{"id":"W2946562067","doi":"10.1049/iet-its.2018.5409","title":"Vision‐based traffic accident detection using sparse spatio‐temporal features and weighted extreme learning machine","year":2019,"lang":"en","type":"article","venue":"IET Intelligent Transport Systems","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Extreme learning machine; Traffic accident; Computer vision; Pattern recognition (psychology); Machine learning; Engineering; Artificial neural network; Transport 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001233349,0.0003323957,0.000473447,0.000300778,0.0002002959,0.0002242711,0.0004103333,0.0001718186,0.00003330279],"category_scores_gemma":[0.00001280019,0.000295795,0.0001639907,0.0004998864,0.00003589778,0.0004574479,0.0000268283,0.0003856016,0.00003638321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008578911,"about_ca_system_score_gemma":0.00006643283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006403479,"about_ca_topic_score_gemma":0.0006287484,"domain_scores_codex":[0.9973707,0.0003403628,0.0006222511,0.0007178082,0.0005441449,0.0004046918],"domain_scores_gemma":[0.9987901,0.0001501104,0.0002604036,0.0005176677,0.0001240496,0.0001576761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002327738,0.0002470909,0.596657,0.0005005857,0.0001628056,0.0001592294,0.002258376,0.3087539,0.005094831,0.0004465282,0.00002425143,0.0854626],"study_design_scores_gemma":[0.000634341,0.0003410954,0.05259713,0.0003788405,0.00003526987,0.0001439356,0.0001192322,0.9332631,0.006443514,0.00003492055,0.005424478,0.0005841452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5223956,0.0009475775,0.4747576,0.00003562416,0.00118694,0.0003850767,0.000002378045,0.0002275073,0.00006174833],"genre_scores_gemma":[0.9925789,0.00004982217,0.006921323,0.00004070097,0.0001045939,0.00001436013,0.00003278917,0.00003549879,0.0002220043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6245092,"threshold_uncertainty_score":0.9999494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03617157371223183,"score_gpt":0.280573390985326,"score_spread":0.2444018172730941,"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."}}