{"id":"W4324148957","doi":"10.3390/s23063081","title":"Domain Adaptation Methods for Lab-to-Field Human Context Recognition","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Defense Advanced Research Projects Agency; Worcester Polytechnic Institute","keywords":"Discriminative model; Computer science; Artificial intelligence; Machine learning; Context (archaeology); Domain adaptation; Field (mathematics); Fidelity; Feature learning; Pattern recognition (psychology); Support vector machine; Deep learning; Classifier (UML)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001327576,0.00014933,0.0002287433,0.0003379065,0.0002737296,0.0002057779,0.000316464,0.00009896221,0.00001923961],"category_scores_gemma":[0.0003788383,0.0001612625,0.0001190899,0.0007809325,0.00001905539,0.0003030169,0.0001002833,0.0001033816,0.0007878898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005521123,"about_ca_system_score_gemma":0.00004219644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001468308,"about_ca_topic_score_gemma":0.0002189652,"domain_scores_codex":[0.9983266,0.0003896845,0.0003111721,0.0004669422,0.0001865062,0.0003191236],"domain_scores_gemma":[0.99779,0.001350306,0.0001240468,0.0003788743,0.0002526454,0.0001041589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000222213,0.00002562173,0.00003118831,0.00002872505,0.00003252741,0.000005731595,0.00512184,0.00004095054,0.01547961,0.003528228,0.003063727,0.9726197],"study_design_scores_gemma":[0.003829391,0.001587168,0.002932299,0.0004132219,0.0000576719,0.00008224353,0.01042546,0.1076319,0.1456084,0.1167771,0.6087508,0.00190438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.17204,0.00001002149,0.8224918,0.002207448,0.000750481,0.0007363583,0.00001727917,0.0005870044,0.001159642],"genre_scores_gemma":[0.7870339,0.000002717418,0.2086571,0.001685255,0.0002543776,0.0003312315,0.00005150064,0.00003513335,0.001948754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9707152,"threshold_uncertainty_score":0.9999901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1187211558607009,"score_gpt":0.3840158573548886,"score_spread":0.2652947014941878,"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."}}