{"id":"W4406330970","doi":"10.3390/s25020430","title":"In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models Against Variability","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Robustness (evolution); Inertial measurement unit; Artificial intelligence; Computer science; Machine learning; Variance (accounting); Wearable computer; Statistics; Mathematics","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":[0.006916787,0.001426919,0.0008326842,0.0008577286,0.0004985,0.001247468,0.001180243,0.001345461,0.0009773178],"category_scores_gemma":[0.02082638,0.0004356117,0.0009144394,0.000576167,0.001090814,0.001453159,0.002080362,0.001989816,0.0003987584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006906014,"about_ca_system_score_gemma":0.000988635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005566735,"about_ca_topic_score_gemma":0.004704703,"domain_scores_codex":[0.9982141,0.0006303355,0.0001527526,0.0005405619,0.0002737983,0.0001883566],"domain_scores_gemma":[0.9918858,0.005096721,0.0005897703,0.001410142,0.0007275357,0.0002900621],"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":[0.001460404,0.0004063,0.05045409,0.0002217853,0.0006358126,0.0002386299,0.0002770905,0.7943018,0.008403002,0.002001172,0.003471752,0.1381282],"study_design_scores_gemma":[0.00002412794,0.000301263,0.008535501,0.00003802455,0.00005414841,0.0000845023,0.00007109953,0.9839371,0.003923412,0.00239994,0.0006011162,0.00002973881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7626364,0.002079729,0.2288221,0.0008330755,0.000300995,0.0001072728,0.001023104,0.001784001,0.002413321],"genre_scores_gemma":[0.9838641,0.0001720512,0.01351237,0.000259896,0.00005025564,0.00005189743,0.001219608,0.000129339,0.0007405995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006916787,"threshold_uncertainty_score":0.03657991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02531544020292413,"score_gpt":0.2764825822121709,"score_spread":0.2511671420092468,"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."}}