{"id":"W3105676231","doi":"10.1117/12.2576447","title":"Anomaly detection using 1D convolutional neural networks for surface enhanced raman scattering","year":2020,"lang":"en","type":"article","venue":"","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Overfitting; Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Outlier; Convolutional neural network; Computer science; Class (philosophy); Identification (biology); Anomaly (physics); Artificial neural network; One-class classification; Machine learning; Support vector machine; Physics","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":[0.00007611552,0.00009967259,0.00009415273,0.000009042019,0.00007749633,0.00002038833,0.0001482627,0.0001429922,0.00005914655],"category_scores_gemma":[0.00006833042,0.00009145612,0.00007751408,0.00008872773,0.0001090668,0.00000306483,0.0001189374,0.0001029982,0.000001190919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002479545,"about_ca_system_score_gemma":0.00002280621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001118624,"about_ca_topic_score_gemma":0.000002655129,"domain_scores_codex":[0.9991608,0.00001597362,0.0001381898,0.0002985143,0.0001147444,0.0002718377],"domain_scores_gemma":[0.9996497,0.00001624075,0.00002918531,0.0001027031,0.00006146973,0.0001407059],"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":[0.0001538519,0.00001243301,0.0001385478,0.00001386085,0.00001327848,3.050838e-7,0.00000260695,0.0003296308,0.998074,0.00001528164,0.0004222972,0.0008238817],"study_design_scores_gemma":[0.0002166003,0.0002327116,0.00004769868,0.000003034839,0.000004359927,0.000002687766,0.000006856605,0.1780099,0.8190218,0.00003144657,0.002323573,0.00009929709],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5481966,0.00007035318,0.4511101,0.0002559255,0.00004102788,0.000117461,0.000003576368,0.00002672741,0.0001783078],"genre_scores_gemma":[0.9907141,0.00002006842,0.00785143,0.0007797515,0.0004440509,0.00001572365,0.00004991902,0.00001496517,0.0001100446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4432587,"threshold_uncertainty_score":0.3729472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02461229260578808,"score_gpt":0.3188630608268405,"score_spread":0.2942507682210524,"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."}}