{"id":"W3154748208","doi":"10.1109/crv52889.2021.00028","title":"Improving state-of-the-art in Detecting Student Engagement with Resnet and TCN Hybrid Network","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University Health Network","funders":"","keywords":"Residual neural network; Computer science; Convolutional neural network; Residual; Student engagement; Key (lock); Deep learning; Artificial intelligence; Architecture; Feature (linguistics); Machine learning; Pattern recognition (psychology); Mathematics education; Psychology; Computer security; Algorithm","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":[0.001523352,0.002314327,0.0009477866,0.001472539,0.0003189259,0.001051519,0.001444988,0.00121985,0.001732467],"category_scores_gemma":[0.003984504,0.0003571393,0.0008528495,0.0007624545,0.0003564169,0.001628494,0.0009245182,0.001557383,0.00145946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000727776,"about_ca_system_score_gemma":0.0006327936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01021989,"about_ca_topic_score_gemma":0.01760593,"domain_scores_codex":[0.9990681,0.000245258,0.00004803313,0.000307997,0.0001893446,0.0001413411],"domain_scores_gemma":[0.9987893,0.000591973,0.0001074919,0.0001482291,0.0002847968,0.00007825206],"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":[0.0006592688,0.0007141549,0.01550696,0.0003504519,0.0004004046,0.0001959879,0.0001700309,0.1010126,0.01543052,0.00182932,0.01132075,0.8524096],"study_design_scores_gemma":[0.00001802962,0.0001684787,0.003890704,0.00004172161,0.00005425419,0.00004587982,0.00005953068,0.9863107,0.005628858,0.001356827,0.00240259,0.00002241903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.40702,0.01396315,0.5444558,0.00159541,0.0009065924,0.0002962059,0.003010288,0.01241759,0.01633492],"genre_scores_gemma":[0.8649541,0.002217875,0.1149165,0.0004862052,0.000286633,0.0001832185,0.005944305,0.0003255283,0.01068561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01021989,"threshold_uncertainty_score":0.02032077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01163720469945264,"score_gpt":0.2558776133681712,"score_spread":0.2442404086687186,"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."}}