{"id":"W2123515711","doi":"10.1007/978-3-642-01818-3_10","title":"An Iterative Hybrid Filter-Wrapper Approach to Feature Selection for Document Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Feature selection; Artificial intelligence; Cluster analysis; Maximization; Feature (linguistics); Filter (signal processing); Pattern recognition (psychology); Data mining; Greedy algorithm; Set (abstract data type); Selection (genetic algorithm); Machine learning; Algorithm; Mathematics; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000562289,0.0005387699,0.0004486668,0.0007839491,0.0003950083,0.00111723,0.001892898,0.000254413,0.000008452907],"category_scores_gemma":[0.00002939687,0.0004750451,0.0001354674,0.0004382175,0.0001061674,0.001210622,0.000421019,0.0005631502,0.00001990912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002884893,"about_ca_system_score_gemma":0.0001978114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008396266,"about_ca_topic_score_gemma":0.00002390961,"domain_scores_codex":[0.9964401,0.00004271862,0.000360422,0.001810022,0.0006891037,0.0006575988],"domain_scores_gemma":[0.9982899,0.0001305718,0.0001820618,0.0008161404,0.0003206381,0.0002606563],"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":[0.00002779404,0.00006448431,0.000004025344,0.00004234048,0.000009586608,0.000006227714,0.001244007,0.09690619,0.001525603,0.001196598,0.0005764139,0.8983967],"study_design_scores_gemma":[0.0003782302,0.0008258328,0.00003194948,0.0004407655,0.00000905073,0.00009231941,5.530677e-7,0.9363404,0.01210578,0.04290232,0.006024788,0.0008479943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001165627,0.00006844683,0.994936,0.0009363593,0.0008997772,0.001088762,0.00001136881,0.0001889809,0.001753747],"genre_scores_gemma":[0.04021906,0.00001065143,0.953667,0.004476197,0.0006564127,0.0000809435,0.00004476108,0.00003367932,0.0008112919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8975487,"threshold_uncertainty_score":0.9999197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01700608273074017,"score_gpt":0.2600075452697171,"score_spread":0.2430014625389769,"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."}}