evaluation of data preprocessing and visualization techniques for enhanced classification and sampling","publication_year":2025,"publication_date":"2025-08-12","ids":{"openalex":"https://openalex.org/W4413188580","doi":"https://doi.org/10.1007/s10586-025-05512-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10586-025-05512-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-025-05512-9","pdf_url":null,"source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"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":"Cluster Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10586-025-05512-9","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076635776","display_name":"Idriss Dagal","orcid":"https://orcid.org/0000-0002-2073-8956"},"institutions":[{"id":"https://openalex.org/I8666313","display_name":"Beykent University","ror":"https://ror.org/03dcvf827","country_code":"TR","type":"education","lineage":["https://openalex.org/I8666313"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Idriss Dagal","raw_affiliation_strings":["Faculty of Electrical Engineering, Beykent University, Ayaza\u011fa Mahallesi, Had\u0131m Koruyolu Cd. No:19, Sar\u0131yer, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-2073-8956","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Beykent University, Ayaza\u011fa Mahallesi, Had\u0131m Koruyolu Cd. No:19, Sar\u0131yer, Istanbul, Turkey","institution_ids":["https://openalex.org/I8666313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043993807","display_name":"Ambe Harrison","orcid":"https://orcid.org/0000-0002-4353-1261"},"institutions":[{"id":"https://openalex.org/I144693123","display_name":"University of Buea","ror":"https://ror.org/041kdhz15","country_code":"CM","type":"education","lineage":["https://openalex.org/I144693123"]},{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["CM","IN"],"is_corresponding":false,"raw_author_name":"Ambe Harrison","raw_affiliation_strings":["Centre for Research Impact & Outcome , Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, 140401, Punjab, India","Department of Electrical and Electronics Engineering, College of Technology (COT), University of Buea, P.O. Box Buea 63, Buea, Cameroon"],"raw_orcid":"https://orcid.org/0000-0002-4353-1261","affiliations":[{"raw_affiliation_string":"Centre for Research Impact & Outcome , Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, 140401, Punjab, India","institution_ids":["https://openalex.org/I74319210"]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, College of Technology (COT), University of Buea, P.O. Box Buea 63, Buea, Cameroon","institution_ids":["https://openalex.org/I144693123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070075928","display_name":"AL-Wesabi Ibrahim","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I24407930","display_name":"Hunan University of Science and Engineering","ror":"https://ror.org/04ymz0q33","country_code":"CN","type":"education","lineage":["https://openalex.org/I24407930"]},{"id":"https://openalex.org/I85461943","display_name":"Saveetha University","ror":"https://ror.org/0034me914","country_code":"IN","type":"education","lineage":["https://openalex.org/I85461943"]}],"countries":["CN","IN"],"is_corresponding":false,"raw_author_name":"AL-Wesabi Ibrahim","raw_affiliation_strings":["College of Electrical and Information Engineering in Hunan University, Hunan, 410083, China","Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, India"],"raw_orcid":"https://orcid.org/0000-0003-1848-427X","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering in Hunan University, Hunan, 410083, China","institution_ids":["https://openalex.org/I16609230","https://openalex.org/I24407930"]},{"raw_affiliation_string":"Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, India","institution_ids":["https://openalex.org/I85461943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024744773","display_name":"Wulfran Fendzi Mbasso","orcid":"https://orcid.org/0000-0002-4049-0716"},"institutions":[{"id":"https://openalex.org/I146367977","display_name":"Applied Science Private University","ror":"https://ror.org/01ah6nb52","country_code":"JO","type":"education","lineage":["https://openalex.org/I146367977"]},{"id":"https://openalex.org/I163423212","display_name":"University of Douala","ror":"https://ror.org/02zr5jr81","country_code":"CM","type":"education","lineage":["https://openalex.org/I163423212"]}],"countries":["CM","JO"],"is_corresponding":false,"raw_author_name":"Wulfran Fendzi Mbasso","raw_affiliation_strings":["Applied Science Research Center, Applied Science Private University, Amman, Jordan","Technology and Applied Sciences Laboratory, U.I.T of Douala, Douala University of Douala, P.O.Box 8689, Douala, Cameroon"],"raw_orcid":"https://orcid.org/0000-0002-4049-0716","affiliations":[{"raw_affiliation_string":"Applied Science Research Center, Applied Science Private University, Amman, Jordan","institution_ids":["https://openalex.org/I146367977"]},{"raw_affiliation_string":"Technology and Applied Sciences Laboratory, U.I.T of Douala, Douala University of Douala, P.O.Box 8689, Douala, Cameroon","institution_ids":["https://openalex.org/I163423212"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076635776"],"corresponding_institution_ids":["https://openalex.org/I8666313"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09425427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.989799976348877,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.989799976348877,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9886000156402588,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9617000222206116,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9320080280303955},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6789271831512451},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6153474450111389},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6006061434745789},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5935600399971008},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4820769429206848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43363434076309204},