{"id":"W4385847493","doi":"10.1145/3582515.3609551","title":"Leveraging Self-Supervised Learning for Human Activity Recognition with Ambient Sensors","year":2023,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi; Université de Montréal; Université de Sherbrooke","funders":"AGE-WELL","keywords":"Activity recognition; Computer science; Transfer of learning; Artificial intelligence; Deep learning; Machine learning; Convolutional neural network; Encoder; Data modeling; Supervised learning; Feature extraction; Pattern recognition (psychology); Artificial neural network; Database","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":[0.0006628432,0.0001991505,0.0002448651,0.0002817394,0.0004888359,0.0003004298,0.000291225,0.00006843911,0.00002980259],"category_scores_gemma":[0.00005186718,0.0001831933,0.0001009096,0.0007673879,0.00001957622,0.0008665572,0.000140988,0.0001960631,0.0002876932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001015032,"about_ca_system_score_gemma":0.00005697603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001775024,"about_ca_topic_score_gemma":0.00007513935,"domain_scores_codex":[0.9982098,0.0001929927,0.0002039918,0.0006168001,0.0003500271,0.0004263332],"domain_scores_gemma":[0.9987879,0.0003861276,0.0001281635,0.0003395117,0.0002462759,0.0001120628],"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":[0.00009329808,0.000398937,0.006358776,0.000310731,0.0003122729,0.00007083215,0.009089975,0.000720808,0.06589945,0.0004969566,0.001858037,0.9143899],"study_design_scores_gemma":[0.004732886,0.001085842,0.01857835,0.0003016887,0.00006444655,0.0001426197,0.001846056,0.8729244,0.08702145,0.001734167,0.009928266,0.001639847],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6638907,0.000001516156,0.3319292,0.0004448796,0.0001475918,0.0004944708,0.000001924988,0.001791488,0.001298219],"genre_scores_gemma":[0.9923547,0.000002452752,0.005977323,0.00009246648,0.00008916637,0.0001828701,0.00002154471,0.00002764576,0.001251832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9127501,"threshold_uncertainty_score":0.7470407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06589076207836665,"score_gpt":0.2764675738616291,"score_spread":0.2105768117832625,"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."}}