{"id":"W4391991111","doi":"10.1139/cjce-2023-0405","title":"An adaptive machine learning framework for multi-scenes road surface weather condition monitoring","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Road surface; Convolutional neural network; Computer science; Artificial intelligence; Computer vision; Artificial neural network; Deep learning; Object detection; Real-time computing; Pattern recognition (psychology); Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002574019,0.000116544,0.0001282319,0.00009971583,0.00009259318,0.00011021,0.0001162837,0.00007407353,0.0003690452],"category_scores_gemma":[0.00007804964,0.0001191085,0.00006298527,0.0001225804,0.00003061044,0.0004144144,0.000006800897,0.0002260075,0.00001795853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003331709,"about_ca_system_score_gemma":0.0000544386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002064391,"about_ca_topic_score_gemma":0.01246567,"domain_scores_codex":[0.9993165,0.0000193859,0.0001958717,0.0001234352,0.0001069407,0.0002378875],"domain_scores_gemma":[0.9995362,0.00003978801,0.00005784902,0.00007030474,0.00001673206,0.0002791565],"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":[0.00001615948,0.000006580484,0.07742085,0.0000424694,0.00006365601,0.00007961417,0.001142928,0.8699836,0.04799446,0.0003499025,0.00005807106,0.002841691],"study_design_scores_gemma":[0.0006050222,0.000542138,0.1165662,0.001224784,0.0001213679,0.0005297952,0.0006497078,0.844406,0.01847762,0.0008426387,0.01528781,0.0007469261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8346673,0.0006048696,0.1622224,0.00003261886,0.002306999,0.00008319458,0.00001357458,0.0000371343,0.00003186823],"genre_scores_gemma":[0.9787122,0.00001136317,0.0208624,0.000003978759,0.0003484802,0.000002658889,0.00000232504,0.00003639351,0.00002020465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1440449,"threshold_uncertainty_score":0.6956137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01423288527340211,"score_gpt":0.2341034005660781,"score_spread":0.219870515292676,"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."}}