{"id":"https://openalex.org/W7214178367","doi":"https://doi.org/10.1038/s41598-026-72138-1","title":"LAFNet: a lightweight neural network with fuzzy attention mechanism for rail surface defect classification","display_name":"LAFNet: a lightweight neural network with fuzzy attention mechanism for rail surface defect classification","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214178367","doi":"https://doi.org/10.1038/s41598-026-72138-1"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-72138-1","doi":"https://doi.org/10.1038/s41598-026-72138-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-72138-1","pdf_url":"https://www.nature.com/articles/s41598-026-72138-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-72138-1_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096717291","display_name":"Yang Liyuan","orcid":"https://orcid.org/0009-0000-2185-2251","observed_orcids":["https://orcid.org/0009-0000-2185-2251"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liyuan Yang","raw_affiliation_strings":["Kunming University, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0000-2185-2251","affiliations":[{"raw_affiliation_string":"Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064400268","display_name":"Ghazali Osman","orcid":"https://orcid.org/0000-0001-5167-5292","observed_orcids":["https://orcid.org/0000-0001-5167-5292"]},"institutions":[{"id":"https://openalex.org/I4210138650","display_name":"Universiti Teknologi MARA System","ror":"https://ror.org/030847t23","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210138650","https://openalex.org/I82724352"]},{"id":"https://openalex.org/I82724352","display_name":"Universiti Teknologi MARA","ror":"https://ror.org/05n8tts92","country_code":"MY","type":"education","lineage":["https://openalex.org/I82724352"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ghazali Osman","raw_affiliation_strings":["College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia","institution_ids":["https://openalex.org/I4210138650","https://openalex.org/I82724352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152759778","display_name":"Muhammad Firdaus Mustapha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210138650","display_name":"Universiti Teknologi MARA System","ror":"https://ror.org/030847t23","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210138650","https://openalex.org/I82724352"]},{"id":"https://openalex.org/I82724352","display_name":"Universiti Teknologi MARA","ror":"https://ror.org/05n8tts92","country_code":"MY","type":"education","lineage":["https://openalex.org/I82724352"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Muhammad Firdaus Mustapha","raw_affiliation_strings":["College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia","institution_ids":["https://openalex.org/I4210138650","https://openalex.org/I82724352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107195681","display_name":"Liling Dai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liling Dai","raw_affiliation_strings":["Kunming University, Kunming, Yunnan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110368408","display_name":"Jiankun Yang","orcid":"https://orcid.org/0009-0002-2336-6606","observed_orcids":["https://orcid.org/0009-0002-2336-6606","https://orcid.org/0009-0001-5265-0916"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankun Yang","raw_affiliation_strings":["Kunming University, Kunming, Yunnan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5096717291"],"corresponding_institution_ids":["https://openalex.org/I146071755"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9541000127792358,"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"}},"topics":[{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9541000127792358,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.03290000185370445,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0071000000461936,"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/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.9810000061988831},{"id":"https://openalex.org/keywords/railway-safety","display_name":"railway safety","score":0.6079999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6420999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845000147819519},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C29470771","wikidata":"https://www.wikidata.org/wiki/Q4165150","display_name":"Neuro-fuzzy","level":4,"score":0.4544999897480011},{"id":"https://openalex.org/C2780049643","wikidata":"https://www.wikidata.org/wiki/Q5511139","display_name":"Fuzzy rule","level":4,"score":0.4535999894142151},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.43130001425743103},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41990000009536743},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2780042925","wikidata":"https://www.wikidata.org/wiki/Q1049667","display_name":"Road surface","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2986395286","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy inference","level":5,"score":0.2624000012874603},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-72138-1","doi":"https://doi.org/10.1038/s41598-026-72138-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-72138-1","pdf_url":"https://www.nature.com/articles/s41598-026-72138-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-72138-1","doi":"https://doi.org/10.1038/s41598-026-72138-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-72138-1","pdf_url":"https://www.nature.com/articles/s41598-026-72138-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5378999710083008}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214178367.pdf","grobid_xml":"https://content.openalex.org/works/W7214178367.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4379620560","https://openalex.org/W4411634881","https://openalex.org/W7119481899","https://openalex.org/W7124317112","https://openalex.org/W7153577851","https://openalex.org/W7160503930"],"related_works":["https://openalex.org/W4412418043","https://openalex.org/W7221750857","https://openalex.org/W7140075130","https://openalex.org/W4288929068","https://openalex.org/W4408853306","https://openalex.org/W4319996167","https://openalex.org/W4412164054","https://openalex.org/W7223095461","https://openalex.org/W7160529583","https://openalex.org/W4414855770"],"abstract_inverted_index":{"Abstract":[0],"Rapid":[1],"and":[2,31,45,95,119,136,160],"accurate":[3],"detection":[4],"of":[5,42,108,157,165],"rail":[6,65],"anomaly":[7,66],"is":[8,101,129],"crucial":[9],"for":[10,48,64],"railway":[11],"transportation":[12],"safety.":[13],"Although":[14],"existing":[15],"deep":[16,78],"learning":[17],"methods":[18],"have":[19],"achieved":[20],"certain":[21],"progress,":[22],"they":[23],"generally":[24],"suffer":[25],"from":[26],"large":[27],"model":[28,62,69,147],"parameter":[29],"sizes":[30],"high":[32],"computational":[33],"costs,":[34],"making":[35],"it":[36],"difficult":[37],"to":[38,76,103,131],"meet":[39],"the":[40,112,145],"requirements":[41],"real-time":[43],"performance":[44],"resource":[46],"constraints":[47],"on-site":[49],"deployment.":[50],"To":[51],"address":[52],"these":[53],"challenges,":[54],"this":[55],"study":[56],"proposes":[57],"a":[58,72,96,124,162],"lightweight":[59],"neural":[60,84],"network":[61,85],"(LAFNet)":[63],"classification.":[67],"The":[68],"first":[70],"adopts":[71],"three-layer":[73],"convolutional":[74,109],"structure":[75],"extract":[77],"features.":[79],"Then,":[80],"an":[81,153],"enhanced":[82],"fuzzy":[83,88,97],"branch":[86],"generates":[87],"rule":[89,113],"activation":[90],"vectors":[91],"with":[92],"clear":[93],"semantics,":[94],"attention":[98],"gating":[99],"module":[100],"introduced":[102],"adaptively":[104],"perform":[105],"channel-wise":[106],"reweighting":[107],"features":[110,118],"using":[111],"vectors,":[114],"thereby":[115],"enhancing":[116],"anomaly-related":[117],"suppressing":[120],"irrelevant":[121],"ones.":[122],"Furthermore,":[123],"residual":[125],"fully":[126],"connected":[127],"block":[128],"employed":[130],"improve":[132],"nonlinear":[133],"representation":[134],"capability":[135],"ensure":[137],"stable":[138],"gradient":[139],"propagation.":[140],"Experimental":[141],"results":[142],"show":[143],"that":[144],"proposed":[146],"has":[148],"only":[149],"0.46":[150],"million":[151],"parameters,":[152],"CPU":[154],"inference":[155],"time":[156],"1.045":[158],"milliseconds,":[159],"achieves":[161],"classification":[163],"accuracy":[164],"99.5%.":[166]},"counts_by_year":[],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-09-25T00:00:00"}