{"id":"W4387874254","doi":"10.3390/smartcities6050134","title":"A Comparative Analysis of Multi-Label Deep Learning Classifiers for Real-Time Vehicle Detection to Support Intelligent Transportation Systems","year":2023,"lang":"en","type":"article","venue":"Smart Cities","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université Laval","funders":"Mitacs","keywords":"Object detection; Computer science; Convolutional neural network; Truck; Pedestrian detection; Component (thermodynamics); Intelligent transportation system; Artificial intelligence; Deep learning; Real-time computing; Computation; Detector; Machine learning; Pattern recognition (psychology); Engineering; Automotive engineering; Pedestrian; Transport engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001873548,0.0001073626,0.0002846273,0.0003805832,0.0002060015,0.00004898958,0.0002212596,0.00003963995,0.000003243236],"category_scores_gemma":[0.00001616228,0.000112805,0.00009168196,0.00203126,0.00004904061,0.0001913071,0.00002106974,0.00006619552,0.00002773441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005740843,"about_ca_system_score_gemma":0.00002116837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007599223,"about_ca_topic_score_gemma":0.0004202436,"domain_scores_codex":[0.9989425,0.00004931444,0.0003273647,0.0002963249,0.0001696983,0.0002148066],"domain_scores_gemma":[0.9991422,0.0002570524,0.0001503836,0.0002165643,0.0001654518,0.00006836347],"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":[0.00005136934,0.00005625016,0.002034189,0.00005817617,0.00041445,0.000001654914,0.01462281,0.9079813,0.04353789,0.00779428,0.0001850408,0.02326258],"study_design_scores_gemma":[0.0001400931,0.0001648745,0.006903603,0.000008810782,0.00008757747,2.158129e-7,0.001461875,0.9834753,0.006956023,0.0001082914,0.0005768113,0.000116496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.284393,0.00001017956,0.7147925,0.00004870735,0.00009312913,0.0003889148,0.00001716642,0.0002099487,0.00004642306],"genre_scores_gemma":[0.9852733,0.00001911698,0.01351847,0.00001718662,0.00002062995,0.0003664882,0.0000919767,0.000008533015,0.0006842772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7012741,"threshold_uncertainty_score":0.4600054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06480022087357425,"score_gpt":0.3236403717524767,"score_spread":0.2588401508789025,"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."}}