{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008528574,0.0001165293,0.0001989416,0.00007531712,0.00002709737,0.00002461582,0.0001047534,0.00003569614,0.000002665613],"category_scores_gemma":[0.00001258369,0.0001022285,0.00005265557,0.000273424,0.00001280374,0.001225885,0.000001578947,0.000196867,0.000001201481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002802172,"about_ca_system_score_gemma":0.00001046313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000302081,"about_ca_topic_score_gemma":0.00001360814,"domain_scores_codex":[0.9991689,0.00001271788,0.0004297991,0.00006914831,0.0001861874,0.0001332659],"domain_scores_gemma":[0.9995646,0.00001194962,0.0001265137,0.00006202306,0.00008272116,0.0001521409],"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":[0.0002637216,0.00001087473,0.0001493518,0.00008406478,0.00003641377,0.000001171242,0.002613618,0.9815707,0.0003878743,0.0001068686,0.0007211432,0.01405418],"study_design_scores_gemma":[0.001977334,0.0002237384,0.03433,0.00006819615,0.00009351342,0.000004298318,0.0006035006,0.957037,0.0006640526,0.00005886005,0.004744813,0.000194683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1166709,0.00003172571,0.8816854,0.0001471813,0.0001195476,0.0002520296,0.000006052313,0.0004058847,0.0006813104],"genre_scores_gemma":[0.9410109,0.0000266859,0.05841328,0.0004315781,0.00006139919,0.00001380056,0.00002903625,0.00001225234,0.000001061208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.82434,"threshold_uncertainty_score":0.4168757,"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."}}