{"id":"W3109937920","doi":"10.18757/ejtir.2020.20.4.5429","title":"Modelling cellphone trace travel mode with neural networks using transit smartcard and home interview survey data","year":2020,"lang":"en","type":"article","venue":"European journal of transport and infrastructure research","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Universidad de la República Uruguay","keywords":"TRIPS architecture; Computer science; Smart card; Public transport; Artificial neural network; Travel survey; Mode choice; Transit (satellite); Mode (computer interface); Travel behavior; Survey data collection; TRACE (psycholinguistics); Data mining; Transport engineering; Computer security; Artificial intelligence; Engineering; Statistics; Human–computer interaction","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":[0.006329389,0.0001480704,0.0003691068,0.0001288588,0.0005016849,0.0001436088,0.0005805726,0.00004898614,0.00008287312],"category_scores_gemma":[0.00003650532,0.0001158047,0.00006315806,0.0005552166,0.000561183,0.0004433111,0.00003020004,0.0009265881,3.519726e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002342509,"about_ca_system_score_gemma":0.0001882931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000984365,"about_ca_topic_score_gemma":0.001216719,"domain_scores_codex":[0.9962248,0.001960401,0.0004831746,0.0003200258,0.0006677308,0.0003439014],"domain_scores_gemma":[0.9986992,0.0001586112,0.0001291936,0.0002026404,0.0003619543,0.0004483408],"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":[0.0007539485,0.00005076425,0.03143985,0.0002036318,0.0002498922,0.0002708483,0.04403315,0.8743475,0.0002047073,0.00003743515,0.0001425328,0.04826576],"study_design_scores_gemma":[0.0009199344,0.0003740321,0.06666846,0.0001609144,0.0001630442,0.00002388577,0.005308767,0.9247275,0.000009125804,0.00005335183,0.001326552,0.0002644298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6380144,0.001632044,0.3591319,0.0008642658,0.00003407223,0.0001146267,0.00003850461,0.000006978449,0.0001631724],"genre_scores_gemma":[0.997108,0.001407867,0.001007016,0.00007245711,0.0003424548,1.609909e-7,0.00002827395,0.00002305135,0.00001071507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3590935,"threshold_uncertainty_score":0.4722379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1927143739527558,"score_gpt":0.3554851757517922,"score_spread":0.1627708017990365,"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."}}