{"id":"W4392297233","doi":"10.3390/eng5010021","title":"Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data","year":2024,"lang":"en","type":"article","venue":"Eng—Advances in Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Fusion (Canada)","funders":"","keywords":"Categorical variable; Workflow; Computer science; Machine learning; Artificial intelligence; Supervised learning; Data science; Artificial neural network","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":[0.0398851,0.001674926,0.001423147,0.004479421,0.002207128,0.008699792,0.00590612,0.002141794,0.003307559],"category_scores_gemma":[0.08640842,0.001873029,0.003097308,0.004223207,0.008248914,0.00928778,0.005755543,0.005773906,0.003359545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002593382,"about_ca_system_score_gemma":0.008263012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004259592,"about_ca_topic_score_gemma":0.004076467,"domain_scores_codex":[0.9719865,0.01230903,0.003713869,0.003648134,0.007766727,0.000575731],"domain_scores_gemma":[0.9347536,0.0395106,0.002938206,0.01393909,0.008014257,0.0008441927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001177012,0.0002024009,0.002627128,0.001230577,0.0001305504,0.0003500907,0.003687364,0.03499845,0.003740591,0.6196744,0.007877778,0.325363],"study_design_scores_gemma":[0.00002945237,0.0000633154,0.0007064249,0.0004857272,0.00002794713,0.0002587064,0.0003447013,0.1110405,0.005358182,0.8422076,0.03938704,0.0000903467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000590303,0.0001239648,0.9969453,0.0004822965,0.00002125207,0.0002107745,0.0000983072,0.0005706697,0.0009571239],"genre_scores_gemma":[0.00881731,0.0002328809,0.9892628,0.0001435349,0.00004252023,0.0005530895,0.0002458144,0.0001736748,0.000528455],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0398851,"threshold_uncertainty_score":0.2109351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02318533791175964,"score_gpt":0.2550979615735789,"score_spread":0.2319126236618193,"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."}}