{"id":"W2287529450","doi":"10.1049/el.2015.2957","title":"Fast identification of partial discharge sources using blind source separation and kurtosis","year":2015,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Kurtosis; Blind signal separation; Identification (biology); Separation (statistics); Source separation; Computer science; Algorithm; Mathematics; Telecommunications; Statistics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000594022,0.0008894624,0.000629481,0.001134638,0.0003608727,0.0006184313,0.0005148595,0.000691941,0.0006773879],"category_scores_gemma":[0.002708788,0.0003434881,0.0007234607,0.0008911234,0.0007287348,0.001613167,0.00105231,0.0008409547,0.000484082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003302875,"about_ca_system_score_gemma":0.0005690649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005414191,"about_ca_topic_score_gemma":0.0004684812,"domain_scores_codex":[0.9995292,0.0001134457,0.00003204402,0.00008004579,0.0002119069,0.00003341859],"domain_scores_gemma":[0.9990795,0.000448098,0.0001460665,0.0001024477,0.0001999074,0.00002412445],"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":[0.0005504874,0.0001207459,0.001667948,0.0003282336,0.0001628813,0.0003635213,0.0002927179,0.2994542,0.2243129,0.03351114,0.001838269,0.4373971],"study_design_scores_gemma":[0.00002433165,0.00008871387,0.0005858022,0.00001270813,0.00001544817,0.0003022571,0.00001793077,0.9556703,0.03465159,0.007183776,0.00139431,0.00005292076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01011635,0.0001273684,0.989101,0.0000395041,0.00002160155,0.00001293452,0.00001919833,0.0002478587,0.0003142408],"genre_scores_gemma":[0.3394005,0.0006484264,0.6573623,0.00006310298,0.00007515442,0.0001007887,0.0002631343,0.0001481644,0.001938332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001134638,"threshold_uncertainty_score":0.003141522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02472799852238328,"score_gpt":0.2890817200638551,"score_spread":0.2643537215414718,"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."}}