{"id":"W4283213951","doi":"10.1109/iemtronics55184.2022.9795745","title":"Intelligent Feature Selection on Multivariate Dataset using Advanced Data Profiling","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Profiling (computer programming); Computer science; Data mining; Machine learning; Multivariate statistics; Artificial intelligence","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":[0.0009583732,0.0003859957,0.0003107658,0.000279331,0.0008568998,0.0004653371,0.003446486,0.0001012201,0.0001091358],"category_scores_gemma":[0.00005750013,0.0004214238,0.00006957779,0.0005008134,0.00004705854,0.0007238003,0.002132151,0.001329408,0.00001748008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000901856,"about_ca_system_score_gemma":0.001054039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009710729,"about_ca_topic_score_gemma":0.00009694326,"domain_scores_codex":[0.996272,0.0001405535,0.0004544083,0.00149163,0.0008637125,0.000777717],"domain_scores_gemma":[0.99777,0.0001212066,0.0003734276,0.001397485,0.0001741353,0.0001637667],"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":[0.00009413601,0.0004283183,0.00003176938,0.0000169651,0.0002688944,0.000009611497,0.000206483,0.02079336,0.01742333,0.806585,0.004280067,0.1498621],"study_design_scores_gemma":[0.0004745146,0.0002673992,0.000005706813,0.0000159983,0.00002644489,0.00005395498,0.0001226707,0.7579805,0.002123862,0.003729716,0.2348432,0.0003560617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03269697,0.001950121,0.945067,0.005974513,0.002850809,0.001583289,0.009196018,0.000355402,0.0003258171],"genre_scores_gemma":[0.7188888,0.003571181,0.2490804,0.00200795,0.00066021,0.0009169281,0.02326884,0.0001727112,0.00143293],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8028553,"threshold_uncertainty_score":0.9998237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06475998024089975,"score_gpt":0.3384563381554218,"score_spread":0.2736963579145221,"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."}}