{"id":"W3087376364","doi":"10.1155/2020/5364252","title":"A Customized Deep Neural Network Approach to Investigate Travel Mode Choice with Interpretable Utility Information","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tsinghua University","keywords":"Interpretability; Computer science; Mode choice; Artificial neural network; Discrete choice; Multinomial logistic regression; Feature (linguistics); Artificial intelligence; Machine learning; Mode (computer interface); Representation (politics); Field (mathematics); Beijing; Deep learning; Data mining; Public transport; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003605318,0.0004904348,0.0002797188,0.0004759988,0.0001818223,0.0004701501,0.0009171102,0.0006432002,0.002612018],"category_scores_gemma":[0.00132163,0.0002313222,0.0004323307,0.0006584413,0.0003113119,0.0008960262,0.0006219332,0.001108468,0.0001940001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116563,"about_ca_system_score_gemma":0.0006263175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01360071,"about_ca_topic_score_gemma":0.0162835,"domain_scores_codex":[0.9998847,0.00003766149,0.000004881497,0.00003628546,0.00001698497,0.00001945484],"domain_scores_gemma":[0.9997881,0.0001047761,0.00002487793,0.00002012842,0.00004412834,0.00001804514],"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":[0.00004581958,0.00007691931,0.003125736,0.00003032307,0.00004540979,0.00006809898,0.00003922417,0.9396998,0.0009078478,0.02246353,0.001351776,0.03214559],"study_design_scores_gemma":[7.895904e-7,0.000002688334,0.0001385016,0.000001295251,0.000001702761,0.000002383568,0.000002024809,0.9962084,0.00005030285,0.00349275,0.00009793483,0.00000105313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1259143,0.0004933611,0.8654684,0.0007336527,0.00007034288,0.00004242945,0.0008076847,0.0003234495,0.006146367],"genre_scores_gemma":[0.9437199,0.0002821524,0.04969291,0.0001060982,0.0000444972,0.00007417089,0.0005105798,0.0000270511,0.005542696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01360071,"threshold_uncertainty_score":0.0270431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008333749932404884,"score_gpt":0.2060833661089947,"score_spread":0.1977496161765898,"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."}}