{"id":"W2007413993","doi":"10.1016/j.eswa.2011.12.038","title":"A finite mixture model for simultaneous high-dimensional clustering, localized feature selection and outlier rejection","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Outlier; Artificial intelligence; A priori and a posteriori; Pattern recognition (psychology); Data mining; Clustering high-dimensional data; Feature (linguistics); CURE data clustering algorithm; Set (abstract data type); Data set; Feature selection; Correlation clustering; Machine learning","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":[0.0001999405,0.0002098008,0.0002320906,0.00009636224,0.0003328571,0.00009243229,0.0002307086,0.0001790627,0.000001809386],"category_scores_gemma":[0.00001616266,0.0001625715,0.00004193518,0.0002634332,0.00003380701,0.000205578,0.0000554897,0.0001385897,0.000003416136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004936792,"about_ca_system_score_gemma":0.00006382485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001281464,"about_ca_topic_score_gemma":0.00007136176,"domain_scores_codex":[0.9987352,0.00006438527,0.0002077836,0.0005782696,0.0001702182,0.0002440813],"domain_scores_gemma":[0.9989578,0.0001212297,0.0001368348,0.0004301073,0.0002216175,0.0001323834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001064525,0.001006305,0.00009373997,0.000603358,0.0005097376,0.00001800112,0.02443008,0.2271993,0.01346096,0.5877444,0.02740587,0.1164637],"study_design_scores_gemma":[0.000524061,0.0001044583,0.000005479661,0.00003489298,0.00001417261,0.00009702798,0.00001701218,0.9878495,0.0002496061,0.00288955,0.007990054,0.0002241387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009527794,0.0004148562,0.9972174,0.0002491497,0.0001276218,0.001431332,0.00001328149,0.0002315053,0.0002196058],"genre_scores_gemma":[0.2564402,0.00001119261,0.7397997,0.0002300723,0.0001347717,0.001848624,0.00001174733,0.00002444784,0.001499271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7606503,"threshold_uncertainty_score":0.6629473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01993788500999412,"score_gpt":0.255815781509133,"score_spread":0.2358778964991388,"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."}}