{"id":"W4393174563","doi":"10.1049/icp.2023.2525","title":"Detection and root cause analysis of performance degradation in optical networks using machine learning","year":2023,"lang":"en","type":"article","venue":"IET conference proceedings.","topic":"Optical Network Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Telus (Canada); Ciena (Canada); École de Technologie Supérieure","funders":"","keywords":"Computer science; Root cause analysis; Artificial intelligence; Machine learning; Supervised learning; Degradation (telecommunications); Root cause; Root (linguistics); Multiclass classification; Optical communication; Telecommunications; Support vector machine; Artificial neural network; Electronic engineering; Engineering; Reliability engineering","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":[0.0001930353,0.000116349,0.0002304391,0.0004540779,0.00004076079,0.0000440617,0.00008140079,0.000134059,0.000005293397],"category_scores_gemma":[0.00009230864,0.0001186209,0.00002541733,0.002006005,0.00006189883,0.0002115671,0.00005864293,0.0003145983,0.000001293389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004350996,"about_ca_system_score_gemma":0.000004812601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001439983,"about_ca_topic_score_gemma":0.00007542272,"domain_scores_codex":[0.9992613,0.000003392161,0.000222177,0.0001647472,0.0001112772,0.000237094],"domain_scores_gemma":[0.9997774,0.0000324781,0.00003824152,0.00005034818,0.00006884413,0.00003271685],"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":[0.00001552944,0.000008508365,0.4421743,0.0001043993,0.0001412528,0.000001749235,0.0002163919,0.5195284,0.009500939,0.00123746,0.000001452573,0.0270696],"study_design_scores_gemma":[0.00008524652,0.00003419055,0.0957309,0.00004282904,0.00009953949,0.000001536059,0.0001210945,0.9013952,0.002339958,0.00003309191,0.000008801559,0.0001076105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989133,0.00005991868,0.0100329,0.00001264656,0.0000396979,0.00007916356,6.042306e-7,0.0004416507,0.0002004497],"genre_scores_gemma":[0.9982026,0.0003713954,0.001376791,9.858609e-7,0.00001254319,0.000009389073,0.000005356864,0.00001371271,0.000007266422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3818668,"threshold_uncertainty_score":0.483722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02428437357829491,"score_gpt":0.234006996757138,"score_spread":0.2097226231788431,"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."}}