{"id":"W2400017509","doi":"10.1061/9780784479827.080","title":"Action Recognition Using a Wristband-Type Activity Tracker: Case Study of Masonry Work","year":2016,"lang":"en","type":"article","venue":"Construction Research Congress 2016","topic":"Hand Gesture Recognition Systems","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Accelerometer; Novelty; Activity recognition; Artificial intelligence; Action recognition; Classifier (UML); Work (physics); Machine learning; 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":[0.001984443,0.0001926055,0.000328737,0.0006623979,0.0003931333,0.0001753574,0.0003727801,0.0001777486,0.0001321656],"category_scores_gemma":[0.0003661308,0.000139558,0.00007064379,0.001434283,0.0003612205,0.001276526,0.0001961085,0.0003293926,0.0001478677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002097251,"about_ca_system_score_gemma":0.0003438377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003584085,"about_ca_topic_score_gemma":0.0001139946,"domain_scores_codex":[0.9959199,0.001571726,0.0004592551,0.000649729,0.0009309833,0.0004684054],"domain_scores_gemma":[0.9960114,0.0007797569,0.0003158702,0.0007126522,0.001971708,0.0002085532],"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":[0.0001985613,0.0003320994,0.00704534,0.00004484217,0.00009632547,0.0004279834,0.0004690066,0.000001515117,0.01227464,0.00005176312,0.0005488306,0.9785091],"study_design_scores_gemma":[0.07976665,0.01738381,0.04414566,0.01730079,0.0008233772,0.1309154,0.08601154,0.01216005,0.5456562,0.02302408,0.0325273,0.01028508],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662748,0.00006591377,0.03021527,0.0001672869,0.002052217,0.0008354583,0.00001314198,0.0001229928,0.0002529126],"genre_scores_gemma":[0.9972276,0.00006338309,0.002143182,0.000003902407,0.0002198049,0.00005497174,9.856122e-7,0.00001720664,0.0002689705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.968224,"threshold_uncertainty_score":0.5691012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.248871078359075,"score_gpt":0.4107494875873191,"score_spread":0.1618784092282441,"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."}}