{"id":"W4408355865","doi":"10.1109/icassp49660.2025.10888558","title":"OSR: Toward Developing Efficient Federated Learning-based Human Activity Recognition using Optimal Server Representations","year":2025,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Activity recognition; Federated learning; Server; Artificial intelligence; Human–computer interaction; Operating system","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":[0.001440837,0.001206898,0.00169875,0.0009035915,0.0003708593,0.001262117,0.002646708,0.00132224,0.001613645],"category_scores_gemma":[0.003972687,0.0004643203,0.0008967603,0.001203098,0.0006934801,0.003197411,0.00237366,0.001741715,0.001705606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007676296,"about_ca_system_score_gemma":0.001434524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004168627,"about_ca_topic_score_gemma":0.003996119,"domain_scores_codex":[0.9986546,0.0003378097,0.00007017089,0.0004823596,0.0002956256,0.0001595343],"domain_scores_gemma":[0.9989911,0.0002564391,0.00009227848,0.0004046785,0.0001787462,0.00007679746],"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":[0.000413192,0.0007246549,0.002817187,0.0001235826,0.0001440741,0.0001354278,0.0001432507,0.2662807,0.01121691,0.007006734,0.01048514,0.7005091],"study_design_scores_gemma":[0.00001421334,0.00003746312,0.0002288118,0.000004770502,0.000007473498,0.00003971472,0.00002221579,0.9916394,0.002711719,0.004558399,0.000727761,0.00000798113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01659328,0.0003088027,0.974554,0.0001931423,0.00004797523,0.00007600284,0.0002484451,0.007275112,0.0007032594],"genre_scores_gemma":[0.5374549,0.000372313,0.454571,0.0004774028,0.00009279879,0.0003070465,0.002515128,0.0002790315,0.003930418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004168627,"threshold_uncertainty_score":0.008288741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09204825444403314,"score_gpt":0.3407623018001397,"score_spread":0.2487140473561065,"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."}}