{"id":"W4213180603","doi":"10.1109/ceidp50766.2021.9705342","title":"Hybrid Algorithm Based on Machine Learning and Deep Learning to Identify Ceramic Insulators and Detect Physical Damages","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)","topic":"Power Line Inspection Robots","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Tech University","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Deep learning; Classifier (UML); Algorithm; Segmentation; Image segmentation","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":[0.000618795,0.0006137862,0.0005596963,0.001096236,0.0002815585,0.0006112156,0.0008531737,0.0007782925,0.001155955],"category_scores_gemma":[0.0008060076,0.0002820185,0.0005830742,0.0006469582,0.0002953697,0.000789527,0.0005301228,0.0006043032,0.0003585954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006258118,"about_ca_system_score_gemma":0.0007720463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003492859,"about_ca_topic_score_gemma":0.004614964,"domain_scores_codex":[0.9996626,0.00003777404,0.00002484392,0.00008362096,0.000144525,0.0000466011],"domain_scores_gemma":[0.9996277,0.0001206976,0.00003972832,0.00004268393,0.0001498576,0.00001930738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002805789,0.0003381774,0.004613159,0.0001124443,0.0002237623,0.00009916777,0.00009362478,0.1769536,0.0383424,0.005065625,0.002478053,0.7713994],"study_design_scores_gemma":[0.0000177682,0.0001111485,0.00100831,0.000006795777,0.0000279783,0.00007024581,0.00001246294,0.9858615,0.01029257,0.001295783,0.001283954,0.00001142652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05290745,0.0004409888,0.9431482,0.000130907,0.00009528178,0.00007932852,0.0000561624,0.001194218,0.001947382],"genre_scores_gemma":[0.5006835,0.0002465045,0.4916724,0.0002469433,0.00006615037,0.0001615095,0.0002599854,0.00008204252,0.006581008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003492859,"threshold_uncertainty_score":0.006945074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154524436141301,"score_gpt":0.2554563282577372,"score_spread":0.2439110838963242,"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."}}