{"id":"W2060003092","doi":"10.1016/j.knosys.2014.01.007","title":"Robust simultaneous positive data clustering and unsupervised feature selection using generalized inverted Dirichlet mixture models","year":2014,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Outlier; Artificial intelligence; Data mining; Pattern recognition (psychology); Latent Dirichlet allocation; Determining the number of clusters in a data set; Model selection; Machine learning; Dirichlet distribution; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Mathematics; Topic model","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"],"consensus_categories":[],"category_scores_codex":[0.001206069,0.0004646539,0.0006289954,0.000261484,0.0004494074,0.0005502895,0.001158891,0.0003741859,0.000001828411],"category_scores_gemma":[0.0001374607,0.0004105094,0.00007981444,0.0007706894,0.00006797937,0.0007437619,0.0004754887,0.0003872585,0.000005446973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001473208,"about_ca_system_score_gemma":0.0001886075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002500366,"about_ca_topic_score_gemma":0.000160086,"domain_scores_codex":[0.9961876,0.00129553,0.0004236858,0.001220904,0.0003195994,0.000552701],"domain_scores_gemma":[0.9973091,0.0004795047,0.0002031512,0.001326469,0.0003940724,0.0002876876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002481094,0.0004438878,0.0002241702,0.001517675,0.0003804046,0.00008305501,0.003953804,0.8141393,0.05753514,0.02211036,0.005521259,0.09384284],"study_design_scores_gemma":[0.001240123,0.00008397937,0.00001065165,0.0003073243,0.00006328391,0.0001027058,0.00001244381,0.995357,0.0006448098,0.000541867,0.001129839,0.0005059415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004321036,0.002188791,0.9907524,0.0002058027,0.000924546,0.0006386646,0.00004274292,0.0003186786,0.0006073203],"genre_scores_gemma":[0.6173545,0.00001199849,0.3814644,0.0002570883,0.0004499854,0.00001860728,0.00007678135,0.00005353357,0.0003131072],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6130335,"threshold_uncertainty_score":0.9998347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0613960326143573,"score_gpt":0.2785006054309159,"score_spread":0.2171045728165586,"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."}}