{"id":"W4308141392","doi":"10.1155/2022/6601014","title":"Stacking-Based Ensemble Learning Method for the Recognition of the Pedestrian Crossing Intention","year":2022,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Pedestrian crossing; Pedestrian; Computer science; Artificial intelligence; Ensemble learning; Support vector machine; Machine learning; Pattern recognition (psychology); Level crossing; Engineering; Transport engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007411498,0.0009385679,0.0008874231,0.001032175,0.0004148008,0.0004503854,0.0007072837,0.0004954533,0.001182026],"category_scores_gemma":[0.001477683,0.0002750296,0.001074244,0.0008794299,0.0001868656,0.001173845,0.0005992948,0.0009775772,0.0005603905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003355215,"about_ca_system_score_gemma":0.000590319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007635844,"about_ca_topic_score_gemma":0.007607763,"domain_scores_codex":[0.9995447,0.00007227957,0.00003352655,0.0001575777,0.0001169482,0.00007510527],"domain_scores_gemma":[0.9994821,0.0001199774,0.00004620674,0.0000709637,0.000251456,0.00002937395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001843136,0.0001885193,0.008221858,0.00006971139,0.0001988736,0.000138958,0.0001882567,0.1066306,0.01566234,0.001400981,0.003495553,0.86362],"study_design_scores_gemma":[0.00000311233,0.00007688021,0.002482596,0.000008739199,0.00005699912,0.00007513044,0.00003602907,0.99134,0.004207083,0.0009365676,0.0007606011,0.00001630112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09403205,0.0008128444,0.9009567,0.0001305545,0.0001703566,0.00005702728,0.00017282,0.001762031,0.001905553],"genre_scores_gemma":[0.8508697,0.000631506,0.1436173,0.0001190349,0.00008717985,0.00009214185,0.0007178325,0.0001015307,0.003763834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007635844,"threshold_uncertainty_score":0.01518279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01511705773790352,"score_gpt":0.2603014178800497,"score_spread":0.2451843601421462,"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."}}