{"id":"https://openalex.org/W7224837299","doi":"https://doi.org/10.3390/s26216864","title":"An Explainable AI-Based Deep Learning Framework with Spatial and Multi-Head Attention for Bubble Detection in Tire Shearography Images: An Industrial Case Study","display_name":"An Explainable AI-Based Deep Learning Framework with Spatial and Multi-Head Attention for Bubble Detection in Tire Shearography Images: An Industrial Case Study","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224837299","doi":"https://doi.org/10.3390/s26216864"},"language":"en","primary_location":{"id":"doi:10.3390/s26216864","doi":"https://doi.org/10.3390/s26216864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26216864","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/s26216864","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075742881","display_name":"Radhwan A. A. Saleh","orcid":"https://orcid.org/0000-0001-9945-3672","observed_orcids":["https://orcid.org/0000-0001-9945-3672"]},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]},{"id":"https://openalex.org/I282159120","display_name":"\u0130stanbul Ni\u015fanta\u015f\u0131 \u00dcniversitesi","ror":"https://ror.org/04tah3159","country_code":"TR","type":"education","lineage":["https://openalex.org/I282159120"]}],"countries":["SA","TR"],"is_corresponding":false,"raw_author_name":"Radhwan A. A. Saleh","raw_affiliation_strings":["Faculty of Engineering and Architecture, Ni\u015fanta\u015f\u0131 University, Istanbul 34485, T\u00fcrkiye","Interdisciplinary Research Center for Construction and Building Materials, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9945-3672","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Architecture, Ni\u015fanta\u015f\u0131 University, Istanbul 34485, T\u00fcrkiye","institution_ids":["https://openalex.org/I282159120"]},{"raw_affiliation_string":"Interdisciplinary Research Center for Construction and Building Materials, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006334862","display_name":"Mehmet Zeki Konyar","orcid":"https://orcid.org/0000-0001-8914-5553","observed_orcids":["https://orcid.org/0000-0001-8914-5553"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Mehmet Zeki Konyar","raw_affiliation_strings":["Department of Software Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye","DigiNova Informat Tech Res Inc., KOU Teknopark, Kocaeli 41275, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0001-8914-5553","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye","institution_ids":["https://openalex.org/I51826884"]},{"raw_affiliation_string":"DigiNova Informat Tech Res Inc., KOU Teknopark, Kocaeli 41275, T\u00fcrkiye","institution_ids":["https://openalex.org/I51826884"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042591909","display_name":"Humam AbuAlkebash","orcid":"https://orcid.org/0000-0001-7571-3783","observed_orcids":["https://orcid.org/0000-0001-7571-3783"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Humam AbuAlkebash","raw_affiliation_strings":["Robotics and Artificial Intelligence Program, Department of Electronics and Automation, Ford Otosan \u0130hsaniye Automotive High Vocational School (FOIMYO), Kocaeli University, Kocaeli 41650, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0001-7571-3783","affiliations":[{"raw_affiliation_string":"Robotics and Artificial Intelligence Program, Department of Electronics and Automation, Ford Otosan \u0130hsaniye Automotive High Vocational School (FOIMYO), Kocaeli University, Kocaeli 41650, T\u00fcrkiye","institution_ids":["https://openalex.org/I51826884"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062149542","display_name":"Farid Al-Areqi","orcid":"https://orcid.org/0000-0001-7607-993X","observed_orcids":["https://orcid.org/0000-0001-7607-993X"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Farid Al-Areqi","raw_affiliation_strings":["Department of Biomedical Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0001-7607-993X","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye","institution_ids":["https://openalex.org/I51826884"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030922232","display_name":"H. Metin Ertun\u00e7","orcid":"https://orcid.org/0000-0003-1874-3104","observed_orcids":["https://orcid.org/0000-0003-1874-3104"]},"institutions":[{"id":"https://openalex.org/I51826884","display_name":"Kocaeli \u00dcniversitesi","ror":"https://ror.org/0411seq30","country_code":"TR","type":"education","lineage":["https://openalex.org/I51826884"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Huseyin Metin Ertunc","raw_affiliation_strings":["Department of Mechatronic Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0003-1874-3104","affiliations":[{"raw_affiliation_string":"Department of Mechatronic Engineering, Kocaeli University, Kocaeli 41001, T\u00fcrkiye","institution_ids":["https://openalex.org/I51826884"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006334862"],"corresponding_institution_ids":["https://openalex.org/I51826884"],"apc_list":{"value":2600,"currency":"CHF","value_usd":3137},"apc_paid":{"value":2600,"currency":"CHF","value_usd":3137},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.863699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"21","first_page":"6864","last_page":"6864"},"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":0.9218999743461609,"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":0.9218999743461609,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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":0.012799999676644802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/air-bubble-detection","display_name":"air bubble detection","score":0.8899999856948853},{"id":"https://openalex.org/keywords/explainable-deep-learning","display_name":"explainable deep learning","score":0.7879999876022339},{"id":"https://openalex.org/keywords/multi-head-attention","display_name":"multi-head attention","score":0.8600000143051147},{"id":"https://openalex.org/keywords/densenet-201","display_name":"DenseNet201","score":0.9599999785423279},{"id":"https://openalex.org/keywords/grad-cam","display_name":"Grad-CAM","score":0.8600000143051147},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.9980000257492065},{"id":"https://openalex.org/keywords/non-destructive-testing","display_name":"non-destructive testing","score":0.7580000162124634},{"id":"https://openalex.org/keywords/manufacturing-quality-control","display_name":"manufacturing quality control","score":0.7400000095367432},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C138246806","wikidata":"https://www.wikidata.org/wiki/Q638475","display_name":"Shearography","level":3,"score":0.8676999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.730400025844574},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6428999900817871},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C155296804","wikidata":"https://www.wikidata.org/wiki/Q30329684","display_name":"Tread","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C154290570","wikidata":"https://www.wikidata.org/wiki/Q1756768","display_name":"Co-occurrence","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25429999828338623},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/s26216864","doi":"https://doi.org/10.3390/s26216864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26216864","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/s26216864","doi":"https://doi.org/10.3390/s26216864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26216864","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2209436463","https://openalex.org/W2494151295","https://openalex.org/W2525076183","https://openalex.org/W2799213142","https://openalex.org/W2807880213","https://openalex.org/W2886683423","https://openalex.org/W2896082628","https://openalex.org/W2897751119","https://openalex.org/W2979739834","https://openalex.org/W2998234644","https://openalex.org/W3001436122","https://openalex.org/W3006931321","https://openalex.org/W3113879609","https://openalex.org/W3119997354","https://openalex.org/W3163141002","https://openalex.org/W4210270665","https://openalex.org/W4220805210","https://openalex.org/W4281261257","https://openalex.org/W4283644514","https://openalex.org/W4308427199","https://openalex.org/W4310191216","https://openalex.org/W4313022330","https://openalex.org/W4318344284","https://openalex.org/W4362665139","https://openalex.org/W4385068134","https://openalex.org/W4386142022","https://openalex.org/W4387673442","https://openalex.org/W4391174849","https://openalex.org/W4391300512","https://openalex.org/W4395013054","https://openalex.org/W4397002046","https://openalex.org/W4398208467","https://openalex.org