{"id":"W4387148966","doi":"10.1016/j.istruc.2023.105280","title":"Structural health monitoring via a group-theoretic WSA for optimal feature selection and data fusion","year":2023,"lang":"en","type":"article","venue":"Structures","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sigmoid function; Binary number; Genetic algorithm; Feature selection; Computer science; Binary classification; Artificial intelligence; Naive Bayes classifier; Pattern recognition (psychology); Particle swarm optimization; Fitness function; Data mining; Feature (linguistics); Fusion; Structural health monitoring; k-nearest neighbors algorithm; Sensor fusion; Bayes' theorem; Machine learning; Support vector machine; Bayesian probability; Mathematics; Artificial neural network; Engineering","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":[0.000167077,0.0002586093,0.0002417415,0.0001493188,0.0003263728,0.00009092584,0.0002640907,0.0001368253,0.000007520467],"category_scores_gemma":[0.00003621031,0.0002249384,0.0000386582,0.0002729979,0.00004090193,0.0002375826,0.000140431,0.0002873294,0.000001351108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008335973,"about_ca_system_score_gemma":0.00001842334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002523732,"about_ca_topic_score_gemma":0.0000155617,"domain_scores_codex":[0.9986874,0.00002003162,0.0001906668,0.0003872828,0.0001712812,0.0005433136],"domain_scores_gemma":[0.9994269,0.00004872564,0.0000497831,0.0003290005,0.00003684966,0.0001087178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003977106,0.000007351651,0.01676539,0.00333619,0.000474096,0.00002961247,0.006929975,0.1238524,0.1436732,0.01251582,0.03177274,0.6602455],"study_design_scores_gemma":[0.002837849,0.0005565418,0.2702765,0.0003874048,0.0001381081,0.0003776613,0.001882076,0.6422578,0.02551204,0.03534919,0.01850722,0.001917717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9852455,0.0008534861,0.008889044,0.0001458258,0.003368902,0.0004860975,0.0001440956,0.0008273069,0.00003979555],"genre_scores_gemma":[0.9839905,0.0001681388,0.013891,0.00001930475,0.001567662,0.0000216701,0.000249788,0.00006450787,0.0000274346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6583278,"threshold_uncertainty_score":0.917272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01572831228520803,"score_gpt":0.2856344171635864,"score_spread":0.2699061048783784,"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."}}