{"id":"W2986573554","doi":"10.3390/make1040061","title":"Multi-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysis","year":2019,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Threat Reduction Agency; Nvidia","keywords":"Thresholding; Pattern recognition (psychology); Linear discriminant analysis; Binary number; Artificial intelligence; Partial least squares regression; Sample (material); Artificial neural network; Computer science; Noise (video); Relevance (law); Mathematics; Machine learning; Chemistry; Chromatography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001530227,0.0008308657,0.0008230535,0.001313017,0.0005436072,0.0009458767,0.001380909,0.001441655,0.001790129],"category_scores_gemma":[0.00319459,0.0003358841,0.0006381184,0.0009089949,0.0007426915,0.001517272,0.001268137,0.001164751,0.0009153198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005211418,"about_ca_system_score_gemma":0.0004907126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001072372,"about_ca_topic_score_gemma":0.001637568,"domain_scores_codex":[0.9987926,0.0002791194,0.00005952425,0.0003762064,0.0003544402,0.0001379505],"domain_scores_gemma":[0.999006,0.0003833794,0.0001434598,0.0001680055,0.000258236,0.00004101593],"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":[0.0004865957,0.0003524917,0.002202624,0.0002087191,0.0001050206,0.0001281622,0.0001522517,0.1095028,0.1214536,0.005980597,0.002032904,0.7573943],"study_design_scores_gemma":[0.00001056884,0.00004731703,0.0006025553,0.000009398676,0.00001791045,0.00004626927,0.00002172808,0.9677784,0.02608861,0.004660147,0.0007017127,0.00001533668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01969374,0.0001974822,0.9782049,0.00008750051,0.00004208602,0.0000343026,0.00003797973,0.000969441,0.0007325559],"genre_scores_gemma":[0.3506355,0.000123913,0.6470038,0.0001464174,0.00005612207,0.0001082232,0.0001926666,0.0001681009,0.001565121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001790129,"threshold_uncertainty_score":0.008092701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02454074126847133,"score_gpt":0.3087977437863794,"score_spread":0.284257002517908,"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."}}