{"id":"W3155738052","doi":"10.1016/j.aap.2021.106107","title":"Using long short term memory and convolutional neural networks for driver drowsiness detection","year":2021,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Sleep and Work-Related Fatigue","field":"Psychology","cited_by":89,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alcohol Countermeasure Systems (Canada)","funders":"","keywords":"Convolutional neural network; Term (time); Poison control; Long short term memory; Short-term memory; Computer science; Occupational safety and health; Injury prevention; Human factors and ergonomics; Artificial intelligence; Engineering; Physical medicine and rehabilitation; Real-time computing; Artificial neural network; Medical emergency; Medicine; Psychology; Neuroscience; Recurrent neural network; Cognition; Working memory","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":[],"consensus_categories":[],"category_scores_codex":[0.0002943421,0.0001602035,0.0002685479,0.0002502099,0.00023548,0.00007786482,0.00008053485,0.0002040294,0.0006065595],"category_scores_gemma":[0.00002172025,0.0001754992,0.0003711604,0.0007884054,0.0000396427,0.0002536614,0.00005215677,0.0001560343,0.000004697687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007023788,"about_ca_system_score_gemma":0.00001415899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007120035,"about_ca_topic_score_gemma":0.002147096,"domain_scores_codex":[0.9985541,0.0001841801,0.0003801473,0.0004615656,0.0001609166,0.0002590847],"domain_scores_gemma":[0.9992763,0.00008238198,0.0001403185,0.0002536954,0.0001803746,0.00006691632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007636628,0.0001250679,0.8794674,0.000001488255,0.002943733,0.00002162971,0.0001422674,0.01239182,0.0006988124,0.0001203342,0.00006403231,0.103947],"study_design_scores_gemma":[0.0008231506,0.00003578807,0.8971047,0.00004119126,0.005710248,0.00002631142,0.0001837478,0.09517018,0.0005098828,0.0001257085,0.000006954313,0.0002621496],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6918573,0.001075976,0.3062275,0.00002794232,0.0005223849,0.0001762535,3.456548e-7,0.00003613748,0.00007614835],"genre_scores_gemma":[0.998516,0.00002816778,0.0003078914,0.00004106799,0.000275728,0.00004841586,0.0002658681,0.00001867304,0.0004982242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3066587,"threshold_uncertainty_score":0.715665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0361380451718645,"score_gpt":0.3401146191125182,"score_spread":0.3039765739406537,"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."}}