{"id":"W4381199109","doi":"10.1109/tvt.2023.3285599","title":"Multivariate Variance-Based Genetic Ensemble Learning for Satellite Anomaly Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Actua; University of Waterloo","funders":"","keywords":"Anomaly detection; Computer science; Artificial intelligence; Bootstrapping (finance); Ensemble learning; Multivariate statistics; Random forest; Machine learning; Boosting (machine learning); Time series; Data mining; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001978563,0.0002110683,0.0002043566,0.0008978093,0.0006434345,0.00006902425,0.0005086737,0.0003522695,0.000006718104],"category_scores_gemma":[0.0000129859,0.0002284792,0.0001779269,0.002269073,0.00007788853,0.0001297831,0.000005733496,0.0004005555,0.0001757474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008950552,"about_ca_system_score_gemma":0.00005230902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000025985,"about_ca_topic_score_gemma":0.00002478797,"domain_scores_codex":[0.9984317,0.00005337454,0.0003023011,0.0006367627,0.0001553998,0.0004204332],"domain_scores_gemma":[0.9988985,0.0001161932,0.0001178398,0.0006658745,0.0001366698,0.00006489897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002478321,0.0001274984,0.0000344987,0.00002494328,0.00004674164,0.0000116811,0.00003967288,0.07736891,0.230605,0.002702194,0.00001636638,0.6889977],"study_design_scores_gemma":[0.0004311395,0.0003880903,0.0004378748,0.00001502349,0.00002188342,0.00002177359,0.00001717664,0.4199256,0.5622196,0.003422207,0.01285938,0.0002402871],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02806109,0.00003156913,0.965542,0.001195963,0.000247074,0.0006420311,0.000004284856,0.004227222,0.00004881511],"genre_scores_gemma":[0.9231754,0.0000466979,0.07496645,0.00009807442,0.00002352422,0.001274395,0.000002497293,0.00003291808,0.0003800271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8951143,"threshold_uncertainty_score":0.931711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01448541791087849,"score_gpt":0.2491510195923562,"score_spread":0.2346656016814777,"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."}}