{"id":"W2965643259","doi":"10.1016/j.solener.2019.07.063","title":"Hotspot diagnosis for solar photovoltaic modules using a Naive Bayes classifier","year":2019,"lang":"en","type":"article","venue":"Solar Energy","topic":"Photovoltaic System Optimization Techniques","field":"Energy","cited_by":166,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Photovoltaic system; Hotspot (geology); Naive Bayes classifier; Computer science; Classifier (UML); Bayes classifier; Artificial intelligence; Pattern recognition (psychology); Support vector machine; Geology; Electrical engineering; Engineering; Geophysics","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":[0.0003395232,0.0004535764,0.0006218222,0.0003510673,0.0002296625,0.0001313062,0.0004808777,0.0004144266,0.000629253],"category_scores_gemma":[0.0001617893,0.0004540837,0.0003488719,0.0004335772,0.00007331627,0.0004471474,0.0001438988,0.0001527873,0.00006485297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002831248,"about_ca_system_score_gemma":0.0001156309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005396497,"about_ca_topic_score_gemma":0.0005620511,"domain_scores_codex":[0.9973424,0.0001741758,0.0006056576,0.0007730006,0.0004104406,0.0006943124],"domain_scores_gemma":[0.9980353,0.0002851508,0.0003155613,0.000860563,0.0003277707,0.00017566],"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":[0.0004392076,0.0006404585,0.01813863,0.0004845875,0.0009662585,0.00003611506,0.0010495,0.05822061,0.8230419,0.06026571,0.01697439,0.01974259],"study_design_scores_gemma":[0.0009560614,0.0001780249,0.0001652907,0.0001766672,0.00007435333,0.00001762389,0.0002013223,0.1518208,0.637089,0.004951524,0.2036465,0.0007229056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4379458,0.001988761,0.5336256,0.0001325488,0.002746985,0.002413888,0.0003068094,0.002533551,0.01830599],"genre_scores_gemma":[0.9623368,0.0002704352,0.03238306,0.0006239555,0.0002973665,0.0009763872,0.0001310497,0.0002132848,0.002767641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.524391,"threshold_uncertainty_score":0.9997911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02240145925081027,"score_gpt":0.254695134679976,"score_spread":0.2322936754291657,"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."}}