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.391484797000885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3334733247756958},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11690965294837952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9320080280303955},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6789271831512451},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6153474450111389},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6006061434745789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5935600399971008},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4820769429206848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43363434076309204},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.391484797000885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3334733247756958},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11690965294837952},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10586-025-05512-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-025-05512-9","pdf_url":null,"source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"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":"Cluster Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10586-025-05512-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-025-05512-9","pdf_url":null,"source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"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":"Cluster Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1971781829","https://openalex.org/W2013885787","https://openalex.org/W2045831561","https://openalex.org/W2323331405","https://openalex.org/W2437990191","https://openalex.org/W2945205820","https://openalex.org/W2990518194","https://openalex.org/W3015872372","https://openalex.org/W3096831136","https://openalex.org/W3111084717","https://openalex.org/W4213114605","https://openalex.org/W4213347399","https://openalex.org/W4220957979","https://openalex.org/W4226323522","https://openalex.org/W4292425254","https://openalex.org/W4297550060","https://openalex.org/W4308091351","https://openalex.org/W4378649810","https://openalex.org/W4385988712","https://openalex.org/W4386171458","https://openalex.org/W4390416991","https://openalex.org/W4390674031","https://openalex.org/W4392167057","https://openalex.org/W4392594314","https://openalex.org/W4404737272","https://openalex.org/W4404737346","https://openalex.org/W4404737379","https://openalex.org/W4404737435","https://openalex.org/W4404737451","https://openalex.org/W4404738221","https://openalex.org/W4404738223","https://openalex.org/W4404761309","https://openalex.org/W4405662637","https://openalex.org/W4406059588","https://openalex.org/W4406059619","https://openalex.org/W4408477302","https://openalex.org/W6810830792"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2952736244"],"abstract_inverted_index":{"Abstract":[0],"Effective":[1],"representation":[2],"and":[3,30,41,87,116,141,165,172,188,212,229,241,247,261,270],"visualization":[4,144],"of":[5,10,23,69,84,91,108,256,273],"data":[6,11,28,37,61,77,109,148],"are":[7],"critical":[8],"components":[9],"analysis,":[12],"particularly":[13],"in":[14,27,35,53,66,94,105,112,134,161,185,196,259],"classification":[15,197,268],"tasks.":[16,198],"This":[17,250],"paper":[18],"presents":[19],"a":[20,143],"comprehensive":[21,251],"evaluation":[22,252],"various":[24],"functions":[25,258],"employed":[26],"preprocessing":[29,260],"visualization,":[31],"emphasizing":[32],"their":[33],"roles":[34],"enhancing":[36,88,117],"representation,":[38],"facilitating":[39],"classification,":[40],"optimizing":[42],"sampling":[43],"techniques.":[44],"We":[45],"explore":[46],"the":[47,67,82,89,123,177,204,209,218,235,254],"Jitter":[48,236],"function,":[49,125,220],"which":[50,126],"mitigates":[51],"overplotting":[52],"visualizations":[54],"by":[55],"introducing":[56],"small":[57],"random":[58,154,205],"variations":[59],"to":[60,146,266],"points,":[62],"thereby":[63],"improving":[64],"clarity":[65],"depiction":[68],"class":[70,92,114],"distributions.":[71],"The":[72,97,153,199],"hexagonal":[73,79],"binning":[74],"function":[75,99,155,179,206,237],"aggregates":[76],"into":[78],"grids,":[80],"enabling":[81],"identification":[83],"density":[85],"patterns":[86],"understanding":[90],"separability":[93],"two-dimensional":[95],"space.":[96],"center":[98,219],"is":[100,156,180],"examined":[101],"for":[102,138,158,169,182,192],"its":[103,159,183],"utility":[104],"computing":[106],"centroids":[107],"clusters,":[110],"aiding":[111],"visualizing":[113,262],"distributions":[115,150],"clustering":[118],"algorithms.":[119],"Additionally,":[120],"we":[121],"investigate":[122],"swarm":[124,136],"serves":[127],"dual":[128],"purposes":[129],"as":[130,142],"an":[131],"optimization":[132,137],"technique":[133],"particle":[135],"feature":[139],"selection":[140],"tool":[145],"illustrate":[147],"point":[149],"without":[151],"overlap.":[152],"discussed":[157],"role":[160],"generating":[162],"synthetic":[163],"datasets":[164],"initializing":[166],"parameters,":[167],"crucial":[168],"achieving":[170],"balanced":[171],"representative":[173],"training":[174],"samples.":[175],"Lastly,":[176],"square":[178],"evaluated":[181],"application":[184],"distance":[186],"calculations":[187],"error":[189],"metrics,":[190],"essential":[191],"assessing":[193],"model":[194],"performance":[195],"experimental":[200],"results":[201],"reveal":[202],"that":[203],"consistently":[207],"shows":[208],"highest":[210],"means":[211,240],"variability":[213,227],"across":[214],"most":[215],"distributions,":[216],"while":[217],"despite":[221],"exhibiting":[222,244],"lower":[223,239],"means,":[224],"demonstrates":[225],"higher":[226],"(CV)":[228],"entropy,":[230],"indicating":[231],"greater":[232],"uncertainty.":[233,249],"Conversely,":[234],"displays":[238],"variances,":[242],"typically":[243],"more":[245],"predictability":[246],"less":[248],"highlights":[253],"importance":[255],"these":[257],"data,":[263],"ultimately":[264],"contributing":[265],"improved":[267],"outcomes":[269],"enhanced":[271],"interpretability":[272],"data-driven":[274],"insights.":[275]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}