{"id":"W4405326891","doi":"10.3390/s24247948","title":"Semantically-Enhanced Feature Extraction with CLIP and Transformer Networks for Driver Fatigue Detection","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Sleep and Work-Related Fatigue","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Natural Science Foundation of Shanghai","keywords":"Transformer; Computer science; Feature extraction; Convolutional neural network; Artificial intelligence; Deep learning; Feature learning; Long short term memory; Artificial neural network; Pattern recognition (psychology); Recurrent neural network; Machine learning; Engineering; Voltage","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":[0.0001071832,0.0001690779,0.0001443396,0.00009144625,0.0001204692,0.0000550206,0.0000362267,0.0003411242,0.0001041016],"category_scores_gemma":[0.000007568802,0.0001318468,0.00006790732,0.0002340187,0.00006695967,0.00009666211,0.000002299633,0.0004159715,0.00003156653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002252805,"about_ca_system_score_gemma":0.000007976042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001792424,"about_ca_topic_score_gemma":0.0001557636,"domain_scores_codex":[0.9990599,0.0000454768,0.0001378875,0.0003772817,0.00009009345,0.0002893803],"domain_scores_gemma":[0.9995396,0.0001843778,0.00002805715,0.0001339715,0.00004095048,0.00007303168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001761813,0.0001296573,0.0006222014,0.00007714571,0.001096476,0.00009227601,0.005984247,0.004262293,0.01051003,0.004751142,0.004158593,0.9665541],"study_design_scores_gemma":[0.04294876,0.01532696,0.1226168,0.01168447,0.01079336,0.002249194,0.02505223,0.275801,0.2334289,0.003687203,0.244066,0.01234512],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7404773,0.0009964447,0.248529,0.0007889432,0.001856804,0.0007274945,0.00001071891,0.0003086764,0.00630461],"genre_scores_gemma":[0.9974141,0.00008861725,0.0005010122,0.00008016582,0.0002978769,0.00005985931,0.00001626645,0.00004446875,0.001497704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.954209,"threshold_uncertainty_score":0.5376557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01440960311922685,"score_gpt":0.2984925133935247,"score_spread":0.2840829102742979,"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."}}