{"id":"W4416028763","doi":"10.1016/j.scsadv.2025.100005","title":"Federated optimal transport domain adaptation using Internet of Things sensor data for activity recognition","year":2025,"lang":"en","type":"article","venue":"Sustainable Cities and Society Advances","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adaptation (eye); Federated learning; Domain (mathematical analysis); Activity recognition; Internet of Things; Domain adaptation; Information privacy; Data sharing; Information sharing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006015645,0.0001434774,0.0002755762,0.00006008135,0.0003095723,0.0001525314,0.0002564591,0.00008382808,0.000002689961],"category_scores_gemma":[0.00006044553,0.0001487139,0.00008916585,0.0002785945,0.000119608,0.003514735,0.0001583687,0.00009854868,1.2557e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009224778,"about_ca_system_score_gemma":0.0002101389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000546104,"about_ca_topic_score_gemma":0.00002238312,"domain_scores_codex":[0.9988373,0.00007050502,0.0002525771,0.0004258551,0.0001470714,0.0002667177],"domain_scores_gemma":[0.998806,0.0002933429,0.0001939491,0.0002160984,0.0004569346,0.00003365836],"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":[0.001055264,0.0006550986,0.001982959,0.01471163,0.001285209,0.0000351844,0.08686557,0.001570897,0.007825595,0.02734559,0.001695851,0.8549712],"study_design_scores_gemma":[0.001748052,0.0001922846,0.0003756433,0.0004011851,0.00007515008,0.00001393245,0.1802529,0.7801501,0.005073647,0.01760799,0.01362439,0.0004847435],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.216308,0.0004598598,0.7821272,0.0002151719,0.0001212865,0.000416802,0.00004804513,0.00006137134,0.0002422406],"genre_scores_gemma":[0.9150675,0.0001570844,0.08346929,0.0001343339,0.00002896844,0.0000382101,0.00007192828,0.000008445178,0.001024223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8544864,"threshold_uncertainty_score":0.6064377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03938885623586352,"score_gpt":0.2875615964461242,"score_spread":0.2481727402102606,"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."}}