{"id":"W2999955388","doi":"10.3390/s22145222","title":"Personalized Activity Recognition with Deep Triplet Embeddings","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Activity recognition; Pattern recognition (psychology); Cross entropy; Machine learning; Categorical variable; Deep learning; Feature (linguistics); Generalization; Mathematics","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":[0.0004821018,0.0001819021,0.0002537453,0.0001932142,0.0004414802,0.0001419086,0.0004128016,0.00003878543,0.0004006321],"category_scores_gemma":[0.00005346847,0.000180085,0.0001049706,0.0006968532,0.00005366466,0.0004911974,0.0002180535,0.0003162726,0.0001449045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001935625,"about_ca_system_score_gemma":0.00008169026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001333721,"about_ca_topic_score_gemma":0.00005039605,"domain_scores_codex":[0.9978769,0.0004595708,0.0001697673,0.0005506304,0.0006220753,0.0003210356],"domain_scores_gemma":[0.9989308,0.0002364621,0.0001960737,0.0004056044,0.0001216892,0.0001094438],"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":[0.0008798793,0.0008113213,0.001464514,0.00008146705,0.000321309,0.0004664886,0.01605272,0.0006341169,0.01018991,0.001245851,0.003169192,0.9646832],"study_design_scores_gemma":[0.02169978,0.004410576,0.01274138,0.0002474289,0.0002586005,0.008049821,0.01424788,0.5353284,0.03771743,0.005862139,0.3532996,0.006136979],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9402757,0.00002766974,0.05316186,0.001158816,0.0004284394,0.0004233285,0.00003327298,0.0004372791,0.004053602],"genre_scores_gemma":[0.9959624,0.000002386455,0.002263527,0.0003323584,0.00006692587,0.0001267475,0.00001282709,0.00002083751,0.001211939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9585462,"threshold_uncertainty_score":0.7343651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02599975266163782,"score_gpt":0.2359839536501432,"score_spread":0.2099842009885053,"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."}}