{"id":"W4226192238","doi":"10.1109/jlt.2022.3168594","title":"Anomaly Prediction With Hybrid Supervised/Unsupervised Deep Learning for Elastic Optical Networks: A Multi-Index Correlative Approach","year":2022,"lang":"en","type":"article","venue":"Journal of Lightwave Technology","topic":"Optical Network Technologies","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"National Natural Science Foundation of China","keywords":"Anomaly detection; Computer science; Anomaly (physics); Robustness (evolution); Artificial intelligence; Data mining; Artificial neural network; Stability (learning theory); Time series; Unsupervised learning; Machine learning; Data modeling; Scheme (mathematics); Pattern recognition (psychology); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003855258,0.0003338052,0.0006363068,0.0008013553,0.0002815566,0.00003873313,0.000596471,0.0002950214,0.00003387145],"category_scores_gemma":[0.0002315049,0.0002880776,0.0001646782,0.0009213959,0.0002623812,0.0002251784,0.0002085634,0.002258659,0.000002897211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003367395,"about_ca_system_score_gemma":0.00004267334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.548412e-7,"about_ca_topic_score_gemma":0.000001766041,"domain_scores_codex":[0.9979373,0.00005369382,0.0007180901,0.0003033525,0.0003485875,0.0006390296],"domain_scores_gemma":[0.9988652,0.0002987977,0.0002175456,0.0002880213,0.0002237065,0.0001067152],"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":[0.0003007094,0.0002160786,0.01025621,0.00004586174,0.000373468,0.0001273023,0.00009471464,0.9761165,0.0004750607,0.00227112,0.0002790528,0.009443923],"study_design_scores_gemma":[0.002281036,0.00253822,0.001095058,0.00004164557,0.0001564689,0.001548918,0.001127699,0.9884331,0.0004139423,0.0004954172,0.001564188,0.000304373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2768272,0.001158188,0.7198815,0.0002173992,0.00037769,0.0004168161,0.000005916969,0.0008741416,0.0002411488],"genre_scores_gemma":[0.903498,0.00009432922,0.09597264,0.00001563027,0.0001337207,0.0001448797,0.00001115904,0.00008805566,0.00004160569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6266707,"threshold_uncertainty_score":0.9999571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008568483487334912,"score_gpt":0.1944682926385491,"score_spread":0.1858998091512142,"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."}}