{"id":"W4390693326","doi":"10.1109/icecs58634.2023.10382732","title":"Enabling Human Activity Recognition in Smart Public Transportation Systems in Presence of Dataset Imbalance","year":2023,"lang":"en","type":"article","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Feature selection; Machine learning; Class (philosophy); Artificial intelligence; Public transport; Orchestration; Relation (database); Set (abstract data type); Feature (linguistics); Feature extraction; Data mining; 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":[],"consensus_categories":[],"category_scores_codex":[0.001943192,0.000048678,0.000131973,0.0002888974,0.0001244576,0.00004005899,0.0001319082,0.00005961024,0.0001357174],"category_scores_gemma":[0.0002285148,0.0000526886,0.0000247214,0.001420495,0.00008807865,0.0004284165,0.000004235227,0.00008436923,0.0000191955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006970569,"about_ca_system_score_gemma":0.00009907375,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1866196,"about_ca_topic_score_gemma":0.6733915,"domain_scores_codex":[0.9988253,0.000301725,0.0002536119,0.0001929109,0.0002506977,0.000175791],"domain_scores_gemma":[0.9994765,0.0002060254,0.00008251866,0.0001341537,0.00006379711,0.00003702291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000432717,0.0008070501,0.903671,0.0005383376,0.00003858497,0.00001584712,0.02983695,0.004971261,0.008760898,0.009434553,0.001611753,0.04027055],"study_design_scores_gemma":[0.0005285428,0.00003337203,0.9595717,0.0001761952,0.00001664614,4.239923e-8,0.02215301,0.01204475,0.000526069,0.001979385,0.002711513,0.000258758],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982728,0.00001212347,0.0002219957,0.0003659988,0.00003761096,0.0002158202,0.0001927914,0.00003793747,0.000642881],"genre_scores_gemma":[0.9985623,0.00003790487,0.000006130059,0.000009963978,0.00002262975,0.00004630112,0.001203627,0.000002668771,0.0001084742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867719,"threshold_uncertainty_score":0.8187968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08724062702832892,"score_gpt":0.3475711291229046,"score_spread":0.2603305020945757,"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."}}