{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002741779,0.001659757,0.003539897,0.003186904,0.001354159,0.002004299,0.004226333,0.002224964,0.004189105],"category_scores_gemma":[0.005006953,0.001051703,0.002682482,0.004321166,0.0007338798,0.00186886,0.00181277,0.001580965,0.003226849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009826808,"about_ca_system_score_gemma":0.001828633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01226531,"about_ca_topic_score_gemma":0.01393332,"domain_scores_codex":[0.9974033,0.0006352381,0.000250457,0.0005280191,0.0009389007,0.0002440053],"domain_scores_gemma":[0.9965221,0.001445205,0.0001390733,0.0004695908,0.001323109,0.0001008894],"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":[0.0003365089,0.0002002197,0.0005105997,0.0001534988,0.0002583702,0.00008992126,0.0001172071,0.05120145,0.01878641,0.002011724,0.008037466,0.9182968],"study_design_scores_gemma":[0.0000452791,0.0001051549,0.0006529574,0.00001272693,0.00008656181,0.0001388123,0.00004218991,0.9799531,0.01223993,0.003831181,0.002850262,0.00004190924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002260362,0.0001478726,0.9958518,0.00002771624,0.00002784675,0.00004314684,0.00006000781,0.001422638,0.0001587764],"genre_scores_gemma":[0.03409912,0.0001387584,0.9620413,0.00008653957,0.00007473301,0.0002154402,0.0006357776,0.0003346783,0.002373687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01226531,"threshold_uncertainty_score":0.02438784,"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."}}