{"id":"W4285387998","doi":"10.1177/03611981221106483","title":"Machine-Learning Approaches to Identify Travel Modes Using Smartphone-Assisted Survey and Map Application Programming Interface","year":2022,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Identification (biology); Support vector machine; Travel survey; Decision tree; Global Positioning System; Data mining; Travel behavior; Machine learning; Artificial intelligence; Transport engineering; Engineering","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01893349,0.0001892648,0.0003849772,0.001067112,0.003748046,0.0003004794,0.0009859055,0.0001105095,0.0002550027],"category_scores_gemma":[0.0003655838,0.0001736403,0.0002384216,0.00323554,0.0006729513,0.0004453716,0.00002103174,0.002137721,0.000006171058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005804633,"about_ca_system_score_gemma":0.0008457006,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1907458,"about_ca_topic_score_gemma":0.4251916,"domain_scores_codex":[0.9877009,0.006300646,0.001063317,0.0004994716,0.003696488,0.000739211],"domain_scores_gemma":[0.9959359,0.001252253,0.0004182015,0.0003193447,0.001642675,0.0004316175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001646937,0.0006311095,0.8116618,0.0002680924,0.0002687186,0.0000210299,0.05047923,0.06883834,0.004358151,0.002978685,0.0003051545,0.05854268],"study_design_scores_gemma":[0.0006914373,0.0003338452,0.9378285,0.00008522213,0.00006624512,3.414164e-7,0.04230511,0.008242563,0.0002256375,0.0009958257,0.008985934,0.0002393706],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9615135,0.0002885979,0.03355953,0.003071666,0.0001415963,0.001278687,0.00006957704,0.00002655046,0.00005034191],"genre_scores_gemma":[0.9974197,0.0001357292,0.001540029,0.00002335355,0.0000872034,0.000184382,0.0000557176,0.0000369908,0.0005168797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2344458,"threshold_uncertainty_score":0.9975489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2904621731939001,"score_gpt":0.4406975074233966,"score_spread":0.1502353342294965,"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."}}