{"id":"W2917694466","doi":"10.1007/s42421-021-00047-y","title":"Semi-supervised GANs to Infer Travel Modes in GPS Trajectories","year":2021,"lang":"en","type":"preprint","venue":"Journal of Big Data Analytics in Transportation","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Toronto Metropolitan University","funders":"","keywords":"Global Positioning System; Computer science; Inference; Convolutional neural network; Context (archaeology); Trajectory; Scale (ratio); Mode (computer interface); Artificial intelligence; Machine learning; Data mining; Geography; Cartography","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":[0.002928783,0.0002161995,0.0007000435,0.0009106847,0.0001071966,0.0002025749,0.001010793,0.0003411436,0.0001310371],"category_scores_gemma":[0.0005472195,0.0002326916,0.0002126067,0.001225287,0.0001194262,0.0004530085,0.0000271813,0.0008920764,0.000001487981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003607056,"about_ca_system_score_gemma":0.002114203,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02004293,"about_ca_topic_score_gemma":0.6320212,"domain_scores_codex":[0.9965567,0.0003369224,0.001459132,0.0004404432,0.0009311677,0.000275657],"domain_scores_gemma":[0.9979345,0.0002443605,0.0004636879,0.0006146334,0.0005618163,0.0001810385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001984424,0.001196422,0.2369609,0.0006034747,0.0004945114,0.000327225,0.2026778,0.5327283,0.0005087106,0.001455816,0.0002418553,0.0226066],"study_design_scores_gemma":[0.002052955,0.0001452629,0.7451985,0.002947765,0.001655062,0.000001841436,0.1883529,0.04889644,0.0005253642,0.007560042,0.00128281,0.001381029],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.92093,0.0003253863,0.07583483,0.001505345,0.0004560066,0.0002614916,0.0004202024,0.00000897295,0.0002577832],"genre_scores_gemma":[0.9958701,0.001155746,0.001054524,0.0001162412,0.0004087999,0.000006120213,0.001324926,0.00001564254,0.0000478677],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6119782,"threshold_uncertainty_score":0.9864827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.144728435980569,"score_gpt":0.3594071555683704,"score_spread":0.2146787195878014,"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."}}