{"id":"W3110096052","doi":"10.1177/0361198120967943","title":"Hybrid Elman Neural Network and an Invasive Weed Optimization Method for Bridge Defect Recognition","year":2020,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Bridge (graph theory); Computer science; Artificial intelligence; Artificial neural network; Set (abstract data type); Context (archaeology); Process (computing); Machine learning; Deep learning; Face (sociological concept); Domain (mathematical analysis); Data mining; Mathematics","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":[0.002195909,0.0002302189,0.0003780734,0.0003232841,0.0004583103,0.0001472806,0.0004482711,0.0001245388,0.00005050797],"category_scores_gemma":[0.0002379301,0.0001914749,0.0002386,0.0009276038,0.0001657954,0.0008086127,0.000004535264,0.00132221,0.000002167897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001096863,"about_ca_system_score_gemma":0.0001764163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001033633,"about_ca_topic_score_gemma":0.003477367,"domain_scores_codex":[0.9963537,0.0005789733,0.0008575731,0.0003288361,0.001155123,0.0007258289],"domain_scores_gemma":[0.9962085,0.0007625264,0.0001949553,0.0001993607,0.002219638,0.0004150005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00197694,0.00004714683,0.01807615,0.0007737098,0.0002598685,0.00006980596,0.003416444,0.9137387,0.01082351,0.0003234734,0.006836387,0.04365788],"study_design_scores_gemma":[0.006056113,0.003468202,0.6886383,0.000860967,0.0003444347,0.000006217578,0.002438137,0.2640158,0.01682233,0.008802333,0.007616225,0.00093097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8324215,0.0001972156,0.1642603,0.001017871,0.0005734463,0.001321601,0.0001033742,0.00006682175,0.00003788471],"genre_scores_gemma":[0.9541743,0.0005455645,0.04384652,0.00009939747,0.001013602,0.0001291339,0.00009132746,0.00008478613,0.00001533554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6705621,"threshold_uncertainty_score":0.7808121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08622659216683717,"score_gpt":0.3617602509452615,"score_spread":0.2755336587784243,"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."}}