{"id":"https://openalex.org/W7225755059","doi":"https://doi.org/10.1186/s40537-026-01590-7","title":"Classification of metal surface defects using a hybrid deep learning and machine learning approach","display_name":"Classification of metal surface defects using a hybrid deep learning and machine learning approach","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225755059","doi":"https://doi.org/10.1186/s40537-026-01590-7"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-026-01590-7","doi":"https://doi.org/10.1186/s40537-026-01590-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01590-7","pdf_url":null,"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,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s40537-026-01590-7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101801813","display_name":"Oya K\u0131lc\u0131","orcid":"https://orcid.org/0000-0002-7993-9875","observed_orcids":["https://orcid.org/0000-0002-7993-9875"]},"institutions":[{"id":"https://openalex.org/I4210153056","display_name":"KTO Karatay University","ror":"https://ror.org/054341q84","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210153056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Oya Kilci","raw_affiliation_strings":["Vocational School of Trade and Industry, Department of Mechatronics, KTO Karatay University, Konya, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-7993-9875","affiliations":[{"raw_affiliation_string":"Vocational School of Trade and Industry, Department of Mechatronics, KTO Karatay University, Konya, T\u00fcrkiye","institution_ids":["https://openalex.org/I4210153056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012042437","display_name":"Murat K\u00f6kl\u00fc","orcid":"https://orcid.org/0000-0002-2737-2360","observed_orcids":["https://orcid.org/0000-0002-2737-2360"]},"institutions":[{"id":"https://openalex.org/I137996928","display_name":"Sel\u00e7uk University","ror":"https://ror.org/045hgzm75","country_code":"TR","type":"education","lineage":["https://openalex.org/I137996928"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Murat Koklu","raw_affiliation_strings":["Technology Faculty, Department of Computer Engineering, Selcuk University, Konya, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-2737-2360","affiliations":[{"raw_affiliation_string":"Technology Faculty, Department of Computer Engineering, Selcuk University, Konya, T\u00fcrkiye","institution_ids":["https://openalex.org/I137996928"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029763877","display_name":"Mohannad Alkanan","orcid":"https://orcid.org/0000-0003-3736-7749","observed_orcids":["https://orcid.org/0000-0003-3736-7749"]},"institutions":[{"id":"https://openalex.org/I4626487","display_name":"King Faisal University","ror":"https://ror.org/00dn43547","country_code":"SA","type":"education","lineage":["https://openalex.org/I4626487"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohannad Alkanan","raw_affiliation_strings":["Department of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa, 31982, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa, 31982, Saudi Arabia","institution_ids":["https://openalex.org/I4626487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013837562","display_name":"Yonis Gulzar","orcid":"https://orcid.org/0000-0002-6515-1569","observed_orcids":["https://orcid.org/0000-0002-6515-1569"]},"institutions":[{"id":"https://openalex.org/I4626487","display_name":"King Faisal University","ror":"https://ror.org/00dn43547","country_code":"SA","type":"education","lineage":["https://openalex.org/I4626487"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Yonis Gulzar","raw_affiliation_strings":["Department of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa, 31982, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6515-1569","affiliations":[{"raw_affiliation_string":"Department of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa, 31982, Saudi Arabia","institution_ids":["https://openalex.org/I4626487"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012042437","https://openalex.org/A5013837562"],"corresponding_institution_ids":["https://openalex.org/I137996928","https://openalex.org/I4626487"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12169","display_name":"Non-Destructive Testing Techniques","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0005000000237487257,"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/metal-surface-defects","display_name":"metal surface defects","score":0.9909999966621399},{"id":"https://openalex.org/keywords/defect-classification","display_name":"defect classification","score":0.9919999837875366},{"id":"https://openalex.org/keywords/hybrid-deep-learning","display_name":"hybrid deep learning