{"id":"W3159307704","doi":"10.1016/j.chemolab.2021.104315","title":"Mixture robust semi-supervised probabilistic principal component regression with missing input data","year":2021,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unavailability; Outlier; Principal component analysis; Probabilistic logic; Computer science; Missing data; Principal component regression; Data mining; Expectation–maximization algorithm; Component (thermodynamics); Regression; Maximization; Statistical model; Regression analysis; Robust regression; Artificial intelligence; Machine learning; Pattern recognition (psychology); Statistics; Mathematics; Mathematical optimization; Maximum likelihood","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004551213,0.0003219654,0.0004846549,0.0002885218,0.0001401427,0.000351838,0.0002919241,0.0001999607,0.00002158625],"category_scores_gemma":[0.0002168084,0.0002537198,0.00003415706,0.001980559,0.000047383,0.0002097988,0.000118217,0.000314294,0.00001131094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619284,"about_ca_system_score_gemma":0.0001008748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001728604,"about_ca_topic_score_gemma":0.00001069158,"domain_scores_codex":[0.9980696,0.0001002997,0.000519581,0.0005363174,0.0004451775,0.0003289614],"domain_scores_gemma":[0.9982704,0.0001156291,0.0001021981,0.000882771,0.0003580336,0.0002710008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005065391,0.001697391,0.02594136,0.0332549,0.003450058,0.002019705,0.00497789,0.3777665,0.4075571,0.002253019,0.05249687,0.08807873],"study_design_scores_gemma":[0.000571805,0.00008491157,0.0001218794,0.0007375372,0.00005867364,0.0001105437,0.0009146326,0.8437487,0.01165596,0.000002783933,0.1414852,0.0005073634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7910273,0.1116648,0.08455608,0.0002394249,0.005987942,0.001820473,0.0005661537,0.001209653,0.002928144],"genre_scores_gemma":[0.9983336,0.000550002,0.000276055,0.0000473016,0.0002848446,0.00003318719,0.0001453656,0.00006517044,0.0002645278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4659822,"threshold_uncertainty_score":0.9999915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03255291854287938,"score_gpt":0.2368165462045662,"score_spread":0.2042636276616868,"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."}}