{"id":"W3159100424","doi":"10.1016/j.knosys.2021.107051","title":"Online mixture-based clustering for high dimensional count data using Neerchal–Morel distribution","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Mixture model; Expectation–maximization algorithm; Artificial intelligence; Clustering high-dimensional data; Selection (genetic algorithm); Maximization; Machine learning; Unsupervised learning; Model selection; Data mining; Pattern recognition (psychology); Maximum likelihood; Mathematical optimization; Statistics","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":[0.001548615,0.0003702333,0.0005576517,0.0001108327,0.0003842026,0.0003496362,0.001197653,0.0002421339,0.00000546417],"category_scores_gemma":[0.0002552099,0.0003453583,0.0001476973,0.0006032995,0.00006179648,0.0003810925,0.0004634167,0.0002508268,0.000009444021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003158222,"about_ca_system_score_gemma":0.001384019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000864572,"about_ca_topic_score_gemma":0.0001363378,"domain_scores_codex":[0.9966955,0.000491503,0.0006820843,0.001128452,0.0004241239,0.0005783999],"domain_scores_gemma":[0.9961005,0.0005484331,0.0002402464,0.002042607,0.0008329757,0.0002352201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007238695,0.009537626,0.0004727841,0.01053241,0.0009496507,0.0006625031,0.001430814,0.1820843,0.2037117,0.3115749,0.04875772,0.2295616],"study_design_scores_gemma":[0.001439392,0.00005653597,0.00005464356,0.0004889488,0.00005626287,0.00003067622,0.000009804525,0.9844849,0.003978601,0.0005792265,0.008407223,0.0004137663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00324143,0.002376053,0.9879888,0.0005235567,0.003537296,0.0005817174,0.00151767,0.0001946934,0.00003881169],"genre_scores_gemma":[0.4105214,0.000001651343,0.5851624,0.0001985992,0.0007495567,0.00004805915,0.003142624,0.00004285649,0.0001327841],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8024006,"threshold_uncertainty_score":0.9998999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07983090663054626,"score_gpt":0.3283377075129023,"score_spread":0.248506800882356,"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."}}