{"id":"W3212535423","doi":"10.1016/j.aca.2021.339255","title":"Evaluating the impact of NIR pre-processing methods via multiblock partial least-squares","year":2021,"lang":"en","type":"article","venue":"Analytica Chimica Acta","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partial least squares regression; Preprocessor; Data processing; Property (philosophy); Least-squares function approximation; Noise (video); Data pre-processing; Artificial intelligence; Data mining; Computer science; Pattern recognition (psychology); Chemistry; Machine learning; Statistics; Mathematics","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":[0.002521838,0.001617065,0.000661461,0.0006230854,0.0005377139,0.0008797127,0.0006446366,0.0008704122,0.002249741],"category_scores_gemma":[0.007930225,0.0003615239,0.0006696255,0.0006157972,0.0003594771,0.001172583,0.0006454819,0.001128111,0.001108962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002957749,"about_ca_system_score_gemma":0.001491154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006727085,"about_ca_topic_score_gemma":0.009994769,"domain_scores_codex":[0.9991255,0.0003192798,0.0000536954,0.0001262449,0.0002986617,0.00007648828],"domain_scores_gemma":[0.9955021,0.003033374,0.0001629601,0.0003127228,0.0009218498,0.0000670863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002593906,0.001006847,0.005763165,0.0008019574,0.0003751601,0.0001274892,0.0001438921,0.26155,0.2123697,0.001610778,0.003034544,0.5106226],"study_design_scores_gemma":[0.00005551821,0.0005655584,0.005836676,0.00002555998,0.0001578043,0.00006970853,0.0001033002,0.8797174,0.1102874,0.0007747631,0.002361613,0.00004476313],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2544456,0.001665852,0.7366499,0.0003428423,0.000221115,0.0001974234,0.0005037766,0.00307488,0.002898658],"genre_scores_gemma":[0.3479559,0.0005991526,0.6462684,0.000166096,0.00004314759,0.000140739,0.001073676,0.0005428997,0.003210024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006727085,"threshold_uncertainty_score":0.01337588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06532855896785628,"score_gpt":0.4570709860493717,"score_spread":0.3917424270815154,"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."}}