{"id":"W4393227484","doi":"10.1007/s00521-024-09645-7","title":"Few-shot transfer learning for wearable IMU-based human activity recognition","year":2024,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inertial measurement unit; Computational Science and Engineering; Transfer of learning; Computer science; Wearable computer; Activity recognition; Artificial intelligence; Shot (pellet); Pattern recognition (psychology); Human–computer interaction; Computer vision; Machine learning; Materials science","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":[0.0003148784,0.0001425696,0.0001589194,0.0001183515,0.0006512502,0.0004852744,0.0001927065,0.00006330162,0.000005481001],"category_scores_gemma":[0.00001359823,0.0001480275,0.00009508141,0.0003604632,0.00003602723,0.0002951081,0.0000424215,0.0002602052,0.00002676509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003170891,"about_ca_system_score_gemma":0.00003834299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004282587,"about_ca_topic_score_gemma":0.0000129056,"domain_scores_codex":[0.9988345,0.00009289593,0.0001867121,0.0005289615,0.0001285372,0.000228381],"domain_scores_gemma":[0.9990161,0.0005765447,0.0000364998,0.0001992797,0.00009285496,0.00007873315],"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":[0.000004642217,0.00005780883,0.0001053034,0.0001570166,0.00001631239,0.000001104268,0.0001785436,0.0005534382,0.02094574,0.001305525,0.0001050768,0.9765695],"study_design_scores_gemma":[0.000423735,0.0001416265,0.0008475625,0.0001706461,0.00002669438,0.00002964018,0.00003082111,0.970749,0.009523584,0.001655952,0.01607237,0.0003284192],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2024119,0.0001190301,0.794947,0.0007518605,0.0001071748,0.0005395224,0.000008999832,0.0006193667,0.0004951224],"genre_scores_gemma":[0.9980648,0.000003007502,0.001225449,0.0001054838,0.0002071592,0.0002261602,0.00002120523,0.00001702522,0.0001297508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9762411,"threshold_uncertainty_score":0.6036385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07061333100416113,"score_gpt":0.3227033420955382,"score_spread":0.2520900110913771,"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."}}