{"id":"W2398397706","doi":"10.1117/12.2224402","title":"Artificial neural networks (ANNS) versus partial least squares (PLS) for spectral interference correction for taking part of the lab to the sample types of applications: an experimental study","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interference (communication); Spectrometer; Partial least squares regression; Artificial neural network; Optics; Computer science; Resolution (logic); Sample (material); Spectral resolution; Imaging spectrometer; Physics; Artificial intelligence; Telecommunications; Spectral line; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005767692,0.0001708773,0.0002401246,0.00002823851,0.0001367652,0.00004869062,0.0007588843,0.00006415138,0.00001271442],"category_scores_gemma":[0.0004075426,0.0001004464,0.0003583037,0.0002156905,0.0002560256,0.000250971,0.0001638872,0.00009403697,3.883767e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190445,"about_ca_system_score_gemma":0.000008034019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009856891,"about_ca_topic_score_gemma":0.000004528332,"domain_scores_codex":[0.9985452,1.326534e-7,0.0005192909,0.0002986518,0.0003894933,0.0002472321],"domain_scores_gemma":[0.9989436,0.0002656202,0.0003749015,0.00008272471,0.0002749418,0.00005816288],"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":[0.001530473,0.0009791987,0.008689783,0.0001261354,0.0005105917,1.053469e-8,0.002149764,0.01081623,0.9155295,0.05401035,0.001152174,0.004505802],"study_design_scores_gemma":[0.001321818,0.002900246,0.002372297,0.0001973919,0.0003444131,0.00000153561,0.01102548,0.1152314,0.8646173,0.000641635,0.0009734313,0.0003730795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955422,0.0000124055,0.002107012,0.0007730232,0.0004713641,0.000979721,0.00006449054,0.00002105683,0.0000287772],"genre_scores_gemma":[0.9945623,0.000002663476,0.004344039,0.00001222683,0.0005317907,0.000490054,0.000003072086,0.00002052523,0.00003330719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1044151,"threshold_uncertainty_score":0.4096086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03068962423332827,"score_gpt":0.2759087725695792,"score_spread":0.2452191483362509,"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."}}