{"id":"W3176695070","doi":"10.1504/ijaisc.2020.113475","title":"Deep neural networks for multimodal data fusion and affect recognition","year":2020,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence and Soft Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Multimodality; Computer science; Artificial intelligence; Benchmark (surveying); Autoencoder; Perceptron; Deep learning; Artificial neural network; Machine learning; Feature (linguistics); Multimodal learning; Multilayer perceptron; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007476813,0.0009290074,0.0006750736,0.0006115233,0.0002522512,0.0007193695,0.0007986146,0.0006598187,0.002454026],"category_scores_gemma":[0.001365324,0.0002665691,0.000732664,0.0007282807,0.0003056746,0.0009935427,0.001091808,0.001219664,0.0007760034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005680259,"about_ca_system_score_gemma":0.0003606222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002318488,"about_ca_topic_score_gemma":0.003204947,"domain_scores_codex":[0.9996102,0.00009863496,0.00002342203,0.0001018853,0.0001087123,0.00005713744],"domain_scores_gemma":[0.9997904,0.00006808458,0.00003171902,0.00003234997,0.00006495202,0.00001254505],"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":[0.00028365,0.0002093923,0.002275404,0.0002401024,0.0002793549,0.000184938,0.0001719617,0.1386288,0.03292162,0.009266687,0.007298165,0.8082399],"study_design_scores_gemma":[0.000008346167,0.00007823809,0.002063177,0.00003380085,0.00005531254,0.00007477907,0.00005650701,0.9719957,0.01088851,0.01008816,0.004633429,0.0000240278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03611482,0.003244301,0.9530195,0.0004915061,0.0002201429,0.00008305266,0.0003591038,0.002009386,0.004458209],"genre_scores_gemma":[0.7484497,0.002156895,0.2406046,0.0004009573,0.0001878746,0.0001873494,0.001195399,0.0001335341,0.006683594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002454026,"threshold_uncertainty_score":0.008209467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1621336394391572,"score_gpt":0.3882717262910064,"score_spread":0.2261380868518492,"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."}}