{"id":"W2157487910","doi":"10.1109/tpami.2008.155","title":"A Hybrid Feature Extraction Selection Approach for High-Dimensional Non-Gaussian Data Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Université de Sherbrooke","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Cluster analysis; Computer science; Mixture model; Feature extraction; Feature selection; Gaussian; Selection (genetic algorithm); Dirichlet distribution; Categorization; Expectation–maximization algorithm; Gaussian process; Maximization; Model selection; Bhattacharyya distance; Mathematics; Maximum likelihood; Statistics; Mathematical optimization","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":[0.0004921359,0.0002741195,0.0003610959,0.000461934,0.0003540303,0.0002059969,0.000596146,0.00009762505,0.00001722624],"category_scores_gemma":[0.000004308138,0.0002358431,0.0001801085,0.0006794218,0.00002637419,0.0005737132,0.000009525882,0.0003609981,0.000002478824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003902281,"about_ca_system_score_gemma":0.00002669399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003111201,"about_ca_topic_score_gemma":0.0002098887,"domain_scores_codex":[0.9980856,0.00009043067,0.0003208734,0.0009518872,0.0002592269,0.0002920162],"domain_scores_gemma":[0.9988016,0.00008535276,0.0001319006,0.0007586658,0.00008027926,0.0001422132],"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":[0.00003139177,0.0002018641,0.000008719669,0.000015307,0.0002255241,0.000003066161,0.00006273248,0.0275031,0.001259149,0.0001436959,0.00007429381,0.9704711],"study_design_scores_gemma":[0.0001335205,0.0001821307,0.0003558447,0.000014201,0.0003639947,0.00005449178,0.000003771842,0.9571747,0.04027386,0.001144731,0.00003693989,0.0002618831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002774845,0.00006083906,0.9980765,0.0008782992,0.0002088556,0.0002755381,0.00008529455,0.00009191694,0.00004524728],"genre_scores_gemma":[0.6694055,0.00005054794,0.3297952,0.0004534845,0.0000495796,0.00001743213,0.00004834816,0.000008478099,0.000171531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9702092,"threshold_uncertainty_score":0.9617403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02827560538389571,"score_gpt":0.3004763755083246,"score_spread":0.2722007701244288,"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."}}