model","score":0.8899999856948853},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.7279999852180481},{"id":"https://openalex.org/keywords/image-based-defect-detection","display_name":"image-based defect detection","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7849000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7847999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307000160217285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2761000096797943}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s40537-026-01590-7","doi":"https://doi.org/10.1186/s40537-026-01590-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01590-7","pdf_url":null,"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,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s40537-026-01590-7","doi":"https://doi.org/10.1186/s40537-026-01590-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01590-7","pdf_url":null,"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,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331156","display_name":"King Faisal University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4381895464","https://openalex.org/W6893137790","https://openalex.org/W7213257517","https://openalex.org/W7171701146","https://openalex.org/W4402530774","https://openalex.org/W7159670394","https://openalex.org/W7163609975","https://openalex.org/W7214602961","https://openalex.org/W7213542495","https://openalex.org/W4407209487"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,75],"comprehensive":[4],"hybrid":[5,48,222],"deep":[6,45,191,227],"learning":[7,10,46,192,228],"and":[8,17,24,38,47,58,83,124,200,244,251],"machine":[9],"framework":[11],"for":[12,161],"steel":[13],"surface":[14],"defect":[15],"classification":[16,49],"evaluates":[18],"its":[19],"robustness":[20],"under":[21,239],"controlled,":[22],"augmented,":[23],"external":[25,96],"benchmarking":[26],"conditions.":[27],"Six":[28],"convolutional":[29],"neural":[30],"network":[31],"backbones":[32],"MobileNet-V2,":[33],"ResNet-50,":[34],"DenseNet-121,":[35],"EfficientNet-B0,":[36],"U-Net,":[37],"LSDNet":[39,162],"were":[40,62,213],"evaluated":[41],"using":[42,101],"both":[43],"end-to-end":[44,190,226,234],"with":[50,156,188],"Logistic":[51,178],"Regression,":[52],"Support":[53],"Vector":[54],"Machine,":[55],"Decision":[56,164],"Tree,":[57],"K-Nearest":[59],"Neighbors.":[60],"Experiments":[61],"conducted":[63],"on":[64,216,219,229],"the":[65,84,129,135,157,181,189,195,258],"original":[66,130],"NEU":[67,78,131],"dataset":[68,79,86],"containing":[69,80,87],"1,800":[70],"images":[71,89],"from":[72,90],"six":[73],"classes,":[74],"source-disjoint":[76],"augmented":[77],"3,600":[81],"images,":[82],"GC10-DET":[85,170,217],"2,312":[88],"ten":[91],"classes":[92],"as":[93],"an":[94],"independent":[95],"benchmark.":[97],"Performance":[98],"was":[99],"assessed":[100],"five-fold":[102],"cross-validation,":[103],"out-of-fold":[104],"predictions,":[105],"accuracy,":[106,108,142],"balanced":[107,201],"macro":[109,111,113,197],"precision,":[110],"recall,":[112],"F1-score,":[114],"Matthews":[115],"Correlation":[116],"Coefficient,":[117],"Cohen\u2019s":[118],"Kappa,":[119],"ROC-AUC,":[120],"bootstrap":[121],"confidence":[122],"intervals,":[123],"statistical":[125],"significance":[126],"tests.":[127],"On":[128],"dataset,":[132],"eight":[133],"of":[134,257],"30":[136],"backbone\u2013head":[137],"combinations":[138],"achieved":[139,180,194],"perfect":[140],"OOF":[141],"while":[143],"all":[144],"configurations":[145],"exceeded":[146],"0.9867,":[147],"indicating":[148],"benchmark":[149],"saturation.":[150],"Augmentation":[151],"mainly":[152],"benefited":[153],"weaker":[154],"configurations,":[155],"largest":[158],"improvement":[159],"observed":[160],"+":[163,177],"Tree":[165],"(+":[166],"0.0089).":[167],"In":[168],"contrast,":[169],"produced":[171],"substantially":[172],"greater":[173],"performance":[174],"variation.":[175],"DenseNet-121":[176,187],"Regression":[179],"highest":[182,196],"overall":[183],"accuracy":[184,202],"(0.8984),":[185],"whereas":[186,233],"head":[193],"F1-score":[198],"(0.8681)":[199],"(0.8609).":[203],"Statistical":[204],"analyses":[205],"further":[206],"showed":[207],"that":[208],"differences":[209],"among":[210],"classifier":[211],"heads":[212],"more":[214,237],"pronounced":[215],"than":[218],"NEU.":[220],"Overall,":[221],"classifiers":[223],"can":[224],"match":[225],"highly":[230],"separable":[231],"benchmarks,":[232],"representations":[235],"become":[236],"important":[238],"class":[240],"imbalance,":[241],"visual":[242],"overlap,":[243],"increased":[245],"distributional":[246],"complexity.":[247],"Grad-CAM,":[248],"Grad-CAM++,":[249],"LIME,":[250],"SHAP":[252],"provided":[253],"complementary":[254],"qualitative":[255],"explanations":[256],"image":[259],"regions":[260],"contributing":[261],"to":[262],"model":[263],"predictions.":[264]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-11T00:00:00"}