{"id":"W3137926756","doi":"10.1007/s11036-021-01741-5","title":"Alternative Deep Learning Architectures for Feature-Level Fusion in Human Activity Recognition","year":2021,"lang":"en","type":"article","venue":"Mobile Networks and Applications","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Concatenation (mathematics); Fuse (electrical); Deep learning; Artificial intelligence; Convolutional neural network; Domain (mathematical analysis); Convolution (computer science); Feature (linguistics); Pattern recognition (psychology); Sensor fusion; Activity recognition; Machine learning; Raw data; Feature learning; Artificial neural network","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":[0.0002155196,0.0001243339,0.000179407,0.00007973962,0.0003284385,0.000143471,0.0001634378,0.00008758861,0.000006358468],"category_scores_gemma":[0.00001955817,0.0001302067,0.00005828678,0.0003528304,0.00003005288,0.0001053706,0.0001362062,0.0002665455,0.000002821078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003969201,"about_ca_system_score_gemma":0.00002063374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000733056,"about_ca_topic_score_gemma":0.0005312787,"domain_scores_codex":[0.9989499,0.0001205135,0.0001529228,0.000471138,0.0001026621,0.0002029038],"domain_scores_gemma":[0.999088,0.0003599485,0.0001196201,0.0002326336,0.0001352653,0.00006446477],"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":[0.000005545924,0.0001118664,0.000591077,0.00001513367,0.00001252744,0.000001739443,0.0001468395,0.01634026,0.001864849,0.000510612,0.00003707369,0.9803625],"study_design_scores_gemma":[0.00203361,0.0002509182,0.03434234,0.0001896492,0.00003228524,0.00008691764,0.0002674471,0.9041271,0.01189456,0.02199232,0.02391784,0.000865043],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1119776,0.0002764368,0.8863448,0.0001322134,0.0000596807,0.0008099817,0.00001593476,0.00007494526,0.0003084037],"genre_scores_gemma":[0.9953083,0.00004168454,0.001685624,0.00007910652,0.0002504312,0.002410807,0.00007779007,0.00001136901,0.0001348505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9794974,"threshold_uncertainty_score":0.5309673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03160857824323783,"score_gpt":0.2845803037102191,"score_spread":0.2529717254669813,"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."}}