{"id":"W3044651858","doi":"10.1109/access.2020.3010715","title":"Deep Neural Networks for Human Activity Recognition With Wearable Sensors: Leave-One-Subject-Out Cross-Validation for Model Selection","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cross-validation; Artificial intelligence; Convolutional neural network; Wearable computer; Machine learning; Deep learning; Artificial neural network; Support vector machine; Subject (documents); Sliding window protocol; Pattern recognition (psychology); Window (computing)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02584512,0.003557441,0.002266095,0.001486698,0.0007608921,0.001117836,0.002094422,0.001957946,0.001468309],"category_scores_gemma":[0.02002301,0.0006414916,0.002196753,0.001068518,0.000976402,0.001025252,0.001989645,0.003043531,0.0009462368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056833,"about_ca_system_score_gemma":0.001780393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032643,"about_ca_topic_score_gemma":0.01014009,"domain_scores_codex":[0.9901851,0.006032667,0.0006772135,0.001652462,0.000966676,0.0004859209],"domain_scores_gemma":[0.9906608,0.005827338,0.0004794866,0.001325145,0.001448698,0.0002585028],"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":[0.002464722,0.001956309,0.02608527,0.0006729851,0.002370795,0.0003867106,0.0003127601,0.4946149,0.008369404,0.001573842,0.01414721,0.447045],"study_design_scores_gemma":[0.00007700932,0.0006379695,0.006114843,0.00008942682,0.0001377236,0.00009372422,0.00006964089,0.9849973,0.004870814,0.001448878,0.001416558,0.00004609171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2568185,0.007557843,0.7244118,0.0004960167,0.0007627922,0.0009614875,0.001581619,0.00540273,0.002007087],"genre_scores_gemma":[0.8397194,0.0008228727,0.1451427,0.0006535167,0.0001372306,0.001365936,0.008377259,0.0005581477,0.003223023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02584512,"threshold_uncertainty_score":0.1366837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.143418748532327,"score_gpt":0.3486028257703112,"score_spread":0.2051840772379842,"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."}}