{"id":"W1520514216","doi":"10.1002/atr.1231","title":"More robust and better: a multiple kernel support vector machine ensemble approach for traffic incident detection","year":2013,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Support vector machine; Computer science; Artificial intelligence; Multiple kernel learning; Kernel (algebra); Ensemble learning; Machine learning; Resampling; Classifier (UML); Ranking SVM; Pattern recognition (psychology); Construct (python library); Set (abstract data type); Data mining; Algorithm; Kernel method; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000131373,0.000112791,0.000167337,0.000125353,0.0001143844,0.00005471066,0.0001670168,0.00005658633,0.000004734463],"category_scores_gemma":[0.00001075746,0.000101238,0.00009885539,0.0001770136,0.00002235765,0.0008627992,0.000003859503,0.0001297086,8.165491e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003932423,"about_ca_system_score_gemma":0.00002277801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001418369,"about_ca_topic_score_gemma":0.00002489098,"domain_scores_codex":[0.9990724,0.00001149957,0.0004256439,0.0001875626,0.0001684277,0.0001344402],"domain_scores_gemma":[0.9991328,0.00004166747,0.0003721061,0.0001329868,0.0002322388,0.00008824318],"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":[0.0001425686,0.0003707931,0.001953217,0.0001509408,0.00006976176,0.000006072174,0.002925293,0.2406923,0.1071999,0.0005975077,0.000210949,0.6456807],"study_design_scores_gemma":[0.003778241,0.0017399,0.3861153,0.00004891142,0.0001111062,0.0002205865,0.000671357,0.5356022,0.06661161,0.001747028,0.002742757,0.0006110055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3950983,0.00003101253,0.6042464,0.0002307396,0.00004919968,0.0002948095,0.00000372198,0.00004115147,0.000004711897],"genre_scores_gemma":[0.717881,0.00003289009,0.2818362,0.00007255721,0.00004301386,0.00009529779,0.00001015153,0.000008962998,0.00001989933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6450697,"threshold_uncertainty_score":0.4128367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01040702154622679,"score_gpt":0.2320667214197938,"score_spread":0.221659699873567,"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."}}