{"id":"W4390842165","doi":"10.1049/ell2.13042","title":"PCBDet: An efficient deep neural network object detection architecture for automatic PCB component detection on the edge","year":2024,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Deep learning; Component (thermodynamics); Object detection; Artificial intelligence; Artificial neural network; Inference; Throughput; Enhanced Data Rates for GSM Evolution; Task (project management); Real-time computing; Pattern recognition (psychology); 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":[0.000630287,0.0002981866,0.0002176246,0.0001880753,0.0003891953,0.0002407083,0.0001501431,0.0001630044,0.00001203754],"category_scores_gemma":[0.00002765963,0.0002246118,0.0002145817,0.0004911347,0.00002370604,0.000069088,0.00001296693,0.0007607491,0.00003528642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005109964,"about_ca_system_score_gemma":0.00001663901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001541147,"about_ca_topic_score_gemma":0.0001563436,"domain_scores_codex":[0.9982311,0.0001616407,0.0003413675,0.0003520066,0.0002776701,0.0006362203],"domain_scores_gemma":[0.9992296,0.0003149823,0.00004999572,0.0003102868,0.00002323181,0.00007198198],"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":[0.00004560051,0.00001037159,5.384122e-7,0.00005860611,0.00006671114,0.000002732866,0.0002052889,0.7471893,0.1027158,0.0001331949,0.0004107221,0.1491611],"study_design_scores_gemma":[0.0002420424,0.0004628559,0.00005259844,0.00005638275,0.00004432432,0.00005114727,0.00002558277,0.9360322,0.05125013,0.00009790623,0.01142655,0.0002582324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6880485,0.0005366402,0.3057096,0.0003636149,0.003431009,0.0009176958,0.000003675963,0.0009437037,0.00004561255],"genre_scores_gemma":[0.9976113,0.000005202636,0.00005234205,0.0003143451,0.001653659,0.0002539401,0.000009040882,0.00009230999,0.000007867547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3095628,"threshold_uncertainty_score":0.9159405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009973610875854641,"score_gpt":0.2141812816779748,"score_spread":0.2042076708021202,"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."}}