{"id":"W3082820800","doi":"10.32866/001c.14520","title":"Classifying Transport Mode from Global Positioning Systems and Accelerometer Data: A Machine Learning Approach","year":2020,"lang":"en","type":"article","venue":"Findings","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Memorial University of Newfoundland","funders":"Canadian Institutes of Health Research","keywords":"Accelerometer; Global Positioning System; Wearable computer; Computer science; Ranging; Boom; Support vector machine; Mode (computer interface); Real-time computing; Artificial intelligence; Embedded system; Engineering; Human–computer interaction; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000416886,0.00009854724,0.0001955757,0.0000301513,0.0007305322,0.0002120875,0.0003038614,0.00008906759,0.0001092613],"category_scores_gemma":[0.0001063744,0.0001020334,0.00004207652,0.0003555157,0.0001053434,0.000393018,0.00004838407,0.0001943837,0.00001411567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007531376,"about_ca_system_score_gemma":0.00006426981,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03021287,"about_ca_topic_score_gemma":0.001306729,"domain_scores_codex":[0.9987428,0.0001417343,0.0001991911,0.000420777,0.0002925555,0.0002028984],"domain_scores_gemma":[0.9995424,0.00006438805,0.00006371412,0.0001421568,0.00003102797,0.0001563115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006929859,0.0001164228,0.8950467,0.0001951076,0.000336298,0.00001474718,0.08438683,0.00685356,0.0006350056,0.006495944,0.0004957413,0.005354341],"study_design_scores_gemma":[0.000908656,0.00007573686,0.05952167,0.0001303998,0.000450169,0.000001688271,0.01885559,0.8941758,0.00002011232,0.0003897684,0.02476534,0.0007051303],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419422,0.000356118,0.05041169,0.001365945,0.0000593228,0.000206343,0.000353598,0.0001633102,0.005141436],"genre_scores_gemma":[0.9979888,0.00002787483,0.0006516415,0.0001747864,0.0002159496,0.000008493576,0.0008370653,0.000007261002,0.00008810033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8873222,"threshold_uncertainty_score":0.976245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08793302872077463,"score_gpt":0.3173434610511441,"score_spread":0.2294104323303695,"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."}}