{"id":"W4408171278","doi":"10.1038/s41598-025-92396-9","title":"Hybrid neural network method for damage localization in structural health monitoring","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Christian-Albrechts-Universität zu Kiel","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Domain (mathematical analysis); Deep learning; Complement (music); Segmentation; Reduction (mathematics); Machine learning; Feature engineering; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092824,0.0001387297,0.0002053581,0.000179086,0.0002570061,0.0001635541,0.00009562398,0.00003881552,0.000003508448],"category_scores_gemma":[0.00006030188,0.00013582,0.00005558627,0.0004612844,0.00003099965,0.0001710254,0.00003498244,0.0001325257,3.59502e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001921688,"about_ca_system_score_gemma":0.00006839795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003531118,"about_ca_topic_score_gemma":0.00002113047,"domain_scores_codex":[0.9985103,0.00002611109,0.0004680179,0.000365903,0.0001507977,0.0004788957],"domain_scores_gemma":[0.9994047,0.0000321687,0.00008211783,0.0003559792,0.00007080387,0.0000542716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004151914,0.000001877956,0.01528213,0.0001339186,0.00000974301,0.00003198813,0.0001762671,0.9499262,0.001145379,0.000233866,0.009120217,0.02393427],"study_design_scores_gemma":[0.0002639158,0.00001578703,0.01088951,0.0003133187,0.00001137143,0.00004564862,0.0001320683,0.9082181,0.0228928,0.03023081,0.02669627,0.000290426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4612283,0.0008816536,0.4484729,0.0001172483,0.08728404,0.0008905736,0.000003538419,0.0003718944,0.0007497868],"genre_scores_gemma":[0.9803469,0.000003764571,0.01887146,0.00003030815,0.0003975826,0.00003696432,0.00003143565,0.00001976858,0.0002618029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5191185,"threshold_uncertainty_score":0.5538577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008755604887247647,"score_gpt":0.2884750072318199,"score_spread":0.2797194023445723,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}