/W4401397131","https://openalex.org/W4401877457","https://openalex.org/W4404271706","https://openalex.org/W4406336790","https://openalex.org/W4408877509","https://openalex.org/W4409001714","https://openalex.org/W4409902664","https://openalex.org/W7102581887","https://openalex.org/W7126238196","https://openalex.org/W7141861399"],"related_works":["https://openalex.org/W4404271706","https://openalex.org/W4283644514","https://openalex.org/W2998234644","https://openalex.org/W4310191216","https://openalex.org/W4415401080","https://openalex.org/W2896082628","https://openalex.org/W4407775410","https://openalex.org/W4397002046","https://openalex.org/W4376873434","https://openalex.org/W4391300512"],"abstract_inverted_index":{"The":[0,77,126,203,253],"safety":[1],"and":[2,57,103,120,180,193,201,211,231,267],"reliability":[3],"of":[4,13,134,155,172,178,187],"automobile":[5],"tires":[6],"depend":[7],"directly":[8],"on":[9,49,130,245],"the":[10,34,146,156,162,185,191,219,240],"early":[11],"detection":[12,72,261],"internal":[14],"defects,":[15],"since":[16],"undetected":[17],"air":[18],"bubbles":[19],"between":[20],"rubber":[21],"layers":[22],"can":[23],"propagate":[24],"into":[25],"catastrophic":[26],"in-service":[27],"failures.":[28],"Although":[29],"digital":[30],"shearography":[31,75,136],"has":[32],"become":[33],"preferred":[35],"non-destructive":[36],"testing":[37],"technique":[38],"for":[39,69,272],"revealing":[40],"such":[41],"subsurface":[42],"anomalies,":[43],"its":[44,243],"industrial":[45,273],"interpretation":[46],"still":[47],"relies":[48],"manual":[50],"expert":[51],"assessment,":[52],"which":[53],"is":[54],"slow,":[55],"operator-dependent,":[56],"difficult":[58],"to":[59],"audit.":[60],"This":[61],"study":[62],"proposes":[63],"an":[64,181],"explainable":[65],"deep":[66],"learning":[67],"framework":[68,78,254],"automated":[70],"bubble":[71,260],"in":[73,223],"tire":[74,143],"images.":[76,158],"couples":[79],"a":[80,88,104,131,169,175,265],"DenseNet201":[81,164,192,194],"backbone":[82],"with":[83,174],"two":[84],"complementary":[85],"attention":[86],"modules:":[87],"Spatial":[89],"Aggregation":[90],"Pyramid":[91],"(SAP)":[92],"that":[93,109,115,239],"refines":[94],"multi-scale":[95],"feature":[96],"representations":[97],"through":[98],"dilated":[99],"depth-wise":[100],"separable":[101],"convolutions,":[102],"Multi-Head":[105],"Attention":[106],"(MHA)":[107],"module":[108],"models":[110],"long-range":[111],"contextual":[112],"dependencies,":[113],"so":[114],"both":[116],"fine-grained":[117],"texture":[118],"variations":[119],"global":[121],"spatial":[122],"cues":[123],"are":[124],"captured.":[125],"model":[127,167,241],"was":[128],"developed":[129],"class-balanced":[132],"set":[133],"1162":[135],"images":[137],"(581":[138],"per":[139],"class)":[140],"from":[141],"174":[142],"treads":[144],"at":[145],"Pirelli":[147],"\u0130zmit":[148],"factory,":[149],"obtained":[150],"by":[151,214],"randomly":[152],"excluding":[153],"part":[154],"non-defective":[157],"Under":[159],"5-fold":[160],"cross-validation,":[161],"proposed":[163],"SAP":[165,195],"MHA":[166],"reached":[168],"mean":[170],"accuracy":[171,262],"0.962":[173],"standard":[176],"deviation":[177],"0.006":[179],"AUC":[182],"(area":[183],"under":[184],"curve)":[186],"0.9794,":[188],"consistently":[189],"outperforming":[190],"baselines":[196],"across":[197,207],"accuracy,":[198],"precision,":[199],"recall,":[200],"F1-score.":[202],"improvements":[204],"were":[205,212,236],"consistent":[206],"all":[208],"five":[209],"folds":[210],"supported":[213],"statistical":[215],"testing.":[216],"To":[217],"address":[218],"black-box":[220],"concern":[221],"inherent":[222],"safety-critical":[224],"inspection,":[225],"Gradient-weighted":[226],"Class":[227],"Activation":[228],"Mapping":[229],"(Grad-CAM)":[230],"SHapley":[232],"Additive":[233],"exPlanations":[234],"(SHAP)":[235],"integrated,":[237],"demonstrating":[238],"bases":[242],"decisions":[244],"diagnostically":[246],"relevant":[247],"regions":[248],"rather":[249],"than":[250],"background":[251],"artefacts.":[252],"therefore":[255],"delivers":[256],"not":[257],"only":[258],"high":[259],"but":[263],"also":[264],"transparent":[266],"auditable":[268],"diagnostic":[269],"tool":[270],"suitable":[271],"quality":[274],"control.":[275]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-31T00:00:00"}