{"id":"W2904042868","doi":"10.1155/2018/3869106","title":"An Improved Deep Learning Model for Traffic Crash Prediction","year":2018,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Tennessee Department of Transportation; Research and Innovative Technology Administration; U.S. Department of Transportation","keywords":"Computer science; Artificial intelligence; Machine learning; Feature (linguistics); Deep learning; Crash; Autoencoder; Feature learning; Data mining; Supervised learning; Curse of dimensionality; Random forest; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001185521,0.00009542645,0.0001374967,0.0000775589,0.00007784324,0.000009275454,0.00006504409,0.00006791414,0.00000565449],"category_scores_gemma":[0.000006170357,0.00008993585,0.00008338906,0.00007575558,0.00001908815,0.0005444686,2.077199e-7,0.0001548762,6.888612e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003677255,"about_ca_system_score_gemma":0.0000177295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.342051e-7,"about_ca_topic_score_gemma":0.00003918502,"domain_scores_codex":[0.9992948,0.000006466406,0.0003740467,0.00008022923,0.0001081282,0.0001363652],"domain_scores_gemma":[0.9995549,0.00001592311,0.0001145669,0.00005490234,0.0001860163,0.00007374761],"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":[0.0001288461,0.00002255689,0.0001091201,0.00002864142,0.00002240785,6.754564e-7,0.002458591,0.9169644,0.01651961,0.00001833512,0.000009630226,0.0637172],"study_design_scores_gemma":[0.001119412,0.0004993413,0.02937686,0.0000259386,0.00005396597,0.000003631627,0.0003694643,0.9671513,0.0008873021,0.00009205416,0.0003271019,0.00009355744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5171393,0.00004958538,0.4823218,0.000007338874,0.0003137101,0.00007198705,0.000007007797,0.00007707696,0.00001214827],"genre_scores_gemma":[0.9631528,0.0001004579,0.03633852,0.000007268573,0.0003170173,0.000004973952,0.00003459949,0.00002874532,0.00001557683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4460135,"threshold_uncertainty_score":0.3667478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00612544029823836,"score_gpt":0.2260695478117455,"score_spread":0.2199441075135071,"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."}}