{"id":"https://openalex.org/W592081968","doi":null,"title":"The Impact of Imbalanced Training Data for Convolutional Neural Networks","display_name":"The Impact of Imbalanced Training Data for Convolutional Neural Networks","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W592081968","mag":"592081968"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-166451","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166451","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023496789","display_name":"David Masko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Masko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030571885","display_name":"Paulina Hensman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paulina Hensman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":196,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.8827999830245972,"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":0.8827999830245972,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09700000286102295,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.015399999916553497,"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/imbalanced-training-data","display_name":"imbalanced training data","score":0.9079999923706055},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.925000011920929},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9950000047683716},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.9940000176429749},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9660000205039978},{"id":"https://openalex.org/keywords/oversampling","display_name":"oversampling","score":0.953000009059906},{"id":"https://openalex.org/keywords/classification-performance","display_name":"classification performance","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6424375176429749},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6167507767677307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938119292259216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5331088304519653},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5274860262870789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45641544461250305},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4253844618797302},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19568514823913574},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:DiVA.org:kth-166451","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166451","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},{"id":"mag:592081968","doi":null,"is_oa":false,"landing_page_url":"http://kth.diva-portal.org/smash/record.jsf?pid=diva2%3A811111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-166451","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166451","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1513762125","https://openalex.org/W1514205146","https://openalex.org/W1527373413","https://openalex.org/W1849277567","https://openalex.org/W2014850486","https://openalex.org/W2015861736","https://openalex.org/W2064630666","https://openalex.org/W2114968414","https://openalex.org/W2117130368","https://openalex.org/W2117539524","https://openalex.org/W2118978333","https://openalex.org/W2130325614","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2148349024","https://openalex.org/W2148461049","https://openalex.org/W2155893237","https://openalex.org/W2161000554","https://openalex.org/W2166528042","https://openalex.org/W2394932179","https://openalex.org/W2963606038","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W7065027540","https://openalex.org/W2810228013","https://openalex.org/W2767106145","https://openalex.org/W3091217939","https://openalex.org/W3130150271","https://openalex.org/W2619434825","https://openalex.org/W4389950937","https://openalex.org/W3216472057","https://openalex.org/W3044929250","https://openalex.org/W7038466804"],"abstract_inverted_index":{"This":[0],"thesis":[1],"empirically":[2],"studies":[3],"the":[4,21,44,79,114,123,129,134,148,153],"impact":[5,102,149],"of":[6,30,55,57,66,133,150],"imbalanced":[7,93,124],"training":[8,38,70,87,94,111,125,154],"data":[9,95,112],"on":[10,103,122],"Convolutional":[11],"Neural":[12],"Network":[13],"(CNN)":[14],"performance":[15,82,105],"in":[16,106,152],"image":[17],"classification.":[18],"Images":[19],"from":[20],"CIFAR-10":[22],"dataset,":[23],"a":[24,51,76,99,143],"set":[25],"containing":[26],"60":[27],"000":[28],"images":[29,56,65],"10":[31],"different":[32,41],"classes,":[33],"are":[34,72],"used":[35,73,121],"to":[36,74,127,131,146],"create":[37],"sets":[39,49,71,126],"with":[40],"distributions":[42],"between":[43],"classes.":[45],"For":[46],"example,":[47],"some":[48],"contain":[50,62],"disproportionately":[52],"large":[53],"amount":[54],"one":[58,67],"class,":[59],"and":[60,78,108],"others":[61],"very":[63],"few":[64],"class.":[68],"These":[69],"train":[75],"CNN,":[77,107],"networks\u2019":[80],"classification":[81],"is":[83,120,138,142],"measured":[84],"for":[85],"each":[86],"set.":[88,136],"The":[89],"results":[90],"show":[91],"that":[92,109,132,140],"can":[96],"potentially":[97],"have":[98],"severely":[100],"negative":[101],"overall":[104],"balanced":[110,135],"yields":[113],"best":[115],"results.":[116],"Following":[117],"this,":[118],"oversampling":[119,141],"increase":[128],"performances":[130],"It":[137],"concluded":[139],"viable":[144],"way":[145],"counter":[147],"imbalances":[151],"data.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}