{"id":"W2982559331","doi":"10.1109/ictis.2019.8883540","title":"Evaluation of Alternative Pre-trained Convolutional Neural Networks for Winter Road Surface Condition Monitoring","year":2019,"lang":"en","type":"article","venue":"","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada); University of Waterloo","funders":"","keywords":"Convolutional neural network; Road surface; Computer science; Chromatin structure remodeling (RSC) complex; Snow removal; Set (abstract data type); Deep learning; Artificial intelligence; Transport engineering; Computer vision; Snow; Engineering; Civil engineering; Meteorology; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001547737,0.002493617,0.0007623592,0.0008536925,0.0003705934,0.0008782591,0.002307535,0.001608146,0.001716933],"category_scores_gemma":[0.003256386,0.0005634586,0.0007328336,0.0005939099,0.000416246,0.001378406,0.0006736337,0.001324418,0.0005952422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002524478,"about_ca_system_score_gemma":0.001600951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05542496,"about_ca_topic_score_gemma":0.05224462,"domain_scores_codex":[0.9994358,0.0000750112,0.00004520272,0.0001917335,0.000123506,0.0001286946],"domain_scores_gemma":[0.9987075,0.0004389602,0.00009161394,0.0001454555,0.0005226478,0.00009375082],"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":[0.001590138,0.00116201,0.01443844,0.0005492584,0.0006107147,0.0003338823,0.00009478932,0.7021971,0.01474658,0.0007030024,0.00617212,0.257402],"study_design_scores_gemma":[0.00002866124,0.0002799834,0.002622551,0.00002785132,0.00006362014,0.00003529848,0.0000228941,0.9904822,0.005839457,0.0001378433,0.0004448002,0.00001479268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9233821,0.004686441,0.05462331,0.0006486861,0.0006838001,0.0002815633,0.002078467,0.006148481,0.007467057],"genre_scores_gemma":[0.9652591,0.0007788201,0.02507797,0.0002126189,0.00004375788,0.0001104387,0.003897706,0.0001048128,0.004514832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.05542496,"threshold_uncertainty_score":0.1102047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01538744877103897,"score_gpt":0.2773844528887909,"score_spread":0.2619970041177519,"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."}}