{"id":"W3080092352","doi":"10.1007/s12652-021-03462-9","title":"Unsupervised multi-modal representation learning for affective computing with multi-corpus wearable data","year":2021,"lang":"en","type":"preprint","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Generalizability theory; Machine learning; Wearable computer; Deep learning; Representation (politics); Feature learning; Wearable technology; Focus (optics); Modalities; Random forest","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001512809,0.0003643181,0.0007662596,0.000340801,0.0004740756,0.0003888706,0.0005304149,0.0002587759,0.0000690428],"category_scores_gemma":[0.0003779318,0.0003338065,0.0002077449,0.0001802787,0.0001066389,0.000233824,0.0006798464,0.001436894,0.000005554002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009242777,"about_ca_system_score_gemma":0.000171666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00020331,"about_ca_topic_score_gemma":0.00009324533,"domain_scores_codex":[0.9968917,0.000481115,0.001065233,0.0008174828,0.0003413095,0.0004031599],"domain_scores_gemma":[0.9959653,0.000697641,0.001661349,0.0004475413,0.001083364,0.000144827],"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":[0.002322309,0.003547602,0.01571576,0.001520163,0.003654266,0.0005098641,0.106727,0.153358,0.003930799,0.0004991337,0.0002678746,0.7079472],"study_design_scores_gemma":[0.007361756,0.001898689,0.01909962,0.007930478,0.0009025082,0.0009930378,0.05579495,0.8996006,0.004666356,0.0003514946,0.000193485,0.001207005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4522633,0.001065769,0.5448372,0.00003838801,0.001226852,0.000458156,0.00000608524,0.00003536508,0.00006894224],"genre_scores_gemma":[0.930912,0.0003033075,0.06769153,0.00009652123,0.0005647952,0.000004432353,0.0001966251,0.00005471412,0.0001761267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7462426,"threshold_uncertainty_score":0.9999114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.177861679911357,"score_gpt":0.3988628302186612,"score_spread":0.2210011503073042,"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."}}