{"id":"W4383682007","doi":"10.35490/ec3.2023.321","title":"Enhancing single-stage excavator activity recognition via knowledge distillation of temporal gradient data","year":2023,"lang":"en","type":"article","venue":"Computing in construction","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Excavator; Distillation; Frame (networking); Construct (python library); Artificial intelligence; Activity recognition; Exploit; Pattern recognition (psychology); Domain knowledge; Data mining; Machine learning; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003472286,0.0006845454,0.0008322404,0.00119476,0.0002299474,0.0006770358,0.0008407968,0.000422635,0.002150195],"category_scores_gemma":[0.001188579,0.0002723929,0.0004780625,0.0009162819,0.0003102663,0.001742003,0.00117477,0.0006759388,0.001161731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002447587,"about_ca_system_score_gemma":0.0007623135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003470824,"about_ca_topic_score_gemma":0.007710225,"domain_scores_codex":[0.9996933,0.00002194217,0.00001426027,0.0001005852,0.0001155436,0.00005434734],"domain_scores_gemma":[0.9996303,0.0001252119,0.00004168346,0.00008101237,0.00009513799,0.00002659496],"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":[0.0003071592,0.0002011017,0.002282691,0.0001521359,0.00004165107,0.0001196986,0.0001167773,0.01620162,0.08338403,0.001283617,0.00208372,0.8938257],"study_design_scores_gemma":[0.00003365399,0.0003387299,0.01162912,0.00004319289,0.00007956868,0.000488148,0.0001958641,0.8361901,0.1365097,0.003506383,0.01091547,0.0000700833],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1138389,0.0006583239,0.8775411,0.0001661879,0.0001011417,0.00008819877,0.0005791445,0.003927579,0.003099529],"genre_scores_gemma":[0.610028,0.0005201512,0.3835466,0.0001224262,0.00004852382,0.0001004962,0.001440294,0.0001660659,0.004027287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003470824,"threshold_uncertainty_score":0.007193148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2533656659201612,"score_gpt":0.4799525884914176,"score_spread":0.2265869225712564,"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."}}