{"id":"https://openalex.org/W4408408552","doi":"https://doi.org/10.3389/fdata.2025.1455442","title":"Impact of imbalanced features on large datasets","display_name":"Impact of imbalanced features on large datasets","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408408552","doi":"https://doi.org/10.3389/fdata.2025.1455442","pmid":"https://pubmed.ncbi.nlm.nih.gov/40151465"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2025.1455442","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1455442","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1455442/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1455442/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037364292","display_name":"Waleed Albattah","orcid":"https://orcid.org/0000-0003-0292-7304"},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]},{"id":"https://openalex.org/I4210092650","display_name":"Buraydah Colleges","ror":"https://ror.org/00j0krs40","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210092650"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Waleed Albattah","raw_affiliation_strings":["Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia","institution_ids":["https://openalex.org/I4210092650","https://openalex.org/I156216236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039401755","display_name":"Rehan Ullah Khan","orcid":"https://orcid.org/0000-0003-3323-2732"},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]},{"id":"https://openalex.org/I4210092650","display_name":"Buraydah Colleges","ror":"https://ror.org/00j0krs40","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210092650"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Rehan Ullah Khan","raw_affiliation_strings":["Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia","institution_ids":["https://openalex.org/I4210092650","https://openalex.org/I156216236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039401755"],"corresponding_institution_ids":["https://openalex.org/I156216236","https://openalex.org/I4210092650"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":29.6982,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99527541,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"1455442","last_page":"1455442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","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/T11652","display_name":"Imbalanced Data Classification Techniques","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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9781000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77459716796875},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6760574579238892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6330301761627197},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5881304740905762},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5857867002487183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5507326722145081},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5273134112358093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.479606032371521},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.4643464684486389},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4566454291343689},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4528334140777588},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44168075919151306},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4135807752609253},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3717467188835144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10753104090690613},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08922314643859863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77459716796875},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6760574579238892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330301761627197},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5881304740905762},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5857867002487183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5507326722145081},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5273134112358093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.479606032371521},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.4643464684486389},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4566454291343689},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4528334140777588},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44168075919151306},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4135807752609253},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3717467188835144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10753104090690613},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08922314643859863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2025.1455442","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1455442","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1455442/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:40151465","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40151465","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:doaj.org/article:d2412b067ee74715a742b55a439ebf28","is_oa":true,"landing_page_url":"https://doaj.org/article/d2412b067ee74715a742b55a439ebf28","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:10759854","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11948280","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fdata.2025.1455442","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1455442","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1455442/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408408552.pdf","grobid_xml":"https://content.openalex.org/works/W4408408552.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W592081968","https://openalex.org/W1534477342","https://openalex.org/W1941659294","https://openalex.org/W2104167780","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2165698076","https://openalex.org/W2167912153","https://openalex.org/W2592929672","https://openalex.org/W2619434825","https://openalex.org/W2767106145","https://openalex.org/W2775795276","https://openalex.org/W2788481061","https://openalex.org/W2919115771","https://openalex.org/W2964385717","https://openalex.org/W3217046794","https://openalex.org/W4225697294","https://openalex.org/W4288748549","https://openalex.org/W4320013936","https://openalex.org/W4379057644","https://openalex.org/W4383374987","https://openalex.org/W4385357056","https://openalex.org/W6747218270","https://openalex.org/W6748382702"],"related_works":["https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W4396689146","https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W2004826645","https://openalex.org/W2889302474","https://openalex.org/W2005234362","https://openalex.org/W1997235926"],"abstract_inverted_index":{"The":[0,97,147],"exponential":[1],"growth":[2],"of":[3,47,86,117],"image":[4,72,90],"and":[5,49,76,126,144],"video":[6],"data":[7],"motivates":[8],"the":[9,67,84,115,134],"need":[10],"for":[11,120],"practical":[12],"real-time":[13],"content-based":[14],"searching":[15],"algorithms.":[16],"Features":[17],"play":[18],"a":[19,31],"vital":[20],"role":[21],"in":[22,139],"identifying":[23],"objects":[24],"within":[25],"images.":[26],"However,":[27,56],"feature-based":[28],"classification":[29,68,91],"faces":[30],"challenge":[32],"due":[33],"to":[34,51,109,132],"uneven":[35],"class":[36,41,61,87],"instance":[37],"distribution.":[38],"Ideally,":[39],"each":[40],"should":[42],"have":[43],"an":[44,111,153],"equal":[45],"number":[46],"instances":[48],"features":[50],"ensure":[52],"optimal":[53],"classifier":[54],"performance.":[55],"real-world":[57],"scenarios":[58],"often":[59],"exhibit":[60],"imbalances.":[62],"Thus,":[63],"this":[64],"article":[65],"explores":[66],"framework":[69],"based":[70],"on":[71,89,94],"features,":[73],"analyzing":[74],"balanced":[75],"imbalanced":[77,112],"distributions.":[78],"Through":[79],"extensive":[80],"experimentation,":[81],"we":[82],"examine":[83],"impact":[85],"imbalance":[88],"performance,":[92],"primarily":[93],"large":[95],"datasets.":[96],"comprehensive":[98],"evaluation":[99],"shows":[100],"that":[101],"all":[102],"models":[103],"perform":[104],"better":[105],"with":[106],"balancing":[107,119],"compared":[108],"using":[110],"dataset,":[113],"underscoring":[114],"importance":[116],"dataset":[118],"model":[121],"accuracy.":[122],"Distributed":[123,127],"Gaussian":[124],"(D-GA)":[125],"Poisson":[128],"(D-PO)":[129],"are":[130],"found":[131],"be":[133],"most":[135],"effective":[136],"techniques,":[137],"especially":[138],"improving":[140],"Random":[141],"Forest":[142],"(RF)":[143],"SVM":[145],"models.":[146],"deep":[148],"learning":[149],"experiments":[150],"also":[151],"show":[152],"improvement":[154],"as":[155],"such.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}