{"id":"W4401732532","doi":"10.1021/acsfoodscitech.4c00331","title":"Freshness in Salmon by Hand-Held Devices: Methods in Feature Selection and Data Fusion for Spectroscopy","year":2024,"lang":"en","type":"article","venue":"ACS Food Science & Technology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Innovate UK; National Oceanic and Atmospheric Administration; Directorate for Biological Sciences; Queen's University Belfast; Queen's University; Small Business Innovation Research","keywords":"Fillet (mechanics); Principal component analysis; Feature selection; Fluorescence spectroscopy; Linear discriminant analysis; Absorbance; Spectroscopy; Biological system; Pattern recognition (psychology); Analytical Chemistry (journal); Context (archaeology); Artificial intelligence; Mathematics; Chemistry; Computer science; Fluorescence; Materials science; Optics; Chromatography; Physics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006878377,0.0001674938,0.000259432,0.001328218,0.0001726348,0.0001518682,0.0009337451,0.0003509231,0.00002444139],"category_scores_gemma":[0.0004465532,0.0001516048,0.00001860399,0.006604936,0.0004308897,0.0003973918,0.0003714136,0.0004838011,0.000001366625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000187665,"about_ca_system_score_gemma":0.0001451111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006378784,"about_ca_topic_score_gemma":0.0007354641,"domain_scores_codex":[0.9982259,0.00001164667,0.0002057354,0.0009192691,0.0001682099,0.0004692696],"domain_scores_gemma":[0.9992374,0.0001499787,0.00005571697,0.000474863,0.00003879499,0.00004327668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001355218,0.00004008111,0.006175824,0.00007775953,0.00001030317,0.000002984333,0.00005734016,0.000001875857,0.9859014,0.0009947134,0.000423976,0.006300228],"study_design_scores_gemma":[0.0002259212,0.0001380435,0.0001161481,0.00006506484,0.00003291389,0.0000311766,0.0005418308,0.003964439,0.9845326,0.003531399,0.006651699,0.0001687804],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665366,0.01542362,0.01425814,0.002682691,0.0001140741,0.0001729842,0.00007784831,0.0002598511,0.0004741274],"genre_scores_gemma":[0.9850712,0.000235948,0.01439587,0.00004012159,0.00003126058,0.00004374685,0.00003453532,0.0000150281,0.0001323003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01853452,"threshold_uncertainty_score":0.6182263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02948878044193059,"score_gpt":0.3845111699597825,"score_spread":0.3550223895178519,"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."}}