{"id":"W4386714095","doi":"10.1002/cjce.25076","title":"Deep chemometrics using one‐dimensional convolutional neural networks for predicting crude oil properties from FTIR spectral data","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partial least squares regression; Chemometrics; Convolutional neural network; Interpretability; Biological system; Artificial neural network; Principal component analysis; Fourier transform infrared spectroscopy; Computer science; Artificial intelligence; Principal component regression; Pattern recognition (psychology); Fourier transform; Preprocessor; Mean squared error; Mathematics; Statistics; Machine learning; Optics; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003188491,0.0002064721,0.0003474377,0.000296829,0.0001891212,0.0001053932,0.0008395916,0.0001591246,0.0001538229],"category_scores_gemma":[0.001199374,0.0001721705,0.0001491753,0.0009196324,0.0001039796,0.0001909753,0.00009416448,0.0006380531,0.000001620132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004099981,"about_ca_system_score_gemma":0.0003630699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001064542,"about_ca_topic_score_gemma":0.0001070595,"domain_scores_codex":[0.9983439,0.000006908762,0.0004775761,0.000225245,0.0003541411,0.0005921865],"domain_scores_gemma":[0.9984826,0.0004244309,0.000191006,0.0003205422,0.0001633404,0.0004180661],"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":[0.00006253573,0.00002138835,0.001390861,0.0001020076,0.0006008705,0.00003974743,0.0001157252,0.402211,0.5942507,0.00005456782,0.0006997701,0.0004508183],"study_design_scores_gemma":[0.0003730768,0.000008158228,0.00008145097,0.00007642555,0.0002432533,0.0000698791,0.00003698495,0.8728104,0.125946,0.00004822165,0.0001203948,0.0001857123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947101,0.002614463,0.001715884,0.0004611489,0.0002758279,0.00003035842,0.0001059675,0.00004711663,0.00003907932],"genre_scores_gemma":[0.9956787,0.000008674288,0.002316041,0.00006125599,0.001721033,0.00000275954,0.0001199089,0.00004400654,0.00004758107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4705994,"threshold_uncertainty_score":0.7020909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05514006406698218,"score_gpt":0.2426008797624582,"score_spread":0.187460815695476,"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."}}