{"id":"W2912346386","doi":"10.1155/2019/4125865","title":"Driver Distraction Identification with an Ensemble of Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":300,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Technische Universität München; Deutsche Forschungsgemeinschaft","keywords":"Distraction; Convolutional neural network; Computer science; Identification (biology); Artificial intelligence; Machine learning; Segmentation; Ensemble learning; Phone; Deep learning; Distracted driving; Artificial neural network; Face (sociological concept); Pattern recognition (psychology)","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":[0.0001358814,0.00006960361,0.0001385407,0.0001020756,0.00002989674,0.00001431441,0.0001923286,0.00004519125,0.00000432126],"category_scores_gemma":[0.000004482441,0.00005862028,0.0000462699,0.0001951591,0.00003561342,0.001185735,0.000001368006,0.0001520753,0.00000105366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002554141,"about_ca_system_score_gemma":0.00003095197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002913862,"about_ca_topic_score_gemma":0.00001630944,"domain_scores_codex":[0.9991807,0.00002170541,0.0003542,0.0001272161,0.0002254001,0.00009081831],"domain_scores_gemma":[0.9988161,0.00003191251,0.0006328059,0.0001440456,0.0003415966,0.00003358478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003222282,0.0002283681,0.05132218,0.00002879926,0.00004351689,0.00001749329,0.0004395386,0.7837108,0.1050016,0.01922795,0.000007692875,0.03964979],"study_design_scores_gemma":[0.0006735686,0.0005556302,0.9715878,0.0000327847,0.00001940427,0.00003034165,0.000108797,0.02061454,0.005247265,0.001021034,0.00003332781,0.00007551347],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.572542,0.00002068988,0.4271132,0.00006894031,0.0001935867,0.00003982931,0.000001030885,0.00001447331,0.000006281522],"genre_scores_gemma":[0.9821438,0.0000104002,0.0177774,0.00000994088,0.0000256225,0.000001095446,0.00001404361,0.000004641158,0.00001312241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9202656,"threshold_uncertainty_score":0.2390466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007240715379631352,"score_gpt":0.2370285528321021,"score_spread":0.2297878374524708,"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."}}