{"id":"W2934625602","doi":"10.1109/tvt.2019.2908425","title":"Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":395,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Transfer of learning; Distraction; Binary classification; Mobile phone; Distracted driving; Computer vision; Pattern recognition (psychology); Support vector machine","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002423892,0.0002467753,0.0003090488,0.0007188134,0.0002736021,0.00002906009,0.0002168849,0.000570898,0.002615334],"category_scores_gemma":[0.00001430704,0.000257712,0.0002599093,0.0004315885,0.0001070039,0.0001486958,0.000002427022,0.0009097158,0.003167908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001282952,"about_ca_system_score_gemma":0.00002049425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001808607,"about_ca_topic_score_gemma":0.00001400366,"domain_scores_codex":[0.9983453,0.0001572448,0.0003345607,0.0006059574,0.0001695733,0.0003873764],"domain_scores_gemma":[0.9989836,0.0001550852,0.0001630888,0.0004639926,0.0001664676,0.00006780084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00111255,0.002212203,0.0003551461,0.000112163,0.0007477219,0.00001100632,0.002591054,0.01773407,0.01709,0.003444127,0.0003300996,0.9542599],"study_design_scores_gemma":[0.01816838,0.008027976,0.005265906,0.0004205496,0.0009587448,0.0009864923,0.02558402,0.3413496,0.3424146,0.007293884,0.2449676,0.004562339],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4081834,0.00001825946,0.5864609,0.0002916996,0.0009248178,0.0006976171,0.00001238322,0.0006209057,0.002790026],"genre_scores_gemma":[0.9933356,0.00002154676,0.001741764,0.0001770402,0.00004087966,0.0007345774,0.00002022422,0.00005141658,0.00387696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9496975,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02625567819256382,"score_gpt":0.3027488113791426,"score_spread":0.2764931331865788,"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."}}