{"id":"W4402830256","doi":"10.1109/jsen.2024.3464416","title":"CDFL: Efficient Federated Human Activity Recognition Using Contrastive Learning and Deep Clustering","year":2024,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence; Deep learning; Pattern recognition (psychology)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008343453,0.0002242298,0.0002801112,0.0003388709,0.0008702797,0.001915262,0.0001337044,0.0001035663,0.000028356],"category_scores_gemma":[0.00008667852,0.000220079,0.0001065729,0.0003565752,0.00005737363,0.0007946471,0.00007705492,0.0008341108,0.00004033024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002361626,"about_ca_system_score_gemma":0.00008261134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005500844,"about_ca_topic_score_gemma":0.00003764129,"domain_scores_codex":[0.9980764,0.0004023401,0.0003381725,0.000441438,0.000361704,0.000379972],"domain_scores_gemma":[0.9989454,0.0003291455,0.0001989999,0.00007904758,0.0002484578,0.0001989268],"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":[0.00005864362,0.0001087905,0.0002778568,0.0001144825,0.0002649422,0.0009231585,0.003881984,0.01152442,0.4177601,0.00001307955,0.00006171744,0.5650108],"study_design_scores_gemma":[0.0004647557,0.0001117662,0.0005844827,0.0004860644,0.00003007586,0.004743994,0.0002634003,0.9828111,0.009906533,0.00008792624,0.0002035016,0.0003063931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5540113,0.0001321456,0.4445294,0.00007024445,0.0008007202,0.0001046413,0.000001754877,0.0001533579,0.0001964206],"genre_scores_gemma":[0.9980416,0.00001929558,0.001402287,0.00002600255,0.0004086455,0.000002899739,7.264596e-7,0.0000261539,0.00007234498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9712867,"threshold_uncertainty_score":0.9991208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04631548503441584,"score_gpt":0.3028261332030844,"score_spread":0.2565106481686685,"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."}}