{"id":"W3123980720","doi":"10.15353/jcvis.v6i1.3554","title":"PlasticNet: Deep Learning for Automatic Microplastic Recognition via FT-IR Spectroscopy","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Discriminative model; Pattern recognition (psychology); Deep learning; Convolutional neural network; Computer science; Convolution (computer science); Spectroscopy; Machine learning; Artificial neural network; Speech recognition; Physics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00007037769,0.0001107945,0.0002217198,0.0001092972,0.00006512477,0.00008502542,0.00004405409,0.00003677099,0.000007216585],"category_scores_gemma":[0.0001966687,0.0000997789,0.00005453393,0.0001010199,0.00002906195,0.000168577,0.00001401683,0.0001914619,0.000005170521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000725104,"about_ca_system_score_gemma":0.000009918896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.506412e-7,"about_ca_topic_score_gemma":1.119488e-7,"domain_scores_codex":[0.9991922,0.00002188701,0.000398197,0.00008177666,0.0001713443,0.0001345984],"domain_scores_gemma":[0.9990059,0.0004935529,0.0001558056,0.00003645511,0.00025735,0.00005092347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001741822,0.00002649325,0.0001684274,0.0003743338,0.00006207461,0.00002979612,0.0000968687,0.6133763,0.3405095,0.00004730971,0.001144885,0.04414658],"study_design_scores_gemma":[0.0005570978,0.00006102233,0.0003579537,0.0003592359,0.00002517337,0.0009428552,0.0002882353,0.9744775,0.01778983,0.004174722,0.000839647,0.000126682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2322324,0.001303604,0.7655194,0.00008447155,0.0006687395,0.00005644347,0.000002440547,0.0001023959,0.00003008638],"genre_scores_gemma":[0.9197987,0.00005347322,0.07990474,0.00001454029,0.0001863063,0.000002302216,0.00001161536,0.0000208256,0.000007536396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6875662,"threshold_uncertainty_score":0.4068865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005962170591127816,"score_gpt":0.2366078660247702,"score_spread":0.2306456954336423,"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."}}