{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004167398,0.001566234,0.003609913,0.002195766,0.001652441,0.00296878,0.004542152,0.001866536,0.001700191],"category_scores_gemma":[0.01728259,0.001365683,0.002702338,0.002933449,0.002110699,0.003744541,0.00446587,0.002837774,0.001278479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146031,"about_ca_system_score_gemma":0.001624368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005114263,"about_ca_topic_score_gemma":0.007681092,"domain_scores_codex":[0.994903,0.001988974,0.000250356,0.001299306,0.001224571,0.0003338721],"domain_scores_gemma":[0.9936553,0.003892104,0.0004812769,0.0009104984,0.0009190058,0.0001418234],"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":[0.0007737993,0.0003789587,0.001984195,0.0004216742,0.0004939238,0.0002613126,0.0005040247,0.376626,0.01087959,0.05756961,0.007173915,0.542933],"study_design_scores_gemma":[0.00001622721,0.00002301105,0.0003137782,0.00001377606,0.0000347259,0.00007239585,0.00003544747,0.9514651,0.002147795,0.04497883,0.0008683166,0.00003057229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003273068,0.0001266188,0.9959288,0.00007152447,0.00001670604,0.00002134395,0.00003996578,0.0002139666,0.000307901],"genre_scores_gemma":[0.2785649,0.0003047051,0.7156498,0.0002228153,0.0001710332,0.0003202721,0.0008734085,0.0004127843,0.003480185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005114263,"threshold_uncertainty_score":0.02203953,"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